Compare commits

..
1 Commits
Author SHA1 Message Date
Illia PolosukhinandClaude Opus 4.6 c19986f06d Add skill system for shareable prompt-level agent behaviors
Skills are TOML manifests containing instructions injected into the LLM
context. They can be loaded from GitHub repos, URLs, or local files and
activated via /skill commands or custom slash commands from any channel.

Five defense layers protect against malicious skills: static analysis
(Aho-Corasick + skill-specific regex), hard tool whitelist (registry +
execution level), resource restrictions (domains, workspace paths, tool
call budget), BLAKE3 approval pinning, and structural prompt isolation
via <external_skill> wrapper with reassertion block.

Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-02-06 08:51:50 -08:00
272 changed files with 8985 additions and 59750 deletions
-95
View File
@@ -1,95 +0,0 @@
---
description: Scaffold a new SSE event end-to-end (Rust backend to web frontend)
allowed-tools: Read, Edit, Write, Glob, Grep, Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*)
argument-hint: <event_name> [description]
model: opus
---
Add a new SSE event called `$ARGUMENTS` to the IronClaw web gateway. This involves changes across 5 files in a specific order. Follow each step exactly.
## Step 1: Add `StatusUpdate` variant
**File**: `src/channels/channel.rs`
Find the `StatusUpdate` enum and add a new variant. Use the event name in PascalCase. Include any fields the event needs as named fields (not a generic String).
Example for reference (existing variants):
```rust
pub enum StatusUpdate {
Thinking(String),
ToolStarted { name: String },
ToolCompleted { name: String, success: bool },
Status(String),
ApprovalNeeded {
request_id: String,
tool_name: String,
description: String,
parameters: serde_json::Value,
},
}
```
## Step 2: Map to `SseEvent` in web channel
**File**: `src/channels/web/mod.rs`
Find the `send_status` method in the `Channel` impl for `WebChannel`. Add a match arm for the new `StatusUpdate` variant that maps it to an `SseEvent`. The SSE event name should be snake_case.
Look at existing match arms for the pattern. The event data is serialized as JSON.
## Step 3: Add types if needed
**File**: `src/channels/web/types.rs`
If the event carries structured data beyond a simple string, add a serializable DTO struct here. Use `#[derive(Debug, Clone, Serialize, Deserialize)]`. Follow the existing patterns in the file.
## Step 4: Add frontend handler
**File**: `src/channels/web/static/app.js`
In the `connectSSE()` function, add a new `eventSource.addEventListener()` for the snake_case event name. Parse the JSON data and call a handler function.
Create the handler function that updates the DOM. Follow existing patterns:
- `showApproval(data)` for complex card-style UI
- `addMessage(role, content)` for simple text
- `setStatus(text, spinning)` for status bar updates
## Step 5: Add CSS if needed
**File**: `src/channels/web/static/style.css`
If the event needs custom UI (cards, badges, etc.), add styles. Follow the existing naming conventions (`.approval-card`, `.log-entry`, etc.).
## Step 6: Send the event from Rust
Identify where in the backend this event should be triggered. Common locations:
- `src/agent/agent_loop.rs` - During message processing or tool execution
- `src/agent/worker.rs` - During job execution
- `src/agent/heartbeat.rs` - During periodic execution
Use the existing pattern:
```rust
let _ = self.channels.send_status(
&message.channel,
StatusUpdate::YourNewVariant { ... },
&message.metadata,
).await;
```
## Step 7: Quality gate
Run `cargo fmt` and `cargo clippy --all --benches --tests --examples --all-features` to verify the changes compile cleanly.
## Checklist
Before finishing, verify:
- [ ] `StatusUpdate` variant added in `channel.rs`
- [ ] Match arm added in `web/mod.rs` `send_status`
- [ ] DTO added in `types.rs` (if needed)
- [ ] `addEventListener` added in `app.js`
- [ ] Handler function created in `app.js`
- [ ] CSS styles added (if needed)
- [ ] Event sent from appropriate backend location
- [ ] `cargo fmt` clean
- [ ] `cargo clippy` clean
- [ ] Non-web channels unaffected (they ignore unknown StatusUpdate variants)
-382
View File
@@ -1,382 +0,0 @@
---
description: Scaffold a new tool (WASM or built-in Rust) with all boilerplate wired up
allowed-tools: Read, Edit, Write, Glob, Grep, Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*), Bash(cargo component:*), Bash(ls:*), Bash(mkdir:*)
argument-hint: <tool_name> [description]
model: opus
---
Scaffold a new tool called `$ARGUMENTS` for the IronClaw agent. First, determine the tool type and then follow the appropriate path.
## Step 0: Determine tool type
Ask the user which type of tool to create:
- **WASM tool** (recommended) - Sandboxed, dynamically loadable, external API integrations. Lives in `tools-src/<name>/`. This is the right choice for anything that talks to an external service (Notion, GitHub, Discord, etc.).
- **Built-in tool** - Compiled into the main binary. Only for core agent infrastructure (e.g., memory, file ops, shell). Lives in `src/tools/builtin/<name>.rs`.
If the description clearly implies an external service integration, default to WASM. If it's a core agent capability, default to built-in.
---
## Path A: WASM Tool
### A1: Create directory structure
Create `tools-src/<name>/` with:
```
tools-src/<name>/
├── Cargo.toml
├── <name>-tool.capabilities.json
└── src/
├── lib.rs
├── types.rs
└── api.rs
```
### A2: Write `Cargo.toml`
Follow this exact pattern (adjust name and description):
```toml
[package]
name = "<name>-tool"
version = "0.1.0"
edition = "2021"
description = "<Description> tool for IronClaw (WASM component)"
license = "MIT OR Apache-2.0"
publish = false
[lib]
crate-type = ["cdylib"]
[dependencies]
wit-bindgen = "=0.36"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
[profile.release]
opt-level = "s"
lto = true
strip = true
codegen-units = 1
```
### A3: Write `<name>-tool.capabilities.json`
Declare the tool's security requirements. Determine what APIs it needs and create the allowlist. Reference `tools-src/slack/slack-tool.capabilities.json` for the format.
Key sections to include:
- `http.allowlist` - API endpoints (host, path_prefix, methods)
- `http.credentials` - Secret injection config (secret_name, location type: bearer/header/query)
- `http.rate_limit` - requests_per_minute, requests_per_hour
- `http.timeout_secs`
- `secrets.allowed_names` - Which secrets the tool can check existence of
- `auth` - Authentication setup (OAuth or manual token entry)
If the tool needs OAuth, include:
```json
{
"auth": {
"secret_name": "<service>_token",
"display_name": "<Service>",
"oauth": {
"authorization_url": "https://...",
"token_url": "https://...",
"client_id_env": "<SERVICE>_OAUTH_CLIENT_ID",
"client_secret_env": "<SERVICE>_OAUTH_CLIENT_SECRET",
"scopes": [],
"use_pkce": false
},
"env_var": "<SERVICE>_TOKEN"
}
}
```
If no OAuth, include manual setup instructions:
```json
{
"auth": {
"secret_name": "<service>_api_key",
"display_name": "<Service>",
"instructions": "Get your API key from <url>",
"setup_url": "https://...",
"token_hint": "Starts with '<prefix>'",
"env_var": "<SERVICE>_API_KEY"
}
}
```
### A4: Write `src/types.rs`
Define the action enum using serde's tagged enum pattern:
```rust
use serde::{Deserialize, Serialize};
#[derive(Debug, Deserialize)]
#[serde(tag = "action", rename_all = "snake_case")]
pub enum <Name>Action {
// Add variants based on the tool's capabilities.
// Each variant maps to one API operation.
}
```
Add result structs with `#[derive(Debug, Serialize)]`. Use `#[serde(skip_serializing_if = "Option::is_none")]` for optional fields.
### A5: Write `src/api.rs`
Implement the API calls using the host HTTP capability:
```rust
use crate::near::agent::host;
use crate::types::*;
const API_BASE: &str = "https://api.example.com";
fn api_call(method: &str, endpoint: &str, body: Option<&str>) -> Result<String, String> {
let url = format!("{}/{}", API_BASE, endpoint);
let headers = if body.is_some() {
r#"{"Content-Type": "application/json"}"#
} else {
"{}"
};
let body_bytes = body.map(|b| b.as_bytes().to_vec());
host::log(host::LogLevel::Debug, &format!("API: {} {}", method, endpoint));
let response = host::http_request(method, &url, headers, body_bytes.as_deref())?;
if response.status < 200 || response.status >= 300 {
return Err(format!(
"API returned status {}: {}",
response.status,
String::from_utf8_lossy(&response.body)
));
}
String::from_utf8(response.body).map_err(|e| format!("Invalid UTF-8: {}", e))
}
```
Add one function per action variant that calls `api_call` and parses the response into the result structs.
### A6: Write `src/lib.rs`
Wire everything together:
```rust
mod api;
mod types;
use types::<Name>Action;
wit_bindgen::generate!({
world: "sandboxed-tool",
path: "../../wit/tool.wit",
});
struct <Name>Tool;
impl exports::near::agent::tool::Guest for <Name>Tool {
fn execute(req: exports::near::agent::tool::Request) -> exports::near::agent::tool::Response {
match execute_inner(&req.params) {
Ok(result) => exports::near::agent::tool::Response {
output: Some(result),
error: None,
},
Err(e) => exports::near::agent::tool::Response {
output: None,
error: Some(e),
},
}
}
fn schema() -> String {
// Return JSON Schema matching the action enum
todo!("Fill in JSON Schema")
}
fn description() -> String {
"<Description>".to_string()
}
}
fn execute_inner(params: &str) -> Result<String, String> {
// Check required secrets
if !crate::near::agent::host::secret_exists("<secret_name>") {
return Err("<Secret> not configured. Please add the '<secret_name>' secret.".to_string());
}
let action: <Name>Action =
serde_json::from_str(params).map_err(|e| format!("Invalid parameters: {}", e))?;
crate::near::agent::host::log(
crate::near::agent::host::LogLevel::Info,
&format!("Executing action: {:?}", action),
);
let result = match action {
// Dispatch to api:: functions for each variant
};
Ok(result)
}
export!(<Name>Tool);
```
Fill in the `schema()` with a proper JSON Schema using `oneOf` for each action variant. Reference `tools-src/slack/src/lib.rs` for the exact pattern.
### A7: Verify
Run `cargo fmt` in the tool directory. If `cargo-component` is available, run `cargo component build --release` to verify the WASM compiles.
---
## Path B: Built-in Tool
### B1: Create the tool file
Create `src/tools/builtin/<name>.rs` implementing the `Tool` trait:
```rust
use async_trait::async_trait;
use crate::context::JobContext;
use crate::tools::tool::{Tool, ToolError, ToolOutput};
pub struct <Name>Tool;
#[async_trait]
impl Tool for <Name>Tool {
fn name(&self) -> &str {
"<snake_case_name>"
}
fn description(&self) -> &str {
"<Description>"
}
fn parameters_schema(&self) -> serde_json::Value {
serde_json::json!({
"type": "object",
"properties": {
// Define parameters here
},
"required": []
})
}
async fn execute(
&self,
params: serde_json::Value,
_ctx: &JobContext,
) -> Result<ToolOutput, ToolError> {
let start = std::time::Instant::now();
// Extract and validate parameters
// Do the work
// Return result
Ok(ToolOutput::text("result", start.elapsed()))
}
fn requires_sanitization(&self) -> bool {
false // Set true if tool processes external data
}
fn requires_approval(&self) -> bool {
false // Set true if tool is destructive or contacts external services
}
}
```
If the tool needs shared state (HTTP client, config), add a struct field and `new()` constructor:
```rust
pub struct <Name>Tool {
client: reqwest::Client,
}
impl <Name>Tool {
pub fn new() -> Self {
Self {
client: reqwest::Client::builder()
.timeout(std::time::Duration::from_secs(30))
.build()
.expect("Failed to create HTTP client"),
}
}
}
```
### B2: Update `src/tools/builtin/mod.rs`
Add the module declaration and pub use, keeping alphabetical order:
```rust
mod <name>;
pub use <name>::<Name>Tool;
```
### B3: Update `src/tools/registry.rs`
Add the import to the `use crate::tools::builtin::{...}` block and register the tool in the appropriate registration method:
- If it's a core tool: add to `register_builtin_tools()`
- If it needs shared state (workspace, context_manager, etc.): create a new `register_<category>_tools()` method or add to an existing one
- Wire the new registration call in `src/main.rs` if a new method was created
### B4: Add tests
Add a `mod tests {}` block at the bottom of the tool file:
```rust
#[cfg(test)]
mod tests {
use super::*;
use crate::context::JobContext;
fn test_context() -> JobContext {
JobContext::test_default()
}
#[tokio::test]
async fn test_<name>_basic() {
let tool = <Name>Tool::new();
let params = serde_json::json!({ /* test params */ });
let result = tool.execute(params, &test_context()).await;
assert!(result.is_ok());
}
#[tokio::test]
async fn test_<name>_missing_params() {
let tool = <Name>Tool::new();
let params = serde_json::json!({});
let result = tool.execute(params, &test_context()).await;
assert!(matches!(result, Err(ToolError::InvalidParameters(_))));
}
}
```
### B5: Quality gate
Run `cargo fmt` and `cargo clippy --all --benches --tests --examples --all-features`. Fix any issues.
Run the new tests: `cargo test --lib -- builtin::<name>::tests`
---
## Checklist
Before finishing, verify:
- [ ] Tool type chosen (WASM or built-in) and confirmed with user
- [ ] All files created with correct structure
- [ ] For WASM: capabilities.json declares all needed permissions (HTTP, secrets, auth)
- [ ] For WASM: JSON Schema in `schema()` matches the action enum variants
- [ ] For built-in: mod.rs updated with module + pub use
- [ ] For built-in: registry.rs imports and registers the tool
- [ ] For built-in: tests added and passing
- [ ] `cargo fmt` clean
- [ ] `cargo clippy` clean (for built-in) or `cargo component build` clean (for WASM)
-97
View File
@@ -1,97 +0,0 @@
---
description: Fetch a GitHub issue, create a branch, research the codebase, plan the fix, implement with tests, and commit
disable-model-invocation: true
allowed-tools: Bash(gh issue view:*), Bash(gh repo view:*), Bash(git fetch:*), Bash(git checkout:*), Bash(git status:*), Bash(git branch:*), Bash(git add:*), Bash(git commit:*), Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*), Read, Edit, Write, Grep, Glob
argument-hint: "<issue-number or github-issue-url>"
---
# Fix GitHub Issue
## Step 1: Resolve the issue
Parse `$ARGUMENTS` to extract the issue number:
- If it's a URL like `https://github.com/owner/repo/issues/42`, extract `42`.
- If it's a bare number, use it directly.
- If empty, stop and ask the user for an issue number.
Fetch the issue:
```
gh issue view {number} --json title,body,labels,assignees,comments,state
```
If the issue is closed, warn the user and ask if they still want to proceed.
## Step 2: Create a branch
Create a fresh branch off the latest main:
1. Fetch latest: `git fetch origin`
2. Detect default branch: `gh repo view --json defaultBranchRef --jq .defaultBranchRef.name`
3. Create and switch to a new branch: `git checkout -b fix/{number}-{short-slug} origin/{default-branch}`
- `{short-slug}` is 3-5 words from the issue title, lowercase, hyphenated (e.g. `fix/42-idor-workspace-check`)
If the working tree has uncommitted changes, warn the user and stop. Do not stash or discard their work.
## Step 3: Understand the issue
Summarize the issue in 2-3 sentences. Identify:
- **What's broken or missing** (the symptom or feature request)
- **Acceptance criteria** (what "done" looks like, from the issue body or comments)
- **Constraints** (mentioned technologies, backward compatibility, performance requirements)
If the issue is unclear or ambiguous, list the open questions. These will be addressed during planning.
## Step 4: Research the codebase
Before planning, gather context:
1. **Find relevant code** - Search for files, functions, types, and patterns mentioned in the issue. Read them in full.
2. **Trace the flow** - If the issue is about a specific behavior, trace the code path from the entry point (route handler, CLI command, etc.) through to the relevant logic.
3. **Check existing tests** - Find tests related to the affected code. Understand what's already covered.
4. **Check for prior art** - Look for similar patterns in the codebase that solve analogous problems. Prefer consistency with existing patterns.
## Step 5: Enter planning mode
Enter planning mode to design the implementation. The plan MUST cover:
1. **Root cause** (for bugs) or **design approach** (for features)
2. **Files to modify** with specific descriptions of what changes in each
3. **New files** (if any) with justification for why they're needed
4. **Tests to add** - every code path introduced or changed needs a test:
- Happy path (expected input produces expected output)
- Error paths (invalid input, missing data, permission denied)
- Edge cases (empty collections, boundary values, concurrent access)
5. **IronClaw-specific concerns**:
- If the change touches persistence, both database backends must be updated (`postgres.rs` and `libsql_backend.rs`)
- New `Database` trait methods need implementations in both backends
- No `.unwrap()` or `.expect()` in production code
- Use `crate::` imports, not `super::`
- Error types via `thiserror` in `error.rs`
6. **Migration or compatibility concerns** (if any)
Follow the project's CLAUDE.md guidance for architecture decisions.
Wait for user approval before implementing.
## Step 6: Implement
After the plan is approved:
1. Implement each change from the plan.
2. Write all planned tests.
3. Run IronClaw's full quality gate:
- `cargo fmt`
- `cargo clippy --all --benches --tests --examples --all-features` (zero warnings)
- `cargo test --lib` (all tests pass)
4. If any check fails, fix it before proceeding.
Note: Integration tests (`--test workspace_integration`) require PostgreSQL and are expected to fail locally. Only `--lib` test failures are blocking.
## Step 7: Commit and summarize
1. Commit with a descriptive message referencing the issue (e.g. `fix: prevent IDOR in function call outputs (#42)`).
2. Summarize what was done:
- Files changed with line references
- Tests added and what they cover
- Any follow-up work or open questions
-81
View File
@@ -1,81 +0,0 @@
---
description: Respond to PR review comments — triage, plan fixes, implement after confirmation, push, and reply to reviewers
disable-model-invocation: true
allowed-tools: Bash(gh pr list:*), Bash(gh pr comment:*), Bash(gh api:*), Bash(gh repo view:*), Bash(git branch:*), Bash(git status:*), Bash(git add:*), Bash(git commit:*), Bash(git push:*), Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*), Read, Edit, Write, Grep, Glob
argument-hint: "[pr-number (optional, auto-detects from branch)]"
---
# Review and Address PR Comments
## Step 1: Find the PR
If `$ARGUMENTS` is provided, use that as the PR number. Otherwise, detect the PR for the current branch:
```
gh pr list --head $(git branch --show-current) --json number,title,url --jq '.[0]'
```
If no PR is found, tell the user and stop.
## Step 2: Fetch all review comments
Resolve the repo owner and name:
```
gh repo view --json owner,name --jq '"\(.owner.login)/\(.name)"'
```
Fetch the full set of review comments (not issue-level comments):
```
gh api --paginate repos/{owner}/{repo}/pulls/{number}/comments
```
Also fetch the review summaries:
```
gh api --paginate repos/{owner}/{repo}/pulls/{number}/reviews
```
Deduplicate comments that appear multiple times (bots sometimes post the same finding under different IDs). Group by the actual issue being raised, not by comment ID.
## Step 3: Triage and plan
For each unique issue raised in the comments:
1. **Check if already addressed** - Read the current code at the referenced location. If a prior commit already fixed it, note it as "already resolved".
2. **Assess validity** - Determine if the comment identifies a real problem or is a false positive. Be honest about false positives but explain why.
3. **Classify severity** - Critical (security/data loss), High (bugs/broken behavior), Medium (correctness/robustness), Low (style/naming/nits).
4. **Plan the fix** - For each valid unresolved issue, describe the specific code change needed.
Present the plan as a table to the user:
| # | Issue | File:Line | Severity | Status | Planned Fix |
|---|-------|-----------|----------|--------|-------------|
Wait for user confirmation before proceeding to implementation.
## Step 4: Implement fixes
After user confirms:
1. Implement each fix in the plan.
2. Run IronClaw's quality gate to verify nothing breaks:
- `cargo fmt`
- `cargo clippy --all --benches --tests --examples --all-features`
- `cargo test --lib`
3. Commit with a descriptive message referencing the PR review.
4. Push to the branch.
## Step 5: Reply to comments
For each comment addressed, reply on the PR with a short message stating what was fixed and the commit SHA. For false positives or already-resolved items, reply explaining why no change was needed.
## Rules
- Never guess at code you haven't read. Always read the referenced file and line before assessing a comment.
- Group duplicate comments (same issue reported by multiple bots) and reply to all of them.
- Do not make changes beyond what the review comments ask for. Stay focused.
- If a comment suggests a change you disagree with, present your reasoning to the user during the planning phase rather than silently ignoring it.
- Follow IronClaw conventions: no `.unwrap()` in production code, use `crate::` imports, `thiserror` errors.
- If changes touch persistence, verify both database backends are updated.
-245
View File
@@ -1,245 +0,0 @@
---
description: Deep audit of the IronClaw crate for vulnerabilities, bugs, unfinished work, inconsistencies, and oversights
disable-model-invocation: true
allowed-tools: Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*), Bash(cargo audit:*), Bash(git diff:*), Bash(git log:*), Bash(git show:*), Bash(wc:*), Read, Grep, Glob, Task
argument-hint: "[path/to/crate]"
---
# Rust Crate Audit
You are performing a thorough audit of a Rust crate. Your goal is to find every vulnerability, bug, unfinished piece of work, inconsistency, and oversight before it ships. Leave no stone unturned.
## Step 1: Locate the crate
Parse `$ARGUMENTS`:
- If a path is provided, use it as the crate root.
- If empty, use the current working directory.
Verify it's a valid Rust crate by checking for `Cargo.toml`. If not found, stop and ask the user.
## Step 2: Understand the crate
Read `Cargo.toml` to understand:
- Crate name, version, edition
- Dependencies (look for outdated, unmaintained, or suspicious crates)
- Feature flags and their implications
- Build scripts (`build.rs`) if any
Read `CLAUDE.md`, `README.md`, or top-level documentation if present to understand intent and architecture.
Read `src/lib.rs` or `src/main.rs` to get the module tree. Then read each module's `mod.rs` or top-level file to build a mental map of the crate's structure before diving into details.
Read all Rust files (`src/*.rs`) to make sure everything is in context when you are reasoning.
## Step 3: Run the compiler's checks
Run these commands and capture output. Do NOT fix anything, just collect findings:
```
cargo fmt --check 2>&1
```
```
cargo clippy --all --benches --tests --examples --all-features -- -W clippy::all -W clippy::pedantic -W clippy::nursery 2>&1
```
```
cargo test --lib 2>&1
```
If any of these fail, record the failures as findings. If `cargo test` has ignored tests, note which ones and why.
Note: Integration tests (`--test workspace_integration`) require a PostgreSQL database and are expected to fail locally. Only report `--lib` test failures as blocking.
## Step 4: Scan for unfinished work
Search the entire `src/` tree for:
```
todo!
unimplemented!
fixme
FIXME
TODO
HACK
XXX
SAFETY:
stub
placeholder
temporary
```
For each match:
- Is it in production code or test code?
- Is it a genuine incomplete feature or a deliberate placeholder?
- Is there a tracking issue referenced?
- Could this panic at runtime?
Any `todo!()` or `unimplemented!()` in non-test code is **High severity** (runtime panic).
## Step 5: Audit for vulnerabilities and unsafe code
### 5a. Unsafe code
Search for all `unsafe` blocks. For each one:
- Is the safety invariant documented with a `// SAFETY:` comment?
- Is the invariant actually upheld by the surrounding code?
- Could the unsafe block be replaced with a safe alternative?
- Are there any pointer dereferences, transmutes, or FFI calls?
### 5b. Unwrap and panic paths
Search for `.unwrap()`, `.expect(`, `panic!`, `unreachable!` in non-test code. For each:
- Can this actually panic in production?
- Is there a code path that reaches this with None/Err?
- Should it be replaced with proper error handling (`?`, `.ok()`, `.unwrap_or_default()`)?
IronClaw convention: `.unwrap()` and `.expect()` are banned in production code. Any occurrence outside `#[cfg(test)]` blocks is a **High severity** finding.
### 5c. SQL and injection vectors
Search for string formatting used in SQL queries, shell commands, or HTML:
- `format!` used near `.execute(`, `.query(`, `Command::new(`
- String interpolation in query construction vs parameterized queries
- User input flowing into file paths (`Path::new`, `std::fs::`)
IronClaw has two database backends (PostgreSQL and libSQL). Check both for injection vectors.
### 5d. Cryptographic issues
If the crate uses crypto:
- Are comparisons constant-time? (look for `==` on secrets/hashes vs `subtle::ConstantTimeEq`)
- Is randomness from `OsRng` / `thread_rng` and not a fixed seed?
- Are keys/secrets zeroized after use? (`secrecy`, `zeroize` crates)
- Are deprecated algorithms used? (MD5, SHA1 for security, RC4, DES)
### 5e. Resource exhaustion
- Are there unbounded allocations? (`Vec` growing from user input without limits)
- Are there unbounded loops? (retry loops without max attempts)
- Are file reads bounded? (`std::fs::read_to_string` on user-provided paths)
- Are timeouts set on all network operations?
- Are there connection/resource leaks? (opened but never closed, missing `Drop`)
### 5f. Error handling
- Are errors swallowed silently? (`let _ = ...`, `.ok()` discarding errors that matter)
- Do error types carry enough context to debug in production?
- Are there error type mismatches? (returning generic `anyhow::Error` where a typed error would prevent confusion)
- Is `thiserror` used consistently for error types (IronClaw convention)?
## Step 6: Check for inconsistencies
### 6a. Naming conventions
- Are types, functions, modules named consistently? (e.g., mixing `get_` and `fetch_`, `create_` and `new_`)
- Do similar operations follow the same patterns?
### 6b. Duplicate or near-duplicate code
Look for:
- Functions that do nearly the same thing with minor variations (candidates for generics or shared helpers)
- Repeated error mapping patterns that should be extracted
- Copy-pasted SQL queries or string templates with slight differences
- Identical struct definitions or conversion logic in different modules
### 6c. API consistency
- Do similar functions take arguments in the same order?
- Are return types consistent? (e.g., some functions return `Option<T>`, similar ones return `Result<T, E>`)
- Are visibility modifiers consistent? (`pub` where it should be `pub(crate)`, or vice versa)
### 6d. Dead code and unused items
- Are there functions, structs, or modules that nothing references?
- Are there `#[allow(dead_code)]` annotations that should be investigated?
- Are there feature-gated items where the feature is never enabled?
### 6e. Import style
IronClaw convention: use `crate::` imports, not `super::`. Flag any `super::` imports in non-test code.
## Step 7: Inspect for change oversights
### 7a. Partial refactors
- Are there old patterns coexisting with new patterns?
- Are there renamed types/functions where some call sites still use the old name via a compatibility alias?
- Are there comments referencing behavior that no longer exists?
### 7b. Trait implementation gaps
- If a trait is defined, do all intended types implement it?
- Are there `impl` blocks that look incomplete?
- Are `Default` implementations sensible?
IronClaw key traits: `Database` (~60 methods), `Channel`, `Tool`, `LlmProvider`, `SuccessEvaluator`, `EmbeddingProvider`. If any new methods were added to `Database`, verify both `postgres.rs` and `libsql_backend.rs` implement them.
### 7c. Test coverage gaps
- Are there public functions without any test?
- Are there error paths without tests?
- Are there recently-changed functions where the tests still assert old behavior?
### 7d. Documentation drift
- Do doc comments match actual function behavior?
- Are examples in doc comments still valid and compilable?
## Step 8: Dependency audit
Review `Cargo.toml` and `Cargo.lock`:
- Are there duplicate versions of the same crate in the lock file? (potential version conflicts)
- Are there dependencies with known security advisories? Run `cargo audit` to check (install with `cargo install cargo-audit` if not present).
- Are there heavy dependencies used for trivial functionality?
- Are dependency features minimal?
## Step 9: Present findings
Compile all findings into a structured report. Group by severity, then by category.
### Format
For each finding:
```
### [Severity] Category: One-line summary
**Location:** `file_path:line_number`
**Category:** Vulnerability | Bug | Unfinished | Inconsistency | Duplicate | Oversight | Style
**Description:**
Detailed explanation of the issue, why it matters, and how it could manifest.
**Suggested fix:**
Concrete suggestion with code if applicable.
```
### Severity levels
- **Critical**: Security vulnerability, data loss, or crash in production
- **High**: Bug that causes incorrect behavior, `todo!()`/`unimplemented!()` in prod code, or missing validation on trust boundaries
- **Medium**: Inconsistency, duplicate code, incomplete error handling, missing tests for important paths
- **Low**: Naming inconsistency, unnecessary complexity, documentation drift, minor dead code
- **Nit**: Style preference, optional improvement
### Summary table
End with a summary table:
| # | Severity | Category | File:Line | Finding |
|---|----------|----------|-----------|---------|
And a final tally: X Critical, Y High, Z Medium, W Low, V Nit.
## Rules
- Read every file before reporting on it. Never guess about code you haven't seen.
- Be specific. "This might have issues" is worthless. "Line 42 calls `.unwrap()` on a `Result` that returns `Err` when the DB connection is dropped" is useful.
- Distinguish certainty levels: "this IS a bug" vs "this COULD be a bug if X".
- Don't invent problems to look thorough. If the code is solid, say so.
- Focus on substance over style. Don't flag formatting unless it causes real confusion.
- Respect existing project conventions (check CLAUDE.md). Don't flag patterns the project explicitly endorses.
- When in doubt about severity, round up.
- For large crates (>50 files), prioritize: core logic > public API > internal utilities > tests > examples.
- Use the Task tool to parallelize file reading across modules when the crate is large.
- Do NOT fix anything. This is a read-only audit. Report findings for the user to action.
-170
View File
@@ -1,170 +0,0 @@
---
description: Paranoid architect review of a PR — fetches diff, reads changed files, deep review across 6 lenses, posts findings as GitHub comments
disable-model-invocation: true
allowed-tools: Bash(gh pr view:*), Bash(gh pr diff:*), Bash(gh pr comment:*), Bash(gh api:*), Bash(gh repo view:*), Bash(git diff:*), Bash(git log:*), Read, Grep, Glob
argument-hint: "<pr-number or github-pr-url>"
---
# Paranoid Architect Code Review
You are reviewing this PR as a paranoid architect. Your job is to find every bug, vulnerability, race condition, edge case, and undocumented assumption before it ships. Assume adversarial users, concurrent access, and Murphy's law.
## Step 1: Resolve the PR
Parse `$ARGUMENTS` to extract the PR number:
- If it's a URL like `https://github.com/owner/repo/pull/123`, extract `123`.
- If it's a bare number, use it directly.
- If empty, stop and ask the user for a PR number.
Fetch PR metadata (including head commit SHA for posting line comments later):
```
gh pr view {number} --json title,body,baseRefName,headRefName,headRefOid,files,additions,deletions
```
Save the `headRefOid` value, you'll need it as `commit_id` in Step 6.
## Step 2: Load the full diff
```
gh pr diff {number}
```
Also get the list of changed files:
```
gh pr diff {number} --name-only
```
## Step 3: Read every changed file in full
For each changed file, read the ENTIRE current file (not just the diff hunks). You need surrounding context to catch:
- Callers of modified functions that now behave differently
- Trait/interface contracts that the change may violate
- Invariants established elsewhere that the diff breaks
If the PR touches more than 20 files, still read all of them, but process in this priority order: service logic > routes/handlers > models/types > tests > docs. Batch reads in groups of ~20 if needed.
## Step 4: Deep review
Go through the changes with each of these lenses. For every finding, note the file, line range, severity, and a concrete description.
### IronClaw-specific checks
In addition to the general lenses below, check IronClaw conventions (see CLAUDE.md):
- No `.unwrap()` or `.expect()` in production code (tests are fine)
- Use `crate::` imports, not `super::`
- Error types use `thiserror` in `error.rs`
- If the change touches persistence, verify both database backends are updated (PostgreSQL in `postgres.rs` AND libSQL in `libsql_backend.rs`)
- New tools must implement the `Tool` trait correctly and be registered in `registry.rs`
- External tool output must pass through the safety layer
### 4a. Correctness and bugs
- Off-by-one errors, wrong comparison operators, inverted conditions
- Unreachable code, dead branches, impossible match arms
- Type confusion (mixing up IDs, using wrong enum variant)
- Incorrect error propagation (swallowed errors, wrong error type/status code)
- Broken invariants (e.g. uniqueness assumptions violated, ordering assumptions wrong)
- Concurrency issues (TOCTOU, missing locks, race conditions between check and use)
### 4b. Edge cases and failure handling
- What happens with empty input, None/null, zero-length collections?
- What happens when external services fail (DB down, HTTP timeout, malformed response)?
- What happens at integer boundaries (overflow, underflow, i64::MAX)?
- What happens with malformed or adversarial input (invalid UTF-8, huge payloads, deeply nested JSON)?
- Are all error paths tested? Does every `?` propagation make sense?
- Are partial failures handled (e.g. wrote to DB but failed to emit event)?
### 4c. Security (assume a malicious actor)
- **Authentication/Authorization bypass**: Can an unauthenticated user reach this? Can workspace A's user access workspace B's data? Are there IDOR vulnerabilities?
- **Injection**: SQL injection via string interpolation? Command injection? Log injection? Header injection?
- **Data leakage**: Are secrets, PII, or conversation content logged? Returned in error messages? Exposed in API responses?
- **Resource exhaustion / DoS**: Can an attacker send unbounded input? Trigger expensive operations without rate limits? Cause OOM via large allocations?
- **Financial abuse**: Can tokens/credits be consumed without being tracked? Can usage limits be bypassed?
- **Replay / race conditions**: Can the same request be replayed for double-spend? Can concurrent requests bypass limits?
- **Cryptographic issues**: Timing attacks on comparisons? Weak randomness? Missing HMAC verification?
### 4d. Test coverage
- Is every new public function/method tested?
- Are error paths tested (not just happy paths)?
- Are edge cases covered (empty input, boundary values, concurrent access)?
- Do existing tests still make sense with the new changes, or do they assert stale behavior?
- Are there integration/e2e tests for the full flow?
- If a test is missing, describe exactly what test should be written.
### 4e. Documentation and assumptions
- Are new assumptions documented in comments? (e.g. "this field is always non-empty because X")
- Are non-obvious algorithms or business rules explained?
- Are API contracts (request/response shapes, error codes, status codes) documented?
- Are there TODO/FIXME/HACK comments that should be tracked as issues?
### 4f. Architectural concerns
- Does this change follow existing patterns in the codebase, or does it introduce a new one without justification?
- Are there unnecessary abstractions or premature generalizations?
- Is there duplicated logic that should be extracted?
- Are dependencies between modules clean, or does this create circular/tight coupling?
- Will this change make future work harder?
## Step 5: Present findings
Summarize findings to the user as a table:
| # | Severity | Category | File:Line | Finding | Suggested Fix |
|---|----------|----------|-----------|---------|---------------|
Severity levels:
- **Critical**: Security vulnerability, data loss, or financial exploit
- **High**: Bug that will cause incorrect behavior in production
- **Medium**: Robustness issue, missing validation, or incomplete error handling
- **Low**: Style, naming, documentation, or minor improvement
- **Nit**: Optional suggestion, take-it-or-leave-it
Ask the user which findings to post as PR comments. Default: all Critical, High, and Medium.
## Step 6: Post comments on GitHub
Resolve the repo owner and name if not already known:
```
gh repo view --json owner,name --jq '"\(.owner.login)/\(.name)"'
```
For each approved finding, post a review comment on the PR at the specific file and line. Use the `headRefOid` from Step 1 as the `commit_id`:
```
gh api repos/{owner}/{repo}/pulls/{number}/comments \
-f body="..." \
-f path="..." \
-f commit_id="{headRefOid}" \
-F line=... \
-f side="RIGHT"
```
For findings that span multiple locations or are architectural, post as a regular PR comment:
```
gh pr comment {number} --body "..."
```
Format each comment clearly:
- Severity tag (e.g. `**High Severity**`)
- One-line summary
- Detailed explanation of the issue
- Concrete suggestion for the fix (with code if possible)
## Rules
- Read every changed file in full before writing a single finding. Context matters.
- Never post a comment about code you haven't actually read. Verify line numbers against the actual file.
- Be specific. "This might have issues" is useless. "Line 42 returns 404 but should return 400 because X" is useful.
- Distinguish between "this IS a bug" and "this COULD be a bug if X". Be honest about certainty.
- Don't nitpick formatting or style unless it causes actual confusion. Focus on substance.
- If the code is good and you find nothing, say so. Don't invent problems to look thorough.
- Respect the project's CLAUDE.md privacy rules: never include customer data, secrets, or PII in comments.
- When in doubt about severity, round up. It's cheaper to dismiss a false alarm than to miss a real bug.
-25
View File
@@ -1,25 +0,0 @@
---
description: Run the full Rust quality gate (fmt, clippy, tests) before shipping changes
allowed-tools: Bash(cargo fmt:*), Bash(cargo clippy:*), Bash(cargo test:*)
---
Run the IronClaw shipping checklist. This is the mandatory quality gate before any change is considered done.
## Steps
1. **Format**: Run `cargo fmt` to normalize formatting.
2. **Lint**: Run `cargo clippy --all --benches --tests --examples --all-features` and report any warnings or errors. ALL clippy warnings must be resolved before proceeding.
3. **Test**: Run `cargo test --lib` to execute the full library test suite. Report the total pass/fail count.
4. **Summary**: Report results for all three steps. If any step failed, list the specific errors and suggest fixes. Do NOT proceed past a failing step.
If `$ARGUMENTS` is provided, treat it as a specific test filter and run `cargo test --lib -- $ARGUMENTS` instead of the full suite in step 3.
The expected outcome for a clean ship is:
- `cargo fmt` produces no changes
- `cargo clippy` has zero warnings
- All tests pass
Note: Integration tests (`--test workspace_integration`) require a PostgreSQL database and are expected to fail locally. Only report `--lib` test failures as blocking.
-89
View File
@@ -1,89 +0,0 @@
---
description: Trace a data flow or bug through the IronClaw codebase end-to-end
allowed-tools: Read, Glob, Grep, Bash(cargo test:*)
argument-hint: <symptom or feature name>
model: sonnet
---
Trace the flow of `$ARGUMENTS` through the IronClaw codebase. Your job is to map every file and function involved, identify where data transforms or could break, and report the full chain.
## Architecture Reference
IronClaw has three main data flow paths. Identify which one(s) are relevant and trace through them:
### Message Flow (user input to LLM response)
```
Channel (cli/web/wasm) → IncomingMessage
→ Agent::run() message loop (agent_loop.rs)
→ handle_message() dispatches by Submission type
→ SubmissionParser::parse() (submission.rs) classifies input
→ process_user_input() for new turns
→ process_approval() for tool approval responses
→ handle_command() for /commands
→ run_agentic_loop() iterates LLM calls
→ Reasoning::respond_with_tools() (reasoning.rs)
→ LlmProvider::complete_with_tools() (nearai_chat.rs or nearai.rs)
→ Tool execution with approval gating
→ Context message accumulation
→ Response flows back through Channel::send_response()
```
### SSE Event Flow (backend status to web UI)
```
StatusUpdate variant (channel.rs)
→ Channel::send_status() trait method
→ WebChannel::send_status() (web/mod.rs) maps to SseEvent
→ broadcast via tokio::broadcast channel
→ SSE endpoint streams events (web/server.rs)
→ Browser EventSource listener (app.js)
→ DOM update function
→ CSS styling (style.css)
```
### Tool Flow (tool definition to execution)
```
Tool trait impl (tools/builtin/*.rs or tools/mcp/client.rs or tools/wasm/wrapper.rs)
→ ToolRegistry::register() (tools/registry.rs)
→ tool_definitions() builds Vec<ToolDefinition> for LLM
→ ToolDefinition { name, description, parameters } (llm/provider.rs)
→ Serialized to ChatCompletionTool (nearai_chat.rs)
→ LLM returns ToolCall { id, name, arguments }
→ agent_loop.rs executes via execute_chat_tool()
→ Safety layer sanitizes output
→ Result added as ChatMessage::tool_result()
```
## Tracing Instructions
1. **Read** each file in the relevant flow path, focusing on the functions that handle the data.
2. **Identify transforms**: Where does the data change shape? (e.g., `McpTool.input_schema``ToolDefinition.parameters``ChatCompletionTool.function.parameters`)
3. **Identify failure points**: Where could the data be lost, malformed, or misrouted?
4. **Report the chain**: List every file:line involved, what happens at each step, and where the issue (if any) is.
## Key Files Quick Reference
| Area | File | Key Functions |
|------|------|---------------|
| Message dispatch | `src/agent/agent_loop.rs` | `handle_message`, `process_user_input`, `process_approval`, `run_agentic_loop` |
| Input parsing | `src/agent/submission.rs` | `SubmissionParser::parse` |
| LLM reasoning | `src/llm/reasoning.rs` | `respond_with_tools`, `select_tools`, `plan` |
| Chat completions | `src/llm/nearai_chat.rs` | `complete_with_tools`, `From<ChatMessage>` |
| Responses API | `src/llm/nearai.rs` | `complete_with_tools`, `split_messages` |
| Channel trait | `src/channels/channel.rs` | `Channel`, `StatusUpdate`, `IncomingMessage` |
| Web gateway | `src/channels/web/mod.rs` | `send_status`, `send_response` |
| Web server | `src/channels/web/server.rs` | Route handlers, SSE endpoints |
| Web frontend | `src/channels/web/static/app.js` | SSE listeners, DOM builders |
| Tool registry | `src/tools/registry.rs` | `tool_definitions`, `get`, `register` |
| MCP tools | `src/tools/mcp/client.rs` | `McpToolWrapper`, `list_tools`, `call_tool` |
| MCP protocol | `src/tools/mcp/protocol.rs` | `McpTool`, `inputSchema` |
| Safety | `src/safety/sanitizer.rs` | `sanitize_tool_output`, `wrap_for_llm` |
| Session state | `src/agent/session.rs` | `ThreadState`, `Turn`, `PendingApproval` |
## Output Format
Report your findings as:
1. **Flow path**: The specific chain of files and functions involved
2. **Data transforms**: How the data changes at each step
3. **Findings**: Any bugs, missing data, or suspicious patterns
4. **Recommendation**: What to fix or investigate further
-8
View File
@@ -1,8 +0,0 @@
target/
.git/
.env
.env.*
*.md
!CLAUDE.md
node_modules/
tools-src/
+3 -3
View File
@@ -1,15 +1,15 @@
# Database Configuration
DATABASE_URL=postgres://localhost/ironclaw
DATABASE_URL=postgres://ironclaw:password@localhost:5432/ironclaw
DATABASE_POOL_SIZE=10
# LLM Provider (NEAR AI)
# NEAR AI provides a unified interface to all models with user authentication
# Session token is stored in ~/.ironclaw/session.json and managed automatically.
# Session token is stored in ~/.near-agent/session.json and managed automatically.
# On first run, the agent will open a browser for OAuth authentication.
NEARAI_MODEL=claude-3-5-sonnet-20241022
NEARAI_BASE_URL=https://cloud-api.near.ai
NEARAI_AUTH_URL=https://private.near.ai
# NEARAI_SESSION_PATH=~/.ironclaw/session.json # optional, default shown
# NEARAI_SESSION_PATH=~/.near-agent/session.json # optional, default shown
# Channel Configuration
# CLI is always enabled
-22
View File
@@ -1,22 +0,0 @@
name: Code Style
on:
pull_request:
jobs:
codestyle:
name: Code Style (fmt + clippy)
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v6
- name: Install Rust
uses: dtolnay/rust-toolchain@stable
with:
profile: minimal
components: rustfmt, clippy
- uses: Swatinem/rust-cache@v2
- name: Check formatting
run: |
cargo fmt --all -- --check
- name: Check lints (cargo clippy)
run: cargo clippy -- -D warnings
-67
View File
@@ -1,67 +0,0 @@
name: Release-plz
on:
push:
branches:
- main
jobs:
# Release unpublished packages.
release-plz-release:
if: ${{ github.repository_owner == 'nearai' }}
name: Release-plz release
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- &checkout
name: Checkout repository
uses: actions/checkout@v6
with:
fetch-depth: 0
persist-credentials: false
- &install-rust
name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- uses: Swatinem/rust-cache@v2
# Generating a GitHub token, so that PRs and tags created by
# the release-plz-action can trigger actions workflows.
- name: Generate GitHub token
uses: actions/create-github-app-token@v2
id: generate-token
with:
# GitHub App ID secret name
app-id: ${{ secrets.GH_RELEASES_MANAGER_APP_ID }}
# GitHub App private key secret name
private-key: ${{ secrets.GH_RELEASES_MANAGER_APP_PRIVATE_KEY }}
- name: Run release-plz
uses: release-plz/[email protected]
with:
command: release
env:
GITHUB_TOKEN: ${{ steps.generate-token.outputs.token }}
CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
# Create a PR with the new versions and changelog, preparing the next release.
release-plz-pr:
if: ${{ github.repository_owner == 'nearai' }}
name: Release-plz PR
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
concurrency:
group: release-plz-${{ github.ref }}
cancel-in-progress: false
steps:
- *checkout
- *install-rust
- uses: Swatinem/rust-cache@v2
- name: Run release-plz
uses: release-plz/[email protected]
with:
command: release-pr
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
CARGO_REGISTRY_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
-299
View File
@@ -1,299 +0,0 @@
# This file was autogenerated by dist: https://axodotdev.github.io/cargo-dist
#
# Copyright 2022-2024, axodotdev
# SPDX-License-Identifier: MIT or Apache-2.0
#
# CI that:
#
# * checks for a Git Tag that looks like a release
# * builds artifacts with dist (archives, installers, hashes)
# * uploads those artifacts to temporary workflow zip
# * on success, uploads the artifacts to a GitHub Release
#
# Note that the GitHub Release will be created with a generated
# title/body based on your changelogs.
name: Release
permissions:
"contents": "write"
# This task will run whenever you push a git tag that looks like a version
# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
#
# If PACKAGE_NAME is specified, then the announcement will be for that
# package (erroring out if it doesn't have the given version or isn't dist-able).
#
# If PACKAGE_NAME isn't specified, then the announcement will be for all
# (dist-able) packages in the workspace with that version (this mode is
# intended for workspaces with only one dist-able package, or with all dist-able
# packages versioned/released in lockstep).
#
# If you push multiple tags at once, separate instances of this workflow will
# spin up, creating an independent announcement for each one. However, GitHub
# will hard limit this to 3 tags per commit, as it will assume more tags is a
# mistake.
#
# If there's a prerelease-style suffix to the version, then the release(s)
# will be marked as a prerelease.
on:
push:
tags:
- '**[0-9]+.[0-9]+.[0-9]+*'
jobs:
# Run 'dist plan' (or host) to determine what tasks we need to do
plan:
runs-on: "ubuntu-22.04"
outputs:
val: ${{ steps.plan.outputs.manifest }}
tag: ${{ !github.event.pull_request && github.ref_name || '' }}
tag-flag: ${{ !github.event.pull_request && format('--tag={0}', github.ref_name) || '' }}
publishing: ${{ !github.event.pull_request }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install dist
# we specify bash to get pipefail; it guards against the `curl` command
# failing. otherwise `sh` won't catch that `curl` returned non-0
shell: bash
run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.30.3/cargo-dist-installer.sh | sh"
- name: Cache dist
uses: actions/upload-artifact@v4
with:
name: cargo-dist-cache
path: ~/.cargo/bin/dist
# sure would be cool if github gave us proper conditionals...
# so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
# functionality based on whether this is a pull_request, and whether it's from a fork.
# (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
# but also really annoying to build CI around when it needs secrets to work right.)
- id: plan
run: |
dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
echo "dist ran successfully"
cat plan-dist-manifest.json
echo "manifest=$(jq -c "." plan-dist-manifest.json)" >> "$GITHUB_OUTPUT"
- name: "Upload dist-manifest.json"
uses: actions/upload-artifact@v4
with:
name: artifacts-plan-dist-manifest
path: plan-dist-manifest.json
# Build and packages all the platform-specific things
build-local-artifacts:
name: build-local-artifacts (${{ join(matrix.targets, ', ') }})
# Let the initial task tell us to not run (currently very blunt)
needs:
- plan
if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }}
strategy:
fail-fast: false
# Target platforms/runners are computed by dist in create-release.
# Each member of the matrix has the following arguments:
#
# - runner: the github runner
# - dist-args: cli flags to pass to dist
# - install-dist: expression to run to install dist on the runner
#
# Typically there will be:
# - 1 "global" task that builds universal installers
# - N "local" tasks that build each platform's binaries and platform-specific installers
matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }}
runs-on: ${{ matrix.runner }}
container: ${{ matrix.container && matrix.container.image || null }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json
steps:
- name: enable windows longpaths
run: |
git config --global core.longpaths true
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install Rust non-interactively if not already installed
if: ${{ matrix.container }}
run: |
if ! command -v cargo > /dev/null 2>&1; then
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
echo "$HOME/.cargo/bin" >> $GITHUB_PATH
fi
- uses: swatinem/rust-cache@v2
with:
key: ${{ join(matrix.targets, '-') }}
cache-provider: ${{ matrix.cache_provider }}
- name: Install dist
run: ${{ matrix.install_dist.run }}
# Get the dist-manifest
- name: Fetch local artifacts
uses: actions/download-artifact@v4
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- name: Install dependencies
run: |
${{ matrix.packages_install }}
- name: Build artifacts
run: |
# Actually do builds and make zips and whatnot
dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
echo "dist ran successfully"
- id: cargo-dist
name: Post-build
# We force bash here just because github makes it really hard to get values up
# to "real" actions without writing to env-vars, and writing to env-vars has
# inconsistent syntax between shell and powershell.
shell: bash
run: |
# Parse out what we just built and upload it to scratch storage
echo "paths<<EOF" >> "$GITHUB_OUTPUT"
dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT"
echo "EOF" >> "$GITHUB_OUTPUT"
cp dist-manifest.json "$BUILD_MANIFEST_NAME"
- name: "Upload artifacts"
uses: actions/upload-artifact@v4
with:
name: artifacts-build-local-${{ join(matrix.targets, '_') }}
path: |
${{ steps.cargo-dist.outputs.paths }}
${{ env.BUILD_MANIFEST_NAME }}
# Build and package all the platform-agnostic(ish) things
build-global-artifacts:
needs:
- plan
- build-local-artifacts
runs-on: "ubuntu-22.04"
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
BUILD_MANIFEST_NAME: target/distrib/global-dist-manifest.json
steps:
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install cached dist
uses: actions/download-artifact@v4
with:
name: cargo-dist-cache
path: ~/.cargo/bin/
- run: chmod +x ~/.cargo/bin/dist
# Get all the local artifacts for the global tasks to use (for e.g. checksums)
- name: Fetch local artifacts
uses: actions/download-artifact@v4
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- id: cargo-dist
shell: bash
run: |
dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
echo "dist ran successfully"
# Parse out what we just built and upload it to scratch storage
echo "paths<<EOF" >> "$GITHUB_OUTPUT"
jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
echo "EOF" >> "$GITHUB_OUTPUT"
cp dist-manifest.json "$BUILD_MANIFEST_NAME"
- name: "Upload artifacts"
uses: actions/upload-artifact@v4
with:
name: artifacts-build-global
path: |
${{ steps.cargo-dist.outputs.paths }}
${{ env.BUILD_MANIFEST_NAME }}
# Determines if we should publish/announce
host:
needs:
- plan
- build-local-artifacts
- build-global-artifacts
# Only run if we're "publishing", and only if plan, local and global didn't fail (skipped is fine)
if: ${{ always() && needs.plan.result == 'success' && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
runs-on: "ubuntu-22.04"
outputs:
val: ${{ steps.host.outputs.manifest }}
steps:
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
- name: Install cached dist
uses: actions/download-artifact@v4
with:
name: cargo-dist-cache
path: ~/.cargo/bin/
- run: chmod +x ~/.cargo/bin/dist
# Fetch artifacts from scratch-storage
- name: Fetch artifacts
uses: actions/download-artifact@v4
with:
pattern: artifacts-*
path: target/distrib/
merge-multiple: true
- id: host
shell: bash
run: |
dist host ${{ needs.plan.outputs.tag-flag }} --steps=upload --steps=release --output-format=json > dist-manifest.json
echo "artifacts uploaded and released successfully"
cat dist-manifest.json
echo "manifest=$(jq -c "." dist-manifest.json)" >> "$GITHUB_OUTPUT"
- name: "Upload dist-manifest.json"
uses: actions/upload-artifact@v4
with:
# Overwrite the previous copy
name: artifacts-dist-manifest
path: dist-manifest.json
# Create a GitHub Release while uploading all files to it
- name: "Download GitHub Artifacts"
uses: actions/download-artifact@v4
with:
pattern: artifacts-*
path: artifacts
merge-multiple: true
- name: Cleanup
run: |
# Remove the granular manifests
rm -f artifacts/*-dist-manifest.json
- name: Create GitHub Release
env:
PRERELEASE_FLAG: "${{ fromJson(steps.host.outputs.manifest).announcement_is_prerelease && '--prerelease' || '' }}"
ANNOUNCEMENT_TITLE: "${{ fromJson(steps.host.outputs.manifest).announcement_title }}"
ANNOUNCEMENT_BODY: "${{ fromJson(steps.host.outputs.manifest).announcement_github_body }}"
RELEASE_COMMIT: "${{ github.sha }}"
run: |
# Write and read notes from a file to avoid quoting breaking things
echo "$ANNOUNCEMENT_BODY" > $RUNNER_TEMP/notes.txt
gh release create "${{ needs.plan.outputs.tag }}" --target "$RELEASE_COMMIT" $PRERELEASE_FLAG --title "$ANNOUNCEMENT_TITLE" --notes-file "$RUNNER_TEMP/notes.txt" artifacts/*
announce:
needs:
- plan
- host
# use "always() && ..." to allow us to wait for all publish jobs while
# still allowing individual publish jobs to skip themselves (for prereleases).
# "host" however must run to completion, no skipping allowed!
if: ${{ always() && needs.host.result == 'success' }}
runs-on: "ubuntu-22.04"
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
steps:
- uses: actions/checkout@v4
with:
persist-credentials: false
submodules: recursive
-21
View File
@@ -1,21 +0,0 @@
name: Run Tests
on:
pull_request:
push:
branches:
- main
jobs:
tests:
name: Run Tests
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v6
- name: Install Rust
uses: dtolnay/rust-toolchain@stable
with:
profile: minimal
- uses: Swatinem/rust-cache@v2
- name: Run Tests
run: cargo test --all-features -- --nocapture
-12
View File
@@ -1,18 +1,6 @@
.env
.env.local
.env.*
!.env.example
# Claude Code worktrees
.claude/worktrees/
# Sidecar tool data
.sidecar/
.todos/
target/
# WASM build artifacts (loaded from disk, not bundled)
*.wasm
-6
View File
@@ -1,6 +0,0 @@
# Agent Rules
## Feature Parity Update Policy
- If you change implementation status for any feature tracked in `FEATURE_PARITY.md`, update that file in the same branch.
- Do not open a PR that changes feature behavior without checking `FEATURE_PARITY.md` for needed status updates (`❌`, `🚧`, `✅`, notes, and priorities).
-171
View File
@@ -1,171 +0,0 @@
# Changelog
All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
## [0.5.0](https://github.com/nearai/ironclaw/compare/v0.4.0...v0.5.0) - 2026-02-17
### Added
- add cooldown management to FailoverProvider ([#114](https://github.com/nearai/ironclaw/pull/114))
## [0.4.0](https://github.com/nearai/ironclaw/compare/v0.3.0...v0.4.0) - 2026-02-17
### Added
- move per-invocation approval check into Tool trait ([#119](https://github.com/nearai/ironclaw/pull/119))
- add polished boot screen on CLI startup ([#118](https://github.com/nearai/ironclaw/pull/118))
- Add lifecycle hooks system with 6 interception points ([#18](https://github.com/nearai/ironclaw/pull/18))
### Other
- remove accidentally committed .sidecar and .todos directories ([#123](https://github.com/nearai/ironclaw/pull/123))
## [0.3.0](https://github.com/nearai/ironclaw/compare/v0.2.0...v0.3.0) - 2026-02-17
### Added
- direct api key and cheap model ([#116](https://github.com/nearai/ironclaw/pull/116))
## [0.2.0](https://github.com/nearai/ironclaw/compare/v0.1.3...v0.2.0) - 2026-02-16
### Added
- mark Ollama + OpenAI-compatible as implemented ([#102](https://github.com/nearai/ironclaw/pull/102))
- multi-provider inference + libSQL onboarding selection ([#92](https://github.com/nearai/ironclaw/pull/92))
- add multi-provider LLM failover with retry backoff ([#28](https://github.com/nearai/ironclaw/pull/28))
- add libSQL/Turso embedded database backend ([#47](https://github.com/nearai/ironclaw/pull/47))
- Move debug log truncation from agent loop to REPL channel ([#65](https://github.com/nearai/ironclaw/pull/65))
### Fixed
- shell destructive-command check bypassed by Value::Object arguments ([#72](https://github.com/nearai/ironclaw/pull/72))
- propagate real tool_call_id instead of hardcoded placeholder ([#73](https://github.com/nearai/ironclaw/pull/73))
- Fix wasm tool schemas and runtime ([#42](https://github.com/nearai/ironclaw/pull/42))
- flatten tool messages for NEAR AI cloud-api compatibility ([#41](https://github.com/nearai/ironclaw/pull/41))
- security hardening across all layers ([#35](https://github.com/nearai/ironclaw/pull/35))
### Other
- Explicitly enable cargo-dist caching for binary artifacts building
- Skip building binary artifacts on every PR
- add module specification rules to CLAUDE.md
- add setup/onboarding specification (src/setup/README.md)
- deduplicate tool code and remove dead stubs ([#98](https://github.com/nearai/ironclaw/pull/98))
- Reformat architecture diagram in README ([#64](https://github.com/nearai/ironclaw/pull/64))
- Add review discipline guidelines to CLAUDE.md ([#68](https://github.com/nearai/ironclaw/pull/68))
- Bump MSRV to 1.92, add GCP deployment files ([#40](https://github.com/nearai/ironclaw/pull/40))
- Add OpenAI-compatible HTTP API (/v1/chat/completions, /v1/models) ([#31](https://github.com/nearai/ironclaw/pull/31))
## [0.1.3](https://github.com/nearai/ironclaw/compare/v0.1.2...v0.1.3) - 2026-02-12
### Other
- Enabled builds caching during CI/CD
- Disabled npm publishing as the name is already taken
## [0.1.2](https://github.com/nearai/ironclaw/compare/v0.1.1...v0.1.2) - 2026-02-12
### Other
- Added Installation instructions for the pre-built binaries
- Disabled Windows ARM64 builds as auto-updater [provided by cargo-dist] does not support this platform yet and it is not a common platform for us to support
## [0.1.1](https://github.com/nearai/ironclaw/compare/v0.1.0...v0.1.1) - 2026-02-12
### Other
- Renamed the secrets in release-plz.yml to match the configuration
- Make sure that the binaries release CD it kicking in after release-plz
## [0.1.0](https://github.com/nearai/ironclaw/releases/tag/v0.1.0) - 2026-02-12
### Added
- Add multi-provider LLM support via rig-core adapter ([#36](https://github.com/nearai/ironclaw/pull/36))
- Sandbox jobs ([#4](https://github.com/nearai/ironclaw/pull/4))
- Add Google Suite & Telegram WASM tools ([#9](https://github.com/nearai/ironclaw/pull/9))
- Improve CLI ([#5](https://github.com/nearai/ironclaw/pull/5))
### Fixed
- resolve runtime panic in Linux keychain integration ([#32](https://github.com/nearai/ironclaw/pull/32))
### Other
- Skip release-plz on forks
- Upgraded release-plz CD pipeline
- Added CI/CD and release pipelines ([#45](https://github.com/nearai/ironclaw/pull/45))
- DM pairing + Telegram channel improvements ([#17](https://github.com/nearai/ironclaw/pull/17))
- Fixes build, adds missing sse event and correct command ([#11](https://github.com/nearai/ironclaw/pull/11))
- Codex/feature parity pr hook ([#6](https://github.com/nearai/ironclaw/pull/6))
- Add WebSocket gateway and control plane ([#8](https://github.com/nearai/ironclaw/pull/8))
- select bundled Telegram channel and auto-install ([#3](https://github.com/nearai/ironclaw/pull/3))
- Adding skills for reusable work
- Fix MCP tool calls, approval loop, shutdown, and improve web UI
- Add auth mode, fix MCP token handling, and parallelize startup loading
- Merge remote-tracking branch 'origin/main' into ui
- Adding web UI
- Rename `setup` CLI command to `onboard` for compatibility
- Add in-chat extension discovery, auth, and activation system
- Add Telegram typing indicator via WIT on-status callback
- Add proactivity features: memory CLI, session pruning, self-repair notifications, slash commands, status diagnostics, context warnings
- Add hosted MCP server support with OAuth 2.1 and token refresh
- Add interactive setup wizard and persistent settings
- Rebrand to IronClaw with security-first mission
- Fix build_software tool stuck in planning mode loop
- Enable sandbox by default
- Fix Telegram Markdown formatting and clarify tool/memory distinctions
- Simplify Telegram channel config with host-injected tunnel/webhook settings
- Apply Telegram channel learnings to WhatsApp implementation
- Merge remote-tracking branch 'origin/main'
- Docker file for sandbox
- Replace hardcoded intent patterns with job tools
- Fix router test to match intentional job creation patterns
- Add Docker execution sandbox for secure shell command isolation
- Move setup wizard credentials to database storage
- Add interactive setup wizard for first-run configuration
- Add Telegram Bot API channel as WASM module
- Add OpenClaw feature parity tracking matrix
- Add Chat Completions API support and expand REPL debugging
- Implementing channels to be handled in wasm
- Support non interactive mode and model selection
- Implement tool approval, fix tool definition refresh, and wire embeddings
- Tool use
- Wiring more
- Add heartbeat integration, planning phase, and auto-repair
- Login flow
- Extend support for session management
- Adding builder capability
- Load tools at launch
- Fix multiline message rendering in TUI
- Parse NEAR AI alternative response format with output field
- Handle NEAR AI plain text responses
- Disable mouse capture to allow text selection in TUI
- Add verbose logging to debug empty NEAR AI responses
- Improve NEAR AI response parsing for varying response formats
- Show status/thinking messages in chat window, debug empty responses
- Add timeout and logging to NEAR AI provider
- Add status updates to show agent thinking/processing state
- Add CLI subcommands for WASM tool management
- Fix TUI shutdown: send /shutdown message and handle in agent loop
- Remove SimpleCliChannel, add Ctrl+D twice quit, redirect logs to TUI
- Fix TuiChannel integration and enable in main.rs
- Integrate Codex patterns: task scheduler, TUI, sessions, compaction
- Adding LICENSE
- Add README with IronClaw branding
- Add WASM sandbox secure API extension
- Wire database Store into agent loop
- Implementing WASM runtime
- Add workspace integration tests
- Compact memory_tree output format
- Replace memory_list with memory_tree tool
- Simplify workspace to path-based storage, remove legacy code
- Add NEAR AI chat-api as default LLM provider
- Add CLAUDE.md project documentation
- Add workspace and memory system (OpenClaw-inspired)
- Initial implementation of the agent framework
+19 -261
View File
@@ -11,13 +11,8 @@
- **Always available** - Multi-channel access with proactive background execution
### Features
- **Multi-channel input**: TUI (Ratatui), HTTP webhooks, WASM channels (Telegram, Slack), web gateway
- **Multi-channel input**: TUI (Ratatui), HTTP webhooks, Telegram, WhatsApp, Slack (WASM channels)
- **Parallel job execution** with state machine and self-repair for stuck jobs
- **Sandbox execution**: Docker container isolation with orchestrator/worker pattern
- **Claude Code mode**: Delegate jobs to Claude CLI inside containers
- **Routines**: Scheduled (cron) and reactive (event, webhook) task execution
- **Web gateway**: Browser UI with SSE/WebSocket real-time streaming
- **Extension management**: Install, auth, activate MCP/WASM extensions
- **Extensible tools**: Built-in tools, WASM sandbox, MCP client, dynamic builder
- **Persistent memory**: Workspace with hybrid search (FTS + vector via RRF)
- **Prompt injection defense**: Sanitizer, validator, policy rules, leak detection
@@ -64,9 +59,7 @@ src/
│ ├── context_monitor.rs # Memory pressure detection
│ ├── undo.rs # Turn-based undo/redo with checkpoints
│ ├── submission.rs # Submission parsing (undo, redo, compact, clear, etc.)
── task.rs # Sub-task execution framework
│ ├── routine.rs # Routine types (Trigger, Action, Guardrails)
│ └── routine_engine.rs # Routine execution (cron ticker, event matcher)
── task.rs # Sub-task execution framework
├── channels/ # Multi-channel input
│ ├── channel.rs # Channel trait, IncomingMessage, OutgoingResponse
@@ -79,33 +72,8 @@ src/
│ │ ├── overlay.rs # Approval overlays
│ │ └── composer.rs # Message composition
│ ├── http.rs # HTTP webhook (axum) with secret validation
│ ├── repl.rs # Simple REPL (for testing)
── web/ # Web gateway (browser UI)
│ │ ├── mod.rs # Gateway builder, startup
│ │ ├── server.rs # Axum router, 40+ API endpoints
│ │ ├── sse.rs # SSE broadcast manager
│ │ ├── ws.rs # WebSocket gateway + connection tracking
│ │ ├── types.rs # Request/response types, SseEvent enum
│ │ ├── auth.rs # Bearer token auth middleware
│ │ ├── log_layer.rs # Tracing layer for log streaming
│ │ └── static/ # HTML, CSS, JS (single-page app)
│ └── wasm/ # WASM channel runtime
│ ├── mod.rs
│ ├── bundled.rs # Bundled channel discovery
│ └── wrapper.rs # Channel trait wrapper for WASM modules
├── orchestrator/ # Internal HTTP API for sandbox containers
│ ├── mod.rs
│ ├── api.rs # Axum endpoints (LLM proxy, events, prompts)
│ ├── auth.rs # Per-job bearer token store
│ └── job_manager.rs # Container lifecycle (create, stop, cleanup)
├── worker/ # Runs inside Docker containers
│ ├── mod.rs
│ ├── runtime.rs # Worker execution loop (tool calls, LLM)
│ ├── claude_bridge.rs # Claude Code bridge (spawns claude CLI)
│ ├── api.rs # HTTP client to orchestrator
│ └── proxy_llm.rs # LlmProvider that proxies through orchestrator
│ ├── slack.rs # Stub
── telegram.rs # Stub
├── safety/ # Prompt injection defense
│ ├── sanitizer.rs # Pattern detection, content escaping
@@ -128,9 +96,6 @@ src/
│ │ ├── file.rs # ReadFile, WriteFile, ListDir, ApplyPatch
│ │ ├── shell.rs # Shell command execution
│ │ ├── memory.rs # Memory tools (search, write, read, tree)
│ │ ├── job.rs # CreateJob, ListJobs, JobStatus, CancelJob
│ │ ├── routine.rs # routine_create/list/update/delete/history
│ │ ├── extension_tools.rs # Extension install/auth/activate/remove
│ │ └── marketplace.rs, ecommerce.rs, taskrabbit.rs, restaurant.rs (stubs)
│ ├── builder/ # Dynamic tool building
│ │ ├── core.rs # BuildRequirement, SoftwareType, Language
@@ -151,12 +116,6 @@ src/
│ ├── rate_limiter.rs # Per-tool rate limiting
│ └── storage.rs # Linear memory persistence
├── db/ # Database abstraction layer
│ ├── mod.rs # Database trait (~60 async methods)
│ ├── postgres.rs # PostgreSQL backend (delegates to Store + Repository)
│ ├── libsql_backend.rs # libSQL/Turso backend (embedded SQLite)
│ └── libsql_migrations.rs # SQLite-dialect schema (idempotent)
├── workspace/ # Persistent memory system (OpenClaw-inspired)
│ ├── mod.rs # Workspace struct, memory operations
│ ├── document.rs # MemoryDocument, MemoryChunk, WorkspaceEntry
@@ -192,15 +151,10 @@ src/
## Key Patterns
### Architecture
When designing new features or systems, always prefer generic/extensible architectures over hardcoding specific integrations. Ask clarifying questions about the desired abstraction level before implementing.
### Error Handling
- Use `thiserror` for error types in `error.rs`
- Never use `.unwrap()` or `.expect()` in production code (tests are fine)
- Never use `.unwrap()` in production code (tests are fine)
- Map errors with context: `.map_err(|e| SomeError::Variant { reason: e.to_string() })?`
- Before committing, grep for `.unwrap()` and `.expect(` in changed files to catch violations mechanically
### Async
- All I/O is async with tokio
@@ -208,7 +162,6 @@ When designing new features or systems, always prefer generic/extensible archite
- Use `RwLock` for concurrent read/write access
### Traits for Extensibility
- `Database` - Add new database backends (must implement all ~60 methods)
- `Channel` - Add new input sources
- `Tool` - Add new capabilities
- `LlmProvider` - Add new LLM backends
@@ -256,12 +209,7 @@ Pending -> InProgress -> Completed -> Submitted -> Accepted
Environment variables (see `.env.example`):
```bash
# Database backend (default: postgres)
DATABASE_BACKEND=postgres # or "libsql" / "turso"
DATABASE_URL=postgres://user:pass@localhost/ironclaw
LIBSQL_PATH=~/.ironclaw/ironclaw.db # libSQL local path (default)
# LIBSQL_URL=libsql://xxx.turso.io # Turso cloud (optional)
# LIBSQL_AUTH_TOKEN=xxx # Required with LIBSQL_URL
# NEAR AI (required)
NEARAI_SESSION_TOKEN=sess_...
@@ -284,30 +232,6 @@ HEARTBEAT_ENABLED=true
HEARTBEAT_INTERVAL_SECS=1800 # 30 minutes
HEARTBEAT_NOTIFY_CHANNEL=tui
HEARTBEAT_NOTIFY_USER=default
# Web gateway
GATEWAY_ENABLED=true
GATEWAY_HOST=127.0.0.1
GATEWAY_PORT=3001
GATEWAY_AUTH_TOKEN=changeme # Required for API access
GATEWAY_USER_ID=default
# Docker sandbox
SANDBOX_ENABLED=true
SANDBOX_IMAGE=ironclaw-worker:latest
SANDBOX_MEMORY_LIMIT_MB=512
SANDBOX_TIMEOUT_SECS=1800
# Claude Code mode (runs inside sandbox containers)
CLAUDE_CODE_ENABLED=false
CLAUDE_CODE_MODEL=claude-sonnet-4-20250514
CLAUDE_CODE_MAX_TURNS=50
CLAUDE_CODE_CONFIG_DIR=/home/worker/.claude
# Routines (scheduled/reactive execution)
ROUTINES_ENABLED=true
ROUTINES_CRON_INTERVAL=60 # Tick interval in seconds
ROUTINES_MAX_CONCURRENT=3
```
### NEAR AI Provider
@@ -321,51 +245,7 @@ Session tokens have the format `sess_xxx` (37 characters). They are authenticate
## Database
IronClaw supports two database backends, selected at compile time via Cargo feature flags and at runtime via the `DATABASE_BACKEND` environment variable.
**IMPORTANT: All new features that touch persistence MUST support both backends.** Implement the operation as a method on the `Database` trait in `src/db/mod.rs`, then add the implementation in both `src/db/postgres.rs` (delegate to Store/Repository) and `src/db/libsql_backend.rs` (native SQL).
### Backends
| Backend | Feature Flag | Default | Use Case |
|---------|-------------|---------|----------|
| PostgreSQL | `postgres` (default) | Yes | Production, existing deployments |
| libSQL/Turso | `libsql` | No | Zero-dependency local mode, edge, Turso cloud |
```bash
# Build with PostgreSQL only (default)
cargo build
# Build with libSQL only
cargo build --no-default-features --features libsql
# Build with both backends available
cargo build --features "postgres,libsql"
```
### Database Trait
The `Database` trait (`src/db/mod.rs`) defines ~60 async methods covering all persistence:
- Conversations, messages, metadata
- Jobs, actions, LLM calls, estimation snapshots
- Sandbox jobs, job events
- Routines, routine runs
- Tool failures, settings
- Workspace: documents, chunks, hybrid search
Both backends implement this trait. PostgreSQL delegates to the existing `Store` + `Repository`. libSQL implements native SQLite-dialect SQL.
### Schema
**PostgreSQL:** `migrations/V1__initial.sql` (351 lines). Uses pgvector for embeddings, tsvector for FTS, PL/pgSQL functions. Managed by `refinery`.
**libSQL:** `src/db/libsql_migrations.rs` (consolidated schema, ~480 lines). Translates PG types:
- `UUID` -> `TEXT`, `TIMESTAMPTZ` -> `TEXT` (ISO-8601), `JSONB` -> `TEXT`
- `VECTOR(1536)` -> `F32_BLOB(1536)` with `libsql_vector_idx`
- `tsvector`/`ts_rank_cd` -> FTS5 virtual table with sync triggers
- PL/pgSQL functions -> SQLite triggers
**Tables (both backends):**
Single migration in `migrations/V1__initial.sql`. Tables:
**Core:**
- `conversations` - Multi-channel conversation tracking
@@ -377,41 +257,12 @@ Both backends implement this trait. PostgreSQL delegates to the existing `Store`
**Workspace/Memory:**
- `memory_documents` - Flexible path-based files (e.g., "context/vision.md", "daily/2024-01-15.md")
- `memory_chunks` - Chunked content with FTS and vector indexes
- `memory_chunks` - Chunked content with FTS (tsvector) and vector (pgvector) indexes
- `heartbeat_state` - Periodic execution tracking
**Other:**
- `routines`, `routine_runs` - Scheduled/reactive execution
- `settings` - Per-user key-value settings
- `tool_failures` - Self-repair tracking
- `secrets`, `wasm_tools`, `tool_capabilities` - Extension infrastructure
Requires pgvector extension: `CREATE EXTENSION IF NOT EXISTS vector;`
### Configuration
```bash
# Backend selection (default: postgres)
DATABASE_BACKEND=libsql
# PostgreSQL
DATABASE_URL=postgres://user:pass@localhost/ironclaw
# libSQL (embedded)
LIBSQL_PATH=~/.ironclaw/ironclaw.db # Default path
# libSQL (Turso cloud sync)
LIBSQL_URL=libsql://your-db.turso.io
LIBSQL_AUTH_TOKEN=your-token # Required when LIBSQL_URL is set
```
### Current Limitations (libSQL backend)
- **Workspace/memory system** not yet wired through Database trait (requires Store migration)
- **Secrets store** not yet available (still requires PostgresSecretsStore)
- **Hybrid search** uses FTS5 only (vector search via libsql_vector_idx not yet implemented)
- **Settings reload from DB** skipped (Config::from_db requires Store)
- No incremental migration versioning (schema is CREATE IF NOT EXISTS, no ALTER TABLE support yet)
- **No encryption at rest** -- The local SQLite database file stores conversation content, job data, workspace memory, and other application data in plaintext. Only secrets (API tokens, credentials) are encrypted via AES-256-GCM before storage. Users handling sensitive data should use full-disk encryption (FileVault, LUKS, BitLocker) or consider the PostgreSQL backend with TDE/encrypted storage.
- **JSON merge patch vs path-targeted update** -- The libSQL backend uses RFC 7396 JSON Merge Patch (`json_patch`) for metadata updates, while PostgreSQL uses path-targeted `jsonb_set`. Merge patch replaces top-level keys entirely, which may drop nested keys not present in the patch. Callers should avoid relying on partial nested object updates in metadata fields.
Run migrations: `refinery migrate -c refinery.toml`
## Safety Layer
@@ -442,14 +293,13 @@ Key test patterns:
## Current Limitations / TODOs
1. **Domain-specific tools** - `marketplace.rs`, `restaurant.rs`, `taskrabbit.rs`, `ecommerce.rs` return placeholder responses; need real API integrations
2. **Integration tests** - Need testcontainers setup for PostgreSQL
3. **MCP stdio transport** - Only HTTP transport implemented
4. **WIT bindgen integration** - Auto-extract tool description/schema from WASM modules (stubbed)
5. **Capability granting after tool build** - Built tools get empty capabilities; need UX for granting HTTP/secrets access
6. **Tool versioning workflow** - No version tracking or rollback for dynamically built tools
7. **Webhook trigger endpoint** - Routines webhook trigger not yet exposed in web gateway
8. **Full channel status view** - Gateway status widget exists, but no per-channel connection dashboard
1. **Slack/Telegram channels** - Stubs only, need implementation
2. **Domain-specific tools** - `marketplace.rs`, `restaurant.rs`, `taskrabbit.rs`, `ecommerce.rs` return placeholder responses; need real API integrations
3. **Integration tests** - Need testcontainers setup for PostgreSQL
4. **MCP stdio transport** - Only HTTP transport implemented
5. **WIT bindgen integration** - Auto-extract tool description/schema from WASM modules (stubbed)
6. **Capability granting after tool build** - Built tools get empty capabilities; need UX for granting HTTP/secrets access
7. **Tool versioning workflow** - No version tracking or rollback for dynamically built tools
### Completed
@@ -466,14 +316,6 @@ Key test patterns:
-**Tool approval enforcement** - Tools with `requires_approval()` (shell, http, file write/patch, build_software) now gate execution, track auto-approved tools per session
-**Tool definition refresh** - Tool definitions refreshed each iteration so newly built tools become visible in same session
-**Worker tool call handling** - Uses `respond_with_tools()` to properly execute tool calls when `select_tools()` returns empty
-**Gateway control plane** - Web gateway with 40+ API endpoints, SSE/WebSocket
-**Web Control UI** - Browser-based dashboard with chat, memory, jobs, logs, extensions, routines
-**Slack/Telegram channels** - Implemented as WASM tools
-**Docker sandbox** - Orchestrator/worker containers with per-job auth
-**Claude Code mode** - Delegate jobs to Claude CLI inside containers
-**Routines system** - Cron, event, webhook, and manual triggers with guardrails
-**Extension management** - Install, auth, activate MCP/WASM extensions via CLI and web UI
-**libSQL/Turso backend** - Database trait abstraction (`src/db/`), feature-gated dual backend support (postgres/libsql), embedded SQLite for zero-dependency local mode
## Adding a New Tool
@@ -489,13 +331,13 @@ Key test patterns:
WASM tools are the preferred way to add new capabilities. They run in a sandboxed environment with explicit capabilities.
1. Create a new crate in `tools-src/<name>/`
1. Create a new crate in `examples/wasm-tools/<name>/`
2. Implement the WIT interface (`wit/tool.wit`)
3. Create `<name>.capabilities.json` declaring required permissions
4. Build with `cargo build --target wasm32-wasip2 --release`
5. Install with `ironclaw tool install path/to/tool.wasm`
See `tools-src/` for examples.
See `examples/wasm-tools/` for examples.
## Tool Architecture Principles
@@ -577,39 +419,6 @@ When running `ironclaw tool auth <tool>`:
The agent reads auth config from the tool's capabilities file and provides the appropriate flow. No service-specific code in the main agent.
### WASM Tools vs MCP Servers: When to Use Which
Both are first-class in the extension system (`ironclaw tool install` handles both), but they have different strengths.
**WASM Tools (IronClaw native)**
- Sandboxed: fuel metering, memory limits, no access except what's allowlisted
- Credentials injected by host runtime, tool code never sees the actual token
- Output scanned for secret leakage before returning to the LLM
- Auth (OAuth/manual) declared in `capabilities.json`, agent handles the flow
- Single binary, no process management, works offline
- Cost: must build yourself in Rust, no ecosystem, synchronous only
**MCP Servers (Model Context Protocol)**
- Growing ecosystem of pre-built servers (GitHub, Notion, Postgres, etc.)
- Any language (TypeScript/Python most common)
- Can do websockets, streaming, background polling
- Cost: external process with full system access (no sandbox), manages own credentials, IronClaw can't prevent leaks
**Decision guide:**
| Scenario | Use |
|----------|-----|
| Good MCP server already exists | **MCP** |
| Handles sensitive credentials (email send, banking) | **WASM** |
| Quick prototype or one-off integration | **MCP** |
| Core capability you'll maintain long-term | **WASM** |
| Needs background connections (websockets, polling) | **MCP** |
| Multiple tools share one OAuth token (e.g., Google suite) | **WASM** |
The LLM-facing interface is identical for both (tool name, schema, execute), so swapping between them is transparent to the agent.
## Adding a New Channel
1. Create `src/channels/my_channel.rs`
@@ -630,22 +439,6 @@ RUST_LOG=ironclaw::agent=debug cargo run
RUST_LOG=ironclaw=debug,tower_http=debug cargo run
```
## Module Specifications
Some modules have a `README.md` that serves as the authoritative specification
for that module's behavior. When modifying code in a module that has a spec:
1. **Read the spec first** before making changes
2. **Code follows spec**: if the spec says X, the code must do X
3. **Update both sides**: if you change behavior, update the spec to match;
if you're implementing a spec change, update the code to match
4. **Spec is the tiebreaker**: when code and spec disagree, the spec is correct
(unless the spec is clearly outdated, in which case fix the spec first)
| Module | Spec File |
|--------|-----------|
| `src/setup/` | `src/setup/README.md` |
## Code Style
- Use `crate::` imports, not `super::`
@@ -654,37 +447,6 @@ for that module's behavior. When modifying code in a module that has a spec:
- Keep functions focused, extract helpers when logic is reused
- Comments for non-obvious logic only
## Review & Fix Discipline
Hard-won lessons from code review -- follow these when fixing bugs or addressing review feedback.
### Fix the pattern, not just the instance
When a reviewer flags a bug (e.g., TOCTOU race in INSERT + SELECT-back), search the entire codebase for all instances of that same pattern. A fix in `SecretsStore::create()` that doesn't also fix `WasmToolStore::store()` is half a fix.
### Propagate architectural fixes to satellite types
If a core type changes its concurrency model (e.g., `LibSqlBackend` switches to connection-per-operation), every type that was handed a resource from the old model (e.g., `LibSqlSecretsStore`, `LibSqlWasmToolStore` holding a single `Connection`) must also be updated. Grep for the old type across the codebase.
### Schema translation is more than DDL
When translating a database schema between backends (PostgreSQL to libSQL, etc.), check for:
- **Indexes** -- diff `CREATE INDEX` statements between the two schemas
- **Seed data** -- check for `INSERT INTO` in migrations (e.g., `leak_detection_patterns`)
- **Semantic differences** -- document where SQL functions behave differently (e.g., `json_patch` vs `jsonb_set`)
### Feature flag testing
When adding feature-gated code, test compilation with each feature in isolation:
```bash
cargo check # default features
cargo check --no-default-features --features libsql # libsql only
cargo check --all-features # all features
```
Dead code behind the wrong `#[cfg]` gate will only show up when building with a single feature.
### Mechanical verification before committing
Run these checks on changed files before committing:
- `grep -rnE '\.unwrap\(|\.expect\(' <files>` -- no panics in production
- `grep -rn 'super::' <files>` -- use `crate::` imports
- If you fixed a pattern bug, `grep` for other instances of that pattern across `src/`
## Workspace & Memory System
Inspired by [OpenClaw](https://github.com/openclaw/openclaw), the workspace provides persistent memory for agents with a flexible filesystem-like structure.
@@ -759,7 +521,7 @@ Four tools for LLM use:
### Hybrid Search (RRF)
Combines full-text search and vector similarity using Reciprocal Rank Fusion:
Combines full-text search (PostgreSQL `ts_rank_cd`) and vector similarity (pgvector cosine) using Reciprocal Rank Fusion:
```
score(d) = Σ 1/(k + rank(d)) for each method where d appears
@@ -767,10 +529,6 @@ score(d) = Σ 1/(k + rank(d)) for each method where d appears
Default k=60. Results from both methods are combined, with documents appearing in both getting boosted scores.
**Backend differences:**
- **PostgreSQL:** `ts_rank_cd` for FTS, pgvector cosine distance for vectors, full RRF
- **libSQL:** FTS5 for keyword search only (vector search via `libsql_vector_idx` not yet wired)
### Heartbeat System
Proactive periodic execution (default: 30 minutes):
-11
View File
@@ -1,11 +0,0 @@
# Contributing
## Feature Parity Requirement
When your change affects a tracked capability, update `FEATURE_PARITY.md` in the same branch.
### Required before opening a PR
1. Review the relevant parity rows in `FEATURE_PARITY.md`.
2. Update status/notes if behavior changed.
3. Include the `FEATURE_PARITY.md` diff in your commit when applicable.
Generated
+234 -1382
View File
File diff suppressed because it is too large Load Diff
+18 -105
View File
@@ -1,49 +1,30 @@
[workspace]
exclude = [
"channels-src/telegram",
"channels-src/slack",
"channels-src/whatsapp",
"tools-src/gmail",
]
[package]
name = "ironclaw"
version = "0.5.0"
version = "0.1.0"
edition = "2024"
rust-version = "1.92"
rust-version = "1.85"
description = "Secure personal AI assistant that protects your data and expands its capabilities on the fly"
authors = ["NEAR AI <[email protected]>"]
license = "MIT OR Apache-2.0"
homepage = "https://github.com/nearai/ironclaw"
repository = "https://github.com/nearai/ironclaw"
[package.metadata.wix]
upgrade-guid = "D0156E61-BA37-451E-8AB9-1A2ECCCFA48F"
path-guid = "F90B6EA6-87F7-499B-BB19-CF55DE1EB339"
license = false
eula = false
[dependencies]
# Async runtime
tokio = { version = "1", features = ["full"] }
tokio-stream = { version = "0.1", features = ["sync"] }
tokio-stream = "0.1"
futures = "0.3"
# HTTP client
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls-native-roots", "stream"] }
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls", "stream"] }
# Serialization
serde = { version = "1", features = ["derive"] }
serde_json = "1"
toml = "0.8"
# Database - PostgreSQL (default, feature-gated)
deadpool-postgres = { version = "0.14", optional = true }
tokio-postgres = { version = "0.7", features = ["with-uuid-1", "with-chrono-0_4", "with-serde_json-1"], optional = true }
postgres-types = { version = "0.2", features = ["with-serde_json-1"], optional = true }
refinery = { version = "0.8", features = ["tokio-postgres"], optional = true }
# Database - libSQL/Turso (optional embedded database)
libsql = { version = "0.6", optional = true, default-features = false, features = ["core", "replication"] }
# Database
deadpool-postgres = "0.14"
tokio-postgres = { version = "0.7", features = ["with-uuid-1", "with-chrono-0_4", "with-serde_json-1"] }
postgres-types = { version = "0.2", features = ["with-serde_json-1"] }
refinery = { version = "0.8", features = ["tokio-postgres"] }
# Error handling
thiserror = "2"
@@ -59,7 +40,7 @@ dotenvy = "0.15"
# Core types
uuid = { version = "1", features = ["v4", "serde"] }
chrono = { version = "0.4", features = ["serde"] }
rust_decimal = { version = "1", features = ["serde", "serde-with-str", "maths"] }
rust_decimal = { version = "1", features = ["serde", "serde-with-str", "db-tokio-postgres", "maths"] }
rust_decimal_macros = "1"
# Async traits
@@ -68,32 +49,26 @@ async-trait = "0.1"
# CLI
clap = { version = "4", features = ["derive", "env"] }
# Terminal
crossterm = "0.28"
rustyline = { version = "17", features = ["derive", "with-file-history"] }
termimad = "0.34"
# TUI
ratatui = "0.29"
crossterm = { version = "0.28", features = ["event-stream"] }
# Channel integrations
axum = { version = "0.8", features = ["ws"] }
axum = "0.8"
tower = "0.5"
tower-http = { version = "0.6", features = ["trace", "cors"] }
# Cron scheduling for routines
cron = "0.13"
# Safety/sanitization
regex = "1"
aho-corasick = "1"
# Filesystem paths
dirs = "6"
fs4 = "0.6"
# Secrecy for sensitive values
secrecy = { version = "0.10", features = ["serde"] }
# URL parsing and encoding
url = "2"
# URL encoding for OAuth flow
urlencoding = "2"
# Open URLs in browser
@@ -101,7 +76,7 @@ open = "5"
# Vector embeddings for semantic search
# The postgres feature provides ToSql/FromSql for postgres-types (shared by tokio-postgres)
pgvector = { version = "0.4", features = ["postgres"], optional = true }
pgvector = { version = "0.4", features = ["postgres"] }
# WASM sandbox for untrusted tool execution
wasmtime = { version = "28", features = ["component-model"] }
@@ -114,10 +89,6 @@ hkdf = "0.12"
sha2 = "0.10"
blake3 = "1"
rand = "0.8"
subtle = "2" # Constant-time comparisons for token validation
# Multi-provider LLM support
rig-core = "0.30"
# Docker sandbox
bollard = "0.18"
@@ -128,7 +99,6 @@ hyper-util = { version = "0.1", features = ["server", "tokio", "http1", "http2"]
http-body-util = "0.1"
bytes = "1"
base64 = "0.22.1"
mime_guess = "2.0.5"
# macOS keychain
[target.'cfg(target_os = "macos")'.dependencies]
@@ -141,67 +111,10 @@ zbus = "4"
[dev-dependencies]
tokio-test = "0.4"
tokio-tungstenite = "0.26"
testcontainers-modules = { version = "0.11", features = ["postgres"] }
pretty_assertions = "1"
tempfile = "3"
[features]
default = ["postgres", "libsql"]
postgres = [
"dep:deadpool-postgres",
"dep:tokio-postgres",
"dep:postgres-types",
"dep:refinery",
"dep:pgvector",
"rust_decimal/db-tokio-postgres",
]
libsql = ["dep:libsql"]
default = []
integration = []
[[example]]
name = "test_heartbeat"
required-features = ["postgres"]
# The profile that 'cargo dist' will build with
[profile.dist]
inherits = "release"
lto = "thin"
# Config for 'dist'
[workspace.metadata.dist]
# The preferred dist version to use in CI (Cargo.toml SemVer syntax)
cargo-dist-version = "0.30.3"
# CI backends to support
ci = "github"
# The installers to generate for each app
installers = ["shell", "powershell", "npm", "msi"]
# Publish jobs to run in CI
publish-jobs = []
# Target platforms to build apps for (Rust target-triple syntax)
targets = [
"aarch64-apple-darwin",
"aarch64-unknown-linux-gnu",
"x86_64-apple-darwin",
"x86_64-unknown-linux-gnu",
"x86_64-pc-windows-msvc",
]
# The archive format to use for windows builds (defaults .zip)
windows-archive = ".tar.gz"
# The archive format to use for non-windows builds (defaults .tar.xz)
unix-archive = ".tar.gz"
# Which actions to run on pull requests
pr-run-mode = "skip"
# Path that installers should place binaries in
install-path = "CARGO_HOME"
# Whether to install an updater program
install-updater = true
# Cache intermediate build artifacts to speed up the release pipelines
cache-builds = true
[workspace.metadata.dist.github-custom-runners]
aarch64-unknown-linux-gnu = "ubuntu-24.04-arm"
x86_64-unknown-linux-gnu = "ubuntu-22.04"
x86_64-pc-windows-msvc = "windows-2022"
x86_64-apple-darwin = "macos-15-intel"
aarch64-apple-darwin = "macos-14"
-46
View File
@@ -1,46 +0,0 @@
# Multi-stage Dockerfile for the IronClaw agent (cloud deployment).
#
# Build:
# docker build --platform linux/amd64 -t ironclaw:latest .
#
# Run:
# docker run --env-file .env -p 3000:3000 ironclaw:latest
# Stage 1: Build
FROM rust:1.92-slim-bookworm AS builder
RUN apt-get update && apt-get install -y --no-install-recommends \
pkg-config libssl-dev cmake gcc g++ \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
# Copy manifests first for layer caching
COPY Cargo.toml Cargo.lock ./
# Copy source and build artifacts
COPY src/ src/
COPY migrations/ migrations/
COPY wit/ wit/
RUN cargo build --release --bin ironclaw
# Stage 2: Runtime
FROM debian:bookworm-slim
RUN apt-get update && apt-get install -y --no-install-recommends \
ca-certificates libssl3 \
&& rm -rf /var/lib/apt/lists/*
COPY --from=builder /app/target/release/ironclaw /usr/local/bin/ironclaw
COPY --from=builder /app/migrations /app/migrations
# Non-root user
RUN useradd -m -u 1000 -s /bin/bash ironclaw
USER ironclaw
EXPOSE 3000
ENV RUST_LOG=ironclaw=info
ENTRYPOINT ["ironclaw"]
-63
View File
@@ -1,63 +0,0 @@
# Multi-stage Dockerfile for the IronClaw worker container.
#
# This image runs the ironclaw binary in worker mode inside Docker containers.
# The orchestrator creates instances of this image for sandboxed job execution.
#
# Build:
# docker build -f Dockerfile.worker -t ironclaw-worker .
#
# The image includes common development tools so workers can build software,
# run tests, and execute shell commands.
FROM rust:1.92-bookworm AS builder
WORKDIR /build
COPY . .
# Build only the ironclaw binary (release mode)
RUN cargo build --release --bin ironclaw
# ---
FROM debian:bookworm-slim
# Install common development tools
RUN apt-get update && apt-get install -y --no-install-recommends \
ca-certificates \
curl \
git \
build-essential \
pkg-config \
libssl-dev \
nodejs \
npm \
python3 \
python3-pip \
python3-venv \
&& rm -rf /var/lib/apt/lists/*
# Install Rust toolchain for the sandbox user
ENV RUSTUP_HOME=/usr/local/rustup \
CARGO_HOME=/usr/local/cargo \
PATH=/usr/local/cargo/bin:$PATH
RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain 1.92.0 \
&& chmod -R a+r /usr/local/rustup /usr/local/cargo
# Install Claude Code CLI (for claude-bridge mode)
RUN npm install -g @anthropic-ai/claude-code@latest
# Copy the binary
COPY --from=builder /build/target/release/ironclaw /usr/local/bin/ironclaw
# Create non-root user (UID 1000 matches the orchestrator's container config)
RUN useradd -m -u 1000 -s /bin/bash sandbox \
&& mkdir -p /workspace \
&& chown sandbox:sandbox /workspace \
&& mkdir -p /home/sandbox/.claude \
&& chown sandbox:sandbox /home/sandbox/.claude
USER sandbox
WORKDIR /workspace
# The orchestrator passes the full command via Docker cmd.
ENTRYPOINT ["ironclaw"]
+51 -57
View File
@@ -16,8 +16,8 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| Hub-and-spoke architecture | ✅ | | Web gateway as central hub |
| WebSocket control plane | ✅ | | Gateway with WebSocket + SSE |
| Hub-and-spoke architecture | ✅ | 🚧 | IronClaw has channels but no central gateway |
| WebSocket control plane | ✅ | | Gateway with ws://127.0.0.1:18789 |
| Single-user system | ✅ | ✅ | |
| Multi-agent routing | ✅ | ❌ | Workspace isolation per-agent |
| Session-based messaging | ✅ | ✅ | Per-sender sessions |
@@ -31,19 +31,19 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| Gateway control plane | ✅ | | Web gateway with 40+ API endpoints |
| HTTP endpoints for Control UI | ✅ | | Web dashboard with chat, memory, jobs, logs, extensions |
| Channel connection lifecycle | ✅ | | ChannelManager + WebSocket tracker |
| Gateway control plane | ✅ | | Central WebSocket server |
| HTTP endpoints for Control UI | ✅ | | Web dashboard |
| Channel connection lifecycle | ✅ | 🚧 | ChannelManager handles streams |
| Session management/routing | ✅ | ✅ | SessionManager exists |
| Configuration hot-reload | ✅ | ❌ | |
| Network modes (loopback/LAN/remote) | ✅ | 🚧 | HTTP only |
| OpenAI-compatible HTTP API | ✅ | | /v1/chat/completions |
| OpenAI-compatible HTTP API | ✅ | | /v1/chat/completions |
| Canvas hosting | ✅ | ❌ | Agent-driven UI |
| Gateway lock (PID-based) | ✅ | ❌ | |
| launchd/systemd integration | ✅ | ❌ | |
| Bonjour/mDNS discovery | ✅ | ❌ | |
| Tailscale integration | ✅ | ❌ | |
| Health check endpoints | ✅ | | /api/health + /api/gateway/status |
| Health check endpoints | ✅ | | |
| `doctor` diagnostics | ✅ | ❌ | |
### Owner: _Unassigned_
@@ -59,14 +59,14 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| REPL (simple) | ✅ | ✅ | - | For testing |
| WASM channels | ❌ | ✅ | - | IronClaw innovation |
| WhatsApp | ✅ | ❌ | P1 | Baileys (Web) |
| Telegram | ✅ | | - | WASM channel(MTProto), DM pairing, caption, /start, bot_username |
| Telegram | ✅ | | P1 | grammY (Bot API) |
| Discord | ✅ | ❌ | P2 | discord.js |
| Signal | ✅ | ❌ | P2 | signal-cli |
| Slack | ✅ | | - | WASM tool |
| Slack | ✅ | 🚧 | P1 | Stub exists, needs implementation |
| iMessage | ✅ | ❌ | P3 | BlueBubbles recommended |
| Feishu/Lark | ✅ | ❌ | P3 | |
| LINE | ✅ | ❌ | P3 | |
| WebChat | ✅ | | - | Web gateway chat |
| WebChat | ✅ | | P2 | Browser-based chat |
| Matrix | ✅ | ❌ | P3 | E2EE support |
| Mattermost | ✅ | ❌ | P3 | |
| Google Chat | ✅ | ❌ | P3 | |
@@ -79,13 +79,13 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| DM pairing codes | ✅ | | `ironclaw pairing list/approve`, host APIs |
| Allowlist/blocklist | ✅ | 🚧 | allow_from + pairing store |
| DM pairing codes | ✅ | | Verification for unknown senders |
| Allowlist/blocklist | ✅ | | Per-channel access control |
| Self-message bypass | ✅ | ❌ | Own messages skip pairing |
| Mention-based activation | ✅ | | bot_username + respond_to_all_group_messages |
| Mention-based activation | ✅ | | Configurable patterns |
| Per-group tool policies | ✅ | ❌ | Allow/deny specific tools |
| Thread isolation | ✅ | ✅ | Separate sessions per thread |
| Per-channel media limits | ✅ | 🚧 | Caption support for media; no size limits |
| Per-channel media limits | ✅ | | |
| Typing indicators | ✅ | 🚧 | TUI shows status |
### Owner: _Unassigned_
@@ -99,20 +99,20 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| `run` (agent) | ✅ | ✅ | - | Default command |
| `tool install/list/remove` | ✅ | ✅ | - | WASM tools |
| `gateway start/stop` | ✅ | ❌ | P2 | |
| `onboard` (wizard) | ✅ | | - | Interactive setup |
| `onboard` (wizard) | ✅ | | P2 | Interactive setup |
| `tui` | ✅ | ✅ | - | Ratatui TUI |
| `config` | ✅ | | - | Read/write config |
| `config` | ✅ | | P2 | Read/write config |
| `channels` | ✅ | ❌ | P2 | Channel management |
| `models` | ✅ | 🚧 | - | Model selector in TUI |
| `status` | ✅ | | - | System status |
| `status` | ✅ | | P2 | System status |
| `agents` | ✅ | ❌ | P3 | Multi-agent management |
| `sessions` | ✅ | ❌ | P3 | Session listing |
| `memory` | ✅ | | - | Memory search CLI |
| `memory` | ✅ | | P2 | Memory search CLI |
| `skills` | ✅ | ❌ | P3 | Agent skills |
| `pairing` | ✅ | | - | list/approve for channel DM pairing |
| `pairing` | ✅ | | P3 | Node pairing |
| `nodes` | ✅ | ❌ | P3 | Device management |
| `plugins` | ✅ | ❌ | P3 | Plugin management |
| `hooks` | ✅ | | P2 | Lifecycle hooks |
| `hooks` | ✅ | | P2 | Lifecycle hooks |
| `cron` | ✅ | ❌ | P2 | Scheduled jobs |
| `webhooks` | ✅ | ❌ | P3 | Webhook config |
| `message send` | ✅ | ❌ | P2 | Send to channels |
@@ -132,8 +132,8 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| Pi agent runtime | ✅ | | IronClaw uses custom runtime |
| RPC-based execution | ✅ | | Orchestrator/worker pattern |
| Multi-provider failover | ✅ | | `FailoverProvider` tries providers sequentially on retryable errors |
| RPC-based execution | ✅ | 🚧 | Worker isolation |
| Multi-provider failover | ✅ | | Provider fallback chains |
| Per-sender sessions | ✅ | ✅ | |
| Global sessions | ✅ | ❌ | Optional shared context |
| Session pruning | ✅ | ❌ | Auto cleanup old sessions |
@@ -164,7 +164,7 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| AWS Bedrock | ✅ | ❌ | P3 | |
| Google Gemini | ✅ | ❌ | P3 | |
| OpenRouter | ✅ | ❌ | P3 | |
| Ollama (local) | ✅ | | - | via `rig::providers::ollama` (full support) |
| Ollama (local) | ✅ | | P2 | Local models |
| node-llama-cpp | ✅ | | - | N/A for Rust |
| llama.cpp (native) | ❌ | 🔮 | P3 | Rust bindings |
@@ -173,8 +173,8 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| Auto-discovery | ✅ | ❌ | |
| Failover chains | ✅ | | `FailoverProvider` with configurable `fallback_model` |
| Cooldown management | ✅ | | Lock-free per-provider cooldown in `FailoverProvider` |
| Failover chains | ✅ | | Provider fallback |
| Cooldown management | ✅ | | Skip failed providers |
| Per-session model override | ✅ | ✅ | Model selector in TUI |
| Model selection UI | ✅ | ✅ | TUI keyboard shortcut |
@@ -303,13 +303,13 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Priority | Notes |
|---------|----------|----------|----------|-------|
| Control UI Dashboard | ✅ | | - | Web gateway with chat, memory, jobs, logs, extensions |
| Channel status view | ✅ | 🚧 | P2 | Gateway status widget, full channel view pending |
| Control UI Dashboard | ✅ | | P2 | Web status/config |
| Channel status view | ✅ | | P2 | |
| Agent management | ✅ | ❌ | P3 | |
| Model selection | ✅ | ✅ | - | TUI only |
| Config editing | ✅ | ❌ | P3 | |
| Debug/logs viewer | ✅ | | - | Real-time log streaming with level/target filters |
| WebChat interface | ✅ | | - | Web gateway chat with SSE/WebSocket |
| Debug/logs viewer | ✅ | | P3 | |
| WebChat interface | ✅ | | P2 | Browser chat |
| Canvas system (A2UI) | ✅ | ❌ | P3 | Agent-driven UI |
### Owner: _Unassigned_
@@ -320,17 +320,17 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Priority | Notes |
|---------|----------|----------|----------|-------|
| Cron jobs | ✅ | | - | Routines with cron trigger |
| Timezone support | ✅ | | - | Via cron expressions |
| One-shot/recurring jobs | ✅ | | - | Manual + cron triggers |
| `beforeInbound` hook | ✅ | | P2 | |
| `beforeOutbound` hook | ✅ | | P2 | |
| `beforeToolCall` hook | ✅ | | P2 | |
| `onMessage` hook | ✅ | | - | Routines with event trigger |
| `onSessionStart` hook | ✅ | | P2 | |
| `onSessionEnd` hook | ✅ | | P2 | |
| Cron jobs | ✅ | | P2 | Schedule-based tasks |
| Timezone support | ✅ | | P2 | |
| One-shot/recurring jobs | ✅ | | P2 | |
| `beforeInbound` hook | ✅ | | P2 | |
| `beforeOutbound` hook | ✅ | | P2 | |
| `beforeToolCall` hook | ✅ | | P2 | |
| `onMessage` hook | ✅ | | P2 | |
| `onSessionStart` hook | ✅ | | P2 | |
| `onSessionEnd` hook | ✅ | | P2 | |
| `transcribeAudio` hook | ✅ | ❌ | P3 | |
| `transformResponse` hook | ✅ | | P2 | |
| `transformResponse` hook | ✅ | | P2 | |
| Bundled hooks | ✅ | ❌ | P2 | |
| Plugin hooks | ✅ | ❌ | P3 | |
| Workspace hooks | ✅ | ❌ | P2 | Inline code |
@@ -346,18 +346,18 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| Feature | OpenClaw | IronClaw | Notes |
|---------|----------|----------|-------|
| Gateway token auth | ✅ | | Bearer token auth on web gateway |
| Gateway token auth | ✅ | 🚧 | HTTP webhook secret |
| Device pairing | ✅ | ❌ | |
| Tailscale identity | ✅ | ❌ | |
| OAuth flows | ✅ | 🚧 | NEAR AI OAuth |
| DM pairing verification | ✅ | | ironclaw pairing approve, host APIs |
| Allowlist/blocklist | ✅ | 🚧 | allow_from + pairing store |
| DM pairing verification | ✅ | | |
| Allowlist/blocklist | ✅ | | |
| Per-group tool policies | ✅ | ❌ | |
| Exec approvals | ✅ | ✅ | TUI overlay |
| TLS 1.3 minimum | ✅ | ✅ | reqwest rustls |
| SSRF protection | ✅ | ✅ | WASM allowlist |
| Loopback-first | ✅ | 🚧 | HTTP binds 0.0.0.0 |
| Docker sandbox | ✅ | | Orchestrator/worker containers |
| Docker sandbox | ✅ | | Uses WASM sandbox |
| WASM sandbox | ❌ | ✅ | IronClaw innovation |
| Tool policies | ✅ | ✅ | |
| Elevated mode | ✅ | ❌ | |
@@ -397,7 +397,6 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
### P0 - Core (Already Done)
- ✅ TUI channel with approval overlays
- ✅ HTTP webhook channel
- ✅ DM pairing (ironclaw pairing list/approve, host APIs)
- ✅ WASM tool sandbox
- ✅ Workspace/memory with hybrid search
- ✅ Prompt injection defense
@@ -405,28 +404,23 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
- ✅ Session management
- ✅ Context compaction
- ✅ Model selection
- ✅ Gateway control plane + WebSocket
- ✅ Web Control UI (chat, memory, jobs, logs, extensions, routines)
- ✅ WebChat channel (web gateway)
- ✅ Slack channel (WASM tool)
- ✅ Telegram channel (WASM tool, MTProto)
- ✅ Docker sandbox (orchestrator/worker)
- ✅ Cron job scheduling (routines)
- ✅ CLI subcommands (onboard, config, status, memory)
- ✅ Gateway token auth
### P1 - High Priority
- ❌ Slack channel (real implementation)
- Telegram channel (WASM, DM pairing, caption, /start)
- Telegram channel
- ❌ WhatsApp channel
- Multi-provider failover (`FailoverProvider` with retryable error classification)
- ✅ Hooks system (beforeInbound, beforeToolCall, beforeOutbound, onSessionStart, onSessionEnd, transformResponse)
- Multi-provider failover
- ❌ Gateway control plane + WebSocket
- ❌ Hooks system (beforeInbound, beforeToolCall, etc.)
### P2 - Medium Priority
- ❌ Cron job scheduling
- ❌ Web Control UI
- ❌ WebChat channel
- ❌ Media handling (images, PDFs)
- ❌ CLI subcommands (config, status, memory, doctor)
- ❌ Ollama/local model support
- ❌ Configuration hot-reload
- ❌ Webhook trigger endpoint in web gateway
### P3 - Lower Priority
- ❌ Discord channel
View File
-191
View File
@@ -1,191 +0,0 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to the Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by the Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding any notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
Copyright 2026 NEAR AI
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
+72 -94
View File
@@ -43,10 +43,7 @@ IronClaw is the AI assistant you can actually trust with your personal and profe
### Always Available
- **Multi-channel** - REPL, HTTP webhooks, WASM channels (Telegram, Slack), and web gateway
- **Docker Sandbox** - Isolated container execution with per-job tokens and orchestrator/worker pattern
- **Web Gateway** - Browser UI with real-time SSE/WebSocket streaming
- **Routines** - Cron schedules, event triggers, webhook handlers for background automation
- **Multi-channel** - Reach your assistant via CLI, Telegram, WhatsApp, Slack, or HTTP webhooks
- **Heartbeat System** - Proactive background execution for monitoring and maintenance tasks
- **Parallel Jobs** - Handle multiple requests concurrently with isolated contexts
- **Self-repair** - Automatic detection and recovery of stuck operations
@@ -68,41 +65,10 @@ IronClaw is the AI assistant you can actually trust with your personal and profe
### Prerequisites
- Rust 1.85+
- PostgreSQL 15+ with [pgvector](https://github.com/pgvector/pgvector) extension
- NEAR AI account (authentication handled via setup wizard)
- PostgreSQL 15+ with pgvector extension
- NEAR AI session token (or other LLM provider)
## Download or Build
Visit [Releases page](https://github.com/nearai/ironclaw/releases/) to see the latest updates.
<details>
<summary>Install via Windows Installer (Windows)</summary>
Download the [Windows Installer](https://github.com/nearai/ironclaw/releases/latest/download/ironclaw-x86_64-pc-windows-msvc.msi) and run it.
</details>
<details>
<summary>Install via powershell script (Windows)</summary>
```sh
irm https://github.com/nearai/ironclaw/releases/latest/download/ironclaw-installer.ps1 | iex
```
</details>
<details>
<summary>Install via shell script (macOS, Linux, Windows/WSL)</summary>
```sh
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/nearai/ironclaw/releases/latest/download/ironclaw-installer.sh | sh
```
</details>
<details>
<summary>Compile the source code (Cargo on Windows, Linux, macOS)</summary>
Install it with `cargo`, just make sure you have [Rust](https://rustup.rs) installed on your computer.
### Build
```bash
# Clone the repository
@@ -116,10 +82,6 @@ cargo build --release
cargo test
```
For **full release** (after modifying channel sources), run `./scripts/build-all.sh` to rebuild channels first.
</details>
### Database Setup
```bash
@@ -128,19 +90,36 @@ createdb ironclaw
# Enable pgvector
psql ironclaw -c "CREATE EXTENSION IF NOT EXISTS vector;"
# Run migrations
refinery migrate -c refinery.toml
```
## Configuration
Run the setup wizard to configure IronClaw:
Copy `.env.example` to `.env` and configure:
```bash
ironclaw onboard
# Required
DATABASE_URL=postgres://user:pass@localhost/ironclaw
NEARAI_SESSION_TOKEN=sess_...
# Optional: Enable channels
TELEGRAM_BOT_TOKEN=...
WHATSAPP_ACCESS_TOKEN=...
SLACK_BOT_TOKEN=xoxb-...
HTTP_PORT=8080
```
The wizard handles database connection, NEAR AI authentication (via browser OAuth),
and secrets encryption (using your system keychain). All settings are saved to
`~/.ironclaw/settings.toml`.
### Environment Variables
| Variable | Description | Required |
|----------|-------------|----------|
| `DATABASE_URL` | PostgreSQL connection string | Yes |
| `NEARAI_SESSION_TOKEN` | NEAR AI authentication token | Yes |
| `NEARAI_MODEL` | Model to use (default: claude-3-5-sonnet) | No |
| `AGENT_MAX_PARALLEL_JOBS` | Max concurrent jobs (default: 5) | No |
| `SECRETS_MASTER_KEY` | 32+ byte key for secret encryption | For secrets |
## Security
@@ -181,42 +160,37 @@ External content passes through multiple security layers:
## Architecture
```
┌────────────────────────────────────────────────────────────────┐
Channels │
│ ┌─────┐ ┌──────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ REPL │ │ HTTP │ │WASM Channels│ │ Web Gateway │
│ └──┬──┘ └─────┘ └────────────┘ │ (SSE + WS)
│ │ │ └──────┬──────┘
└─────────┴──────────────┴────────────────┘
┌─────────▼─────────┐
│ Agent Loop Intent routing
└────┬──────────┬───┘
│ │
┌──────────▼────┐ ┌──▼───────────────┐
│ Scheduler │ Routines Engine
│(parallel jobs)│ │(cron, event, wh) │
──────────────┘ └─────────────────┘
┌─────────────┼────────────────────
│ │
──────── ┌────▼────────────────
│ Local │ Orchestrator │
│Workers ┌───────────────┐ │
│(in-proc)│ │ Docker Sandbox│
└───┬─────┘ Containers
┌───────────
│ │ │Worker / CC
│ │ └───────────┘
└───────────────┘ │
└────────┬──────────┘ │
│ └──────────────────
│ │ │
│ ┌───────────▼──────────┐ │
│ │ Tool Registry │ │
│ │ Built-in, MCP, WASM │ │
│ └──────────────────────┘ │
└────────────────────────────────────────────────────────────────┘
┌────────────────────────────────────────────────────────────────
│ Channels
│ ┌─────┐ ┌──────────┐ ┌──────────┐ ┌───────┐
│ │ CLI │ │ Telegram │ │ WhatsApp │ │ Slack │
│ └──┬──┘ └────┬────┘ └─────────┘ └───┬───┘
└──────────┴─────────────┴────────────┘
┌────▼────┐
│ Router │ Intent classification
└────┬────┘
┌──────────▼──────────┐
│ Scheduler Parallel job management
└──────────┬──────────┘
──────────────────────────────
│ ┌─────────┐ ┌─────────┐ ┌─────────
│ Worker │ │ Worker │ Worker LLM reasoning
──────── ────────┘ └────────
└───────────────┼───────────────┘
┌──────────▼──────────┐
Tool Registry
│ │ ┌───────────────┐
│ │ │ Built-in │ │ │
│ │ │ MCP │
│ │ │ WASM Sandbox │ │
└───────────────┘
└─────────────────────┘
└─────────────────────────────────────────────────────────────────┘
```
### Core Components
@@ -227,25 +201,33 @@ External content passes through multiple security layers:
| **Router** | Classifies user intent (command, query, task) |
| **Scheduler** | Manages parallel job execution with priorities |
| **Worker** | Executes jobs with LLM reasoning and tool calls |
| **Orchestrator** | Container lifecycle, LLM proxying, per-job auth |
| **Web Gateway** | Browser UI with chat, memory, jobs, logs, extensions, routines |
| **Routines Engine** | Scheduled (cron) and reactive (event, webhook) background tasks |
| **Workspace** | Persistent memory with hybrid search |
| **Safety Layer** | Prompt injection defense and content sanitization |
## Usage
```bash
# First-time setup (configures database, auth, etc.)
ironclaw onboard
### CLI Mode
# Start interactive REPL
```bash
# Start interactive CLI
cargo run
# With debug logging
RUST_LOG=ironclaw=debug cargo run
```
### HTTP Server
```bash
# Start with HTTP webhook server
HTTP_PORT=8080 cargo run
# Send a request
curl -X POST http://localhost:8080/webhook \
-H "Content-Type: application/json" \
-d '{"message": "Hello, IronClaw!"}'
```
## Development
```bash
@@ -256,16 +238,12 @@ cargo fmt
cargo clippy --all --benches --tests --examples --all-features
# Run tests
createdb ironclaw_test
cargo test
# Run specific test
cargo test test_name
```
- **Telegram channel**: See [docs/TELEGRAM_SETUP.md](docs/TELEGRAM_SETUP.md) for setup and DM pairing.
- **Changing channel sources**: Run `./channels-src/telegram/build.sh` before `cargo build` so the updated WASM is bundled.
## OpenClaw Heritage
IronClaw is a Rust reimplementation inspired by [OpenClaw](https://github.com/openclaw/openclaw). See [FEATURE_PARITY.md](FEATURE_PARITY.md) for the complete tracking matrix.
-106
View File
@@ -1,106 +0,0 @@
//! Build script: compile Telegram channel WASM from source.
//!
//! Do not commit compiled WASM binaries — they are a supply chain risk.
//! This script builds telegram.wasm from channels-src/telegram before the main crate compiles.
//!
//! Reproducible build:
//! cargo build --release
//! (build.rs invokes the channel build automatically)
//!
//! Prerequisites: rustup target add wasm32-wasip2, cargo install wasm-tools
use std::env;
use std::path::PathBuf;
use std::process::Command;
fn main() {
let manifest_dir = env::var("CARGO_MANIFEST_DIR").unwrap();
let root = PathBuf::from(&manifest_dir);
let channel_dir = root.join("channels-src/telegram");
let wasm_out = channel_dir.join("telegram.wasm");
// Rerun when channel source or build script changes
println!("cargo:rerun-if-changed=channels-src/telegram/src");
println!("cargo:rerun-if-changed=channels-src/telegram/Cargo.toml");
println!("cargo:rerun-if-changed=wit/channel.wit");
if !channel_dir.is_dir() {
return;
}
// Build WASM module
let status = match Command::new("cargo")
.args([
"build",
"--release",
"--target",
"wasm32-wasip2",
"--manifest-path",
channel_dir.join("Cargo.toml").to_str().unwrap(),
])
.current_dir(&root)
.status()
{
Ok(s) => s,
Err(_) => {
eprintln!(
"cargo:warning=Telegram channel build failed. Run: ./channels-src/telegram/build.sh"
);
return;
}
};
if !status.success() {
eprintln!(
"cargo:warning=Telegram channel build failed. Run: ./channels-src/telegram/build.sh"
);
return;
}
let raw_wasm = channel_dir.join("target/wasm32-wasip2/release/telegram_channel.wasm");
if !raw_wasm.exists() {
eprintln!(
"cargo:warning=Telegram WASM output not found at {:?}",
raw_wasm
);
return;
}
// Convert to component and strip (wasm-tools)
let component_ok = Command::new("wasm-tools")
.args([
"component",
"new",
raw_wasm.to_str().unwrap(),
"-o",
wasm_out.to_str().unwrap(),
])
.current_dir(&root)
.status()
.map(|s| s.success())
.unwrap_or(false);
if !component_ok {
// Fallback: copy raw module if wasm-tools unavailable
if std::fs::copy(&raw_wasm, &wasm_out).is_err() {
eprintln!("cargo:warning=wasm-tools not found. Run: cargo install wasm-tools");
}
} else {
// Strip debug info (use temp file to avoid clobbering)
let stripped = wasm_out.with_extension("wasm.stripped");
let strip_ok = Command::new("wasm-tools")
.args([
"strip",
wasm_out.to_str().unwrap(),
"-o",
stripped.to_str().unwrap(),
])
.current_dir(&root)
.status()
.map(|s| s.success())
.unwrap_or(false);
if strip_ok {
let _ = std::fs::rename(&stripped, &wasm_out);
}
}
}
-23
View File
@@ -1,23 +0,0 @@
[package]
name = "discord-channel"
version = "0.1.0"
edition = "2021"
description = "Discord channel for IronClaw"
license = "MIT OR Apache-2.0"
publish = false
[dependencies]
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
wit-bindgen = "0.41.0"
[lib]
crate-type = ["cdylib"]
[profile.release]
strip = true
opt-level = "s"
lto = true
codegen-units = 1
-121
View File
@@ -1,121 +0,0 @@
# Discord Channel for IronClaw
WASM channel for Discord integration - handle slash commands and button interactions via webhooks.
## Features
- **Slash Commands** - Process Discord slash commands
- **Button Interactions** - Handle button clicks
- **Thread Support** - Respond in threads
- **DM Support** - Handle direct messages
## Setup
1. Create a Discord Application at <https://discord.com/developers/applications>
2. Create a Bot and get the token
3. Set up Interactions URL to point to your IronClaw instance
4. Copy the Application ID and Public Key
5. Store in IronClaw secrets:
```bash
ironclaw secret set discord_bot_token YOUR_BOT_TOKEN
```
**Note:** The `discord_bot_token` secret is the only value read directly by this
Discord channel WASM component. The `discord_app_id` and `discord_public_key`
secrets are used by the IronClaw host (for example, to verify Discord
interaction signatures and manage slash command registration) and are not
accessed from the WASM module itself.
## Discord Configuration
### Register Slash Commands
```bash
curl -X POST \
-H "Authorization: Bot YOUR_BOT_TOKEN" \
-H "Content-Type: application/json" \
https://discord.com/api/v10/applications/YOUR_APP_ID/commands \
-d '{
"name": "ask",
"description": "Ask the AI agent",
"options": [{
"name": "question",
"description": "Your question",
"type": 3,
"required": true
}]
}'
```
### Set Interactions Endpoint
In your Discord app settings, set:
- Interactions Endpoint URL: `https://your-ironclaw.com/webhook/discord`
## Usage Examples
### Slash Command
User types: `/ask question: What is the weather?`
The agent receives:
```text
User: @username
Content: /ask question: What is the weather?
```
### Button Click
When a user clicks a button in a message, the agent receives:
```text
User: @username
Content: [Button clicked] Original message content
```
## Error Handling
If an internal error occurs (e.g., metadata serialization failure), the tool attempts to send an ephemeral message to the user:
```text
❌ Internal Error: Failed to process command metadata.
```
Check the host logs for detailed error information.
## Advanced Usage
### Embeds
To send embeds, include an `embeds` array in the `metadata_json` field of the agent's response. The structure should match the Discord API `embed` object.
## Troubleshooting
### "Invalid Signature"
- Check that `discord_public_key` is set correctly in IronClaw secrets.
- This validation happens on the host before reaching the WASM.
### "401 Unauthorized"
- Check that `discord_bot_token` is set correctly in IronClaw secrets.
- Ensure the bot is added to the server.
### "Interaction Failed"
- The interaction might have timed out (Discord requires a response within 3 seconds).
- The `interactions_endpoint_url` might be unreachable.
## Building
```bash
cd channels-src/discord
cargo build --target wasm32-wasi --release
```
## License
MIT/Apache-2.0
@@ -1,39 +0,0 @@
{
"type": "channel",
"name": "discord",
"description": "Discord Gateway/Webhook channel for handling slash commands, buttons, and messages",
"capabilities": {
"http": {
"allowlist": [
{ "host": "discord.com", "path_prefix": "/api/v10" }
],
"credentials": {
"discord_bot_token": {
"secret_name": "discord_bot_token",
"location": { "type": "header", "header_name": "Authorization", "prefix": "Bot " },
"host_patterns": ["discord.com"]
}
},
"rate_limit": {
"requests_per_minute": 60,
"requests_per_hour": 3600
}
},
"secrets": {
"allowed_names": ["discord_bot_token", "discord_*"]
},
"channel": {
"allowed_paths": ["/webhook/discord"],
"allow_polling": false,
"callback_timeout_secs": 45,
"workspace_prefix": "channels/discord/",
"emit_rate_limit": {
"messages_per_minute": 100,
"messages_per_hour": 5000
}
}
},
"config": {
"require_signature_verification": true
}
}
-476
View File
@@ -1,476 +0,0 @@
//! Discord Gateway/Webhook channel for IronClaw.
//!
//! This WASM component implements the channel interface for handling Discord
//! interactions via webhooks and sending messages back to Discord.
//!
//! # Features
//!
//! - URL verification for Discord interactions
//! - Slash command handling
//! - Message event parsing (@mentions, DMs)
//! - Thread support for conversations
//! - Response posting via Discord Web API
//! - Automatic message truncation (> 2000 chars)
//!
//! # Security
//!
//! - Signature validation is handled by the host (webhook secrets)
//! - Bot token is injected by host during HTTP requests
//! - WASM never sees raw credentials
wit_bindgen::generate!({
world: "sandboxed-channel",
path: "../../wit/channel.wit",
});
use serde::{Deserialize, Serialize};
use exports::near::agent::channel::{
AgentResponse, ChannelConfig, Guest, HttpEndpointConfig, IncomingHttpRequest,
OutgoingHttpResponse, StatusUpdate,
};
use near::agent::channel_host::{self, EmittedMessage};
/// Discord interaction wrapper.
#[derive(Debug, Deserialize)]
struct DiscordInteraction {
/// Interaction type (1=Ping, 2=ApplicationCommand, 3=MessageComponent)
#[serde(rename = "type")]
interaction_type: u8,
/// Interaction ID
id: String,
/// Application ID
application_id: String,
/// Guild ID (if in server)
#[allow(dead_code)] // Part of API payload, currently unused
guild_id: Option<String>,
/// Channel ID
channel_id: Option<String>,
/// Member info (if in server)
member: Option<DiscordMember>,
/// User info (if DM)
user: Option<DiscordUser>,
/// Command data (for slash commands)
data: Option<DiscordCommandData>,
/// Message (for component interactions)
message: Option<DiscordMessage>,
/// Token for responding
token: String,
}
#[derive(Debug, Deserialize, Clone)]
struct DiscordMember {
user: DiscordUser,
#[allow(dead_code)] // Part of API payload, currently unused
nick: Option<String>,
}
#[derive(Debug, Deserialize, Clone)]
struct DiscordUser {
id: String,
username: String,
global_name: Option<String>,
}
#[derive(Debug, Deserialize, Clone)]
struct DiscordCommandData {
#[allow(dead_code)] // Part of API payload, currently unused
id: String,
name: String,
options: Option<Vec<DiscordCommandOption>>,
}
#[derive(Debug, Deserialize, Clone)]
struct DiscordCommandOption {
name: String,
value: serde_json::Value,
}
#[derive(Debug, Deserialize, Clone)]
struct DiscordMessage {
#[allow(dead_code)] // Part of API payload, currently unused
id: String,
content: String,
channel_id: String,
#[allow(dead_code)] // Part of API payload, currently unused
author: DiscordUser,
}
/// Metadata stored with emitted messages for response routing.
#[derive(Debug, Serialize, Deserialize)]
struct DiscordMessageMetadata {
/// Discord channel ID
channel_id: String,
/// Interaction ID for followups
interaction_id: String,
/// Interaction token for responding
token: String,
/// Application ID
application_id: String,
/// Thread ID (for forum threads)
thread_id: Option<String>,
}
struct DiscordChannel;
impl Guest for DiscordChannel {
fn on_start(_config_json: String) -> Result<ChannelConfig, String> {
channel_host::log(channel_host::LogLevel::Info, "Discord channel starting");
Ok(ChannelConfig {
display_name: "Discord".to_string(),
http_endpoints: vec![HttpEndpointConfig {
path: "/webhook/discord".to_string(),
methods: vec!["POST".to_string()],
require_secret: true,
}],
poll: None,
})
}
fn on_http_request(req: IncomingHttpRequest) -> OutgoingHttpResponse {
let body_str = match std::str::from_utf8(&req.body) {
Ok(s) => s,
Err(_) => {
return json_response(400, serde_json::json!({"error": "Invalid UTF-8 body"}));
}
};
let interaction: DiscordInteraction = match serde_json::from_str(body_str) {
Ok(i) => i,
Err(e) => {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Failed to parse Discord interaction: {}", e),
);
return json_response(400, serde_json::json!({"error": "Invalid interaction"}));
}
};
match interaction.interaction_type {
// Ping - Discord verification
1 => {
channel_host::log(channel_host::LogLevel::Info, "Responding to Discord ping");
json_response(200, serde_json::json!({"type": 1}))
}
// Application Command (slash command)
2 => {
handle_slash_command(&interaction);
json_response(
200,
serde_json::json!({
"type": 5,
"data": {
"content": "🤔 Thinking..."
}
}),
)
}
// Message Component (buttons, selects)
3 => {
if let Some(ref message) = interaction.message {
handle_message_component(&interaction, message);
}
json_response(200, serde_json::json!({"type": 6}))
}
_ => {
channel_host::log(
channel_host::LogLevel::Warn,
&format!(
"Unknown Discord interaction type: {}",
interaction.interaction_type
),
);
json_response(200, serde_json::json!({"type": 6}))
}
}
}
fn on_poll() {}
fn on_respond(response: AgentResponse) -> Result<(), String> {
let metadata: DiscordMessageMetadata = serde_json::from_str(&response.metadata_json)
.map_err(|e| format!("Failed to parse metadata: {}", e))?;
// Use webhook endpoint for followup
let url = format!(
"https://discord.com/api/v10/webhooks/{}/{}",
metadata.application_id, metadata.token
);
// Truncate content to 2000 characters to comply with Discord limits
let content = truncate_message(&response.content);
let mut payload = serde_json::json!({
"content": content,
});
// Check for embeds in metadata
if let Ok(meta_json) = serde_json::from_str::<serde_json::Value>(&response.metadata_json) {
if let Some(embeds) = meta_json.get("embeds") {
payload["embeds"] = embeds.clone();
}
}
let payload_bytes =
serde_json::to_vec(&payload).map_err(|e| format!("Failed to serialize: {}", e))?;
let headers = serde_json::json!({
"Content-Type": "application/json"
});
let result = channel_host::http_request(
"POST",
&url,
&headers.to_string(),
Some(&payload_bytes),
None,
);
match result {
Ok(http_response) => {
if http_response.status >= 200 && http_response.status < 300 {
channel_host::log(channel_host::LogLevel::Debug, "Posted followup to Discord");
Ok(())
} else {
let body_str = String::from_utf8_lossy(&http_response.body);
Err(format!(
"Discord API error: {} - {}",
http_response.status, body_str
))
}
}
Err(e) => Err(format!("HTTP request failed: {}", e)),
}
}
fn on_status(_update: StatusUpdate) {}
fn on_shutdown() {
channel_host::log(
channel_host::LogLevel::Info,
"Discord channel shutting down",
);
}
}
fn handle_slash_command(interaction: &DiscordInteraction) {
let user = interaction
.member
.as_ref()
.map(|m| &m.user)
.or(interaction.user.as_ref());
let user_id = user.map(|u| u.id.clone()).unwrap_or_default();
let user_name = user
.map(|u| {
u.global_name
.as_ref()
.filter(|s| !s.is_empty())
.unwrap_or(&u.username)
.clone()
})
.unwrap_or_default();
let channel_id = interaction.channel_id.clone().unwrap_or_default();
let command_name = interaction
.data
.as_ref()
.map(|d| d.name.clone())
.unwrap_or_default();
let options = interaction.data.as_ref().and_then(|d| d.options.clone());
let content = if let Some(opts) = options {
let opt_str = opts
.iter()
.map(|o| format!("{}: {}", o.name, o.value))
.collect::<Vec<_>>()
.join(", ");
format!("/{} {}", command_name, opt_str)
} else {
format!("/{}", command_name)
};
let metadata = DiscordMessageMetadata {
channel_id: channel_id.clone(),
interaction_id: interaction.id.clone(),
token: interaction.token.clone(),
application_id: interaction.application_id.clone(),
thread_id: None,
};
let metadata_json = match serde_json::to_string(&metadata) {
Ok(json) => json,
Err(e) => {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Failed to serialize metadata: {}", e),
);
// Attempt to notify user of internal error
let url = format!(
"https://discord.com/api/v10/webhooks/{}/{}",
interaction.application_id, interaction.token
);
let payload = serde_json::json!({
"content": "❌ Internal Error: Failed to process command metadata.",
"flags": 64 // Ephemeral
});
let _ = channel_host::http_request(
"POST",
&url,
&serde_json::json!({"Content-Type": "application/json"}).to_string(),
Some(&serde_json::to_vec(&payload).unwrap_or_default()),
None,
);
return;
}
};
channel_host::emit_message(&EmittedMessage {
user_id,
user_name: Some(user_name),
content,
thread_id: None,
metadata_json,
});
}
fn handle_message_component(interaction: &DiscordInteraction, message: &DiscordMessage) {
// Check member first (for server contexts), then user (for DMs)
let user = interaction
.member
.as_ref()
.map(|m| &m.user)
.or(interaction.user.as_ref());
let user_id = user.map(|u| u.id.clone()).unwrap_or_default();
let user_name = user
.map(|u| {
u.global_name
.as_ref()
.filter(|s| !s.is_empty())
.unwrap_or(&u.username)
.clone()
})
.unwrap_or_default();
let channel_id = message.channel_id.clone();
let metadata = DiscordMessageMetadata {
channel_id: channel_id.clone(),
interaction_id: interaction.id.clone(),
token: interaction.token.clone(),
application_id: interaction.application_id.clone(),
thread_id: None,
};
let metadata_json = match serde_json::to_string(&metadata) {
Ok(json) => json,
Err(e) => {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Failed to serialize metadata: {}", e),
);
return; // Don't emit message if metadata can't be serialized
}
};
channel_host::emit_message(&EmittedMessage {
user_id,
user_name: Some(user_name),
content: format!("[Button clicked] {}", message.content),
thread_id: None,
metadata_json,
});
}
fn json_response(status: u16, value: serde_json::Value) -> OutgoingHttpResponse {
let body = serde_json::to_vec(&value).unwrap_or_default();
let headers = serde_json::json!({"Content-Type": "application/json"});
OutgoingHttpResponse {
status,
headers_json: headers.to_string(),
body,
}
}
export!(DiscordChannel);
fn truncate_message(content: &str) -> String {
if content.len() <= 2000 {
content.to_string()
} else {
let max_bytes = 1990;
let cutoff = content
.char_indices()
.map(|(i, c)| i + c.len_utf8())
.take_while(|&end| end <= max_bytes)
.last()
.unwrap_or(0);
let mut truncated = content[..cutoff].to_string();
truncated.push_str("\n... (truncated)");
truncated
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_truncate_message() {
let short = "Hello world";
assert_eq!(truncate_message(short), short);
let long = "a".repeat(2005);
let truncated = truncate_message(&long);
assert_eq!(truncated.len(), 2006); // 1990 + 16 chars suffix
assert!(truncated.ends_with("\n... (truncated)"));
// Test with multibyte characters (Euro sign is 3 bytes)
// 1000 chars * 3 bytes = 3000 bytes
let multi = "".repeat(1000);
let truncated_multi = truncate_message(&multi);
// 1990 bytes limit. 1990 / 3 = 663 with remainder 1.
// Should truncate at 663 chars (1989 bytes).
// Suffix is 16 bytes. Total: 1989 + 16 = 2005 bytes.
assert!(truncated_multi.len() <= 2006);
assert!(truncated_multi.len() >= 2006 - 4); // Allow for max utf8 char width variance
assert!(truncated_multi.ends_with("\n... (truncated)"));
let content_part = &truncated_multi[..truncated_multi.len() - 16];
assert!(content_part.chars().all(|c| c == '€'));
}
#[test]
fn test_metadata_serialization() {
let metadata = DiscordMessageMetadata {
channel_id: "123".into(),
interaction_id: "456".into(),
token: "abc".into(),
application_id: "789".into(),
thread_id: None,
};
let json = serde_json::to_string(&metadata).unwrap();
let parsed: DiscordMessageMetadata = serde_json::from_str(&json).unwrap();
assert_eq!(parsed.channel_id, "123");
assert_eq!(parsed.interaction_id, "456");
}
}
-497
View File
@@ -1,497 +0,0 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "ahash"
version = "0.8.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
dependencies = [
"cfg-if",
"once_cell",
"version_check",
"zerocopy",
]
[[package]]
name = "anyhow"
version = "1.0.101"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5f0e0fee31ef5ed1ba1316088939cea399010ed7731dba877ed44aeb407a75ea"
[[package]]
name = "bitflags"
version = "2.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "812e12b5285cc515a9c72a5c1d3b6d46a19dac5acfef5265968c166106e31dd3"
[[package]]
name = "block-buffer"
version = "0.10.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
dependencies = [
"generic-array",
]
[[package]]
name = "cfg-if"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
[[package]]
name = "cpufeatures"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
dependencies = [
"libc",
]
[[package]]
name = "crypto-common"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
dependencies = [
"generic-array",
"typenum",
]
[[package]]
name = "digest"
version = "0.10.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
dependencies = [
"block-buffer",
"crypto-common",
"subtle",
]
[[package]]
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "generic-array"
version = "0.14.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
dependencies = [
"typenum",
"version_check",
]
[[package]]
name = "hashbrown"
version = "0.14.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
dependencies = [
"ahash",
]
[[package]]
name = "hashbrown"
version = "0.16.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100"
[[package]]
name = "heck"
version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]]
name = "hex"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
[[package]]
name = "hmac"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
dependencies = [
"digest",
]
[[package]]
name = "id-arena"
version = "2.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954"
[[package]]
name = "indexmap"
version = "2.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7714e70437a7dc3ac8eb7e6f8df75fd8eb422675fc7678aff7364301092b1017"
dependencies = [
"equivalent",
"hashbrown 0.16.1",
"serde",
"serde_core",
]
[[package]]
name = "itoa"
version = "1.0.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "92ecc6618181def0457392ccd0ee51198e065e016d1d527a7ac1b6dc7c1f09d2"
[[package]]
name = "leb128"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "884e2677b40cc8c339eaefcb701c32ef1fd2493d71118dc0ca4b6a736c93bd67"
[[package]]
name = "libc"
version = "0.2.180"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bcc35a38544a891a5f7c865aca548a982ccb3b8650a5b06d0fd33a10283c56fc"
[[package]]
name = "log"
version = "0.4.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
[[package]]
name = "memchr"
version = "2.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
[[package]]
name = "once_cell"
version = "1.21.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
[[package]]
name = "prettyplease"
version = "0.2.37"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
dependencies = [
"proc-macro2",
"syn",
]
[[package]]
name = "proc-macro2"
version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "21b2ebcf727b7760c461f091f9f0f539b77b8e87f2fd88131e7f1b433b3cece4"
dependencies = [
"proc-macro2",
]
[[package]]
name = "semver"
version = "1.0.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d767eb0aabc880b29956c35734170f26ed551a859dbd361d140cdbeca61ab1e2"
[[package]]
name = "serde"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
dependencies = [
"serde_core",
"serde_derive",
]
[[package]]
name = "serde_core"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.149"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
dependencies = [
"itoa",
"memchr",
"serde",
"serde_core",
"zmij",
]
[[package]]
name = "sha2"
version = "0.10.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
dependencies = [
"cfg-if",
"cpufeatures",
"digest",
]
[[package]]
name = "slack-channel"
version = "0.1.0"
dependencies = [
"hex",
"hmac",
"serde",
"serde_json",
"sha2",
"wit-bindgen",
]
[[package]]
name = "smallvec"
version = "1.15.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
[[package]]
name = "spdx"
version = "0.10.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3e17e880bafaeb362a7b751ec46bdc5b61445a188f80e0606e68167cd540fa3"
dependencies = [
"smallvec",
]
[[package]]
name = "subtle"
version = "2.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
[[package]]
name = "syn"
version = "2.0.114"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d4d107df263a3013ef9b1879b0df87d706ff80f65a86ea879bd9c31f9b307c2a"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "typenum"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
[[package]]
name = "unicode-ident"
version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
[[package]]
name = "unicode-xid"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
[[package]]
name = "version_check"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
[[package]]
name = "wasm-encoder"
version = "0.220.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e913f9242315ca39eff82aee0e19ee7a372155717ff0eb082c741e435ce25ed1"
dependencies = [
"leb128",
"wasmparser",
]
[[package]]
name = "wasm-metadata"
version = "0.220.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "185dfcd27fa5db2e6a23906b54c28199935f71d9a27a1a27b3a88d6fee2afae7"
dependencies = [
"anyhow",
"indexmap",
"serde",
"serde_derive",
"serde_json",
"spdx",
"wasm-encoder",
"wasmparser",
]
[[package]]
name = "wasmparser"
version = "0.220.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8d07b6a3b550fefa1a914b6d54fc175dd11c3392da11eee604e6ffc759805d25"
dependencies = [
"ahash",
"bitflags",
"hashbrown 0.14.5",
"indexmap",
"semver",
]
[[package]]
name = "wit-bindgen"
version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a2b3e15cd6068f233926e7d8c7c588b2ec4fb7cc7bf3824115e7c7e2a8485a3"
dependencies = [
"wit-bindgen-rt",
"wit-bindgen-rust-macro",
]
[[package]]
name = "wit-bindgen-core"
version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b632a5a0fa2409489bd49c9e6d99fcc61bb3d4ce9d1907d44662e75a28c71172"
dependencies = [
"anyhow",
"heck",
"wit-parser",
]
[[package]]
name = "wit-bindgen-rt"
version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7947d0131c7c9da3f01dfde0ab8bd4c4cf3c5bd49b6dba0ae640f1fa752572ea"
dependencies = [
"bitflags",
]
[[package]]
name = "wit-bindgen-rust"
version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4329de4186ee30e2ef30a0533f9b3c123c019a237a7c82d692807bf1b3ee2697"
dependencies = [
"anyhow",
"heck",
"indexmap",
"prettyplease",
"syn",
"wasm-metadata",
"wit-bindgen-core",
"wit-component",
]
[[package]]
name = "wit-bindgen-rust-macro"
version = "0.36.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "177fb7ee1484d113b4792cc480b1ba57664bbc951b42a4beebe573502135b1fc"
dependencies = [
"anyhow",
"prettyplease",
"proc-macro2",
"quote",
"syn",
"wit-bindgen-core",
"wit-bindgen-rust",
]
[[package]]
name = "wit-component"
version = "0.220.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b505603761ed400c90ed30261f44a768317348e49f1864e82ecdc3b2744e5627"
dependencies = [
"anyhow",
"bitflags",
"indexmap",
"log",
"serde",
"serde_derive",
"serde_json",
"wasm-encoder",
"wasm-metadata",
"wasmparser",
"wit-parser",
]
[[package]]
name = "wit-parser"
version = "0.220.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae2a7999ed18efe59be8de2db9cb2b7f84d88b27818c79353dfc53131840fe1a"
dependencies = [
"anyhow",
"id-arena",
"indexmap",
"log",
"semver",
"serde",
"serde_derive",
"serde_json",
"unicode-xid",
"wasmparser",
]
[[package]]
name = "zerocopy"
version = "0.8.39"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db6d35d663eadb6c932438e763b262fe1a70987f9ae936e60158176d710cae4a"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.8.39"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4122cd3169e94605190e77839c9a40d40ed048d305bfdc146e7df40ab0f3e517"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "zmij"
version = "1.0.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3ff05f8caa9038894637571ae6b9e29466c1f4f829d26c9b28f869a29cbe3445"
+1 -1
View File
@@ -30,7 +30,7 @@ if [ -f "$WASM_PATH" ]; then
wasm-tools strip slack.wasm -o slack.wasm
echo "Built: slack.wasm ($(du -h slack.wasm | cut -f1))"
echo "Copy slack.wasm and slack.capabilities.json to ~/.ironclaw/channels/"
echo "Copy slack.wasm and slack.capabilities.json to ~/.near-agent/channels/"
else
echo "Error: WASM output not found at $WASM_PATH"
exit 1
+25 -41
View File
@@ -27,7 +27,7 @@ use serde::{Deserialize, Serialize};
// Re-export generated types
use exports::near::agent::channel::{
AgentResponse, ChannelConfig, Guest, HttpEndpointConfig, IncomingHttpRequest,
OutgoingHttpResponse, StatusUpdate,
OutgoingHttpResponse, PollConfig,
};
use near::agent::channel_host::{self, EmittedMessage};
@@ -108,10 +108,7 @@ struct SlackPostMessageResponse {
#[derive(Debug, Deserialize)]
struct SlackConfig {
/// Name of secret containing signing secret (for verification by host).
/// Parsed from config for forward compatibility; not yet used in WASM
/// (host handles signature verification).
#[serde(default = "default_signing_secret_name")]
#[allow(dead_code)]
signing_secret_name: String,
}
@@ -178,7 +175,11 @@ impl Guest for SlackChannel {
// Actual event callback
"event_callback" => {
if let Some(event) = event_wrapper.event {
handle_slack_event(event, event_wrapper.team_id, event_wrapper.event_id);
handle_slack_event(
event,
event_wrapper.team_id,
event_wrapper.event_id,
);
}
// Always respond 200 quickly to Slack (they have a 3s timeout)
json_response(200, serde_json::json!({"ok": true}))
@@ -229,7 +230,6 @@ impl Guest for SlackChannel {
"https://slack.com/api/chat.postMessage",
&headers.to_string(),
Some(&payload_bytes),
None,
);
match result {
@@ -243,15 +243,14 @@ impl Guest for SlackChannel {
// Parse Slack response
let slack_response: SlackPostMessageResponse =
serde_json::from_slice(&http_response.body)
.map_err(|e| format!("Failed to parse Slack response: {}", e))?;
serde_json::from_slice(&http_response.body).map_err(|e| {
format!("Failed to parse Slack response: {}", e)
})?;
if !slack_response.ok {
return Err(format!(
"Slack API error: {}",
slack_response
.error
.unwrap_or_else(|| "unknown".to_string())
slack_response.error.unwrap_or_else(|| "unknown".to_string())
));
}
@@ -270,24 +269,23 @@ impl Guest for SlackChannel {
}
}
fn on_status(_update: StatusUpdate) {}
fn on_shutdown() {
channel_host::log(channel_host::LogLevel::Info, "Slack channel shutting down");
}
}
/// Handle a Slack event and emit message if applicable.
fn handle_slack_event(event: SlackEvent, team_id: Option<String>, _event_id: Option<String>) {
fn handle_slack_event(
event: SlackEvent,
team_id: Option<String>,
_event_id: Option<String>,
) {
match event.event_type.as_str() {
// Direct mention of the bot
"app_mention" => {
if let (Some(user), Some(channel), Some(text), Some(ts)) = (
event.user,
event.channel.clone(),
event.text,
event.ts.clone(),
) {
if let (Some(user), Some(channel), Some(text), Some(ts)) =
(event.user, event.channel.clone(), event.text, event.ts.clone())
{
emit_message(user, text, channel, event.thread_ts.or(Some(ts)), team_id);
}
}
@@ -299,12 +297,9 @@ fn handle_slack_event(event: SlackEvent, team_id: Option<String>, _event_id: Opt
return;
}
if let (Some(user), Some(channel), Some(text), Some(ts)) = (
event.user,
event.channel.clone(),
event.text,
event.ts.clone(),
) {
if let (Some(user), Some(channel), Some(text), Some(ts)) =
(event.user, event.channel.clone(), event.text, event.ts.clone())
{
// Only process DMs (channel IDs starting with D)
if channel.starts_with('D') {
emit_message(user, text, channel, event.thread_ts.or(Some(ts)), team_id);
@@ -338,18 +333,13 @@ fn emit_message(
team_id,
};
let metadata_json = serde_json::to_string(&metadata).unwrap_or_else(|e| {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Failed to serialize Slack metadata: {}", e),
);
"{}".to_string()
});
let metadata_json =
serde_json::to_string(&metadata).unwrap_or_else(|_| "{}".to_string());
// Strip @ mentions of the bot from the text for cleaner messages
let cleaned_text = strip_bot_mention(&text);
channel_host::emit_message(&EmittedMessage {
channel_host::emit_message(EmittedMessage {
user_id,
user_name: None, // Could fetch from Slack API if needed
content: cleaned_text,
@@ -372,13 +362,7 @@ fn strip_bot_mention(text: &str) -> String {
/// Create a JSON HTTP response.
fn json_response(status: u16, value: serde_json::Value) -> OutgoingHttpResponse {
let body = serde_json::to_vec(&value).unwrap_or_else(|e| {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Failed to serialize JSON response: {}", e),
);
Vec::new()
});
let body = serde_json::to_vec(&value).unwrap_or_default();
let headers = serde_json::json!({"Content-Type": "application/json"});
OutgoingHttpResponse {
+2 -2
View File
@@ -32,8 +32,8 @@ if [ -f "$WASM_PATH" ]; then
echo "Built: telegram.wasm ($(du -h telegram.wasm | cut -f1))"
echo ""
echo "To install:"
echo " mkdir -p ~/.ironclaw/channels"
echo " cp telegram.wasm telegram.capabilities.json ~/.ironclaw/channels/"
echo " mkdir -p ~/.near-agent/channels"
echo " cp telegram.wasm telegram.capabilities.json ~/.near-agent/channels/"
echo ""
echo "Then add your bot token to secrets:"
echo " # Set TELEGRAM_BOT_TOKEN in your environment or secrets store"
+100 -392
View File
@@ -72,10 +72,6 @@ struct TelegramMessage {
/// Message text.
text: Option<String>,
/// Caption for media (photo, video, document, etc.).
#[serde(default)]
caption: Option<String>,
/// Original message if this is a reply.
reply_to_message: Option<Box<TelegramMessage>>,
@@ -164,21 +160,6 @@ const POLLING_STATE_PATH: &str = "state/last_update_id";
/// Workspace path for persisting owner_id across WASM callbacks.
const OWNER_ID_PATH: &str = "state/owner_id";
/// Workspace path for persisting dm_policy across WASM callbacks.
const DM_POLICY_PATH: &str = "state/dm_policy";
/// Workspace path for persisting allow_from (JSON array) across WASM callbacks.
const ALLOW_FROM_PATH: &str = "state/allow_from";
/// Channel name for pairing store (used by pairing host APIs).
const CHANNEL_NAME: &str = "telegram";
/// Workspace path for persisting bot_username for mention detection in groups.
const BOT_USERNAME_PATH: &str = "state/bot_username";
/// Workspace path for persisting respond_to_all_group_messages flag.
const RESPOND_TO_ALL_GROUP_PATH: &str = "state/respond_to_all_group_messages";
// ============================================================================
// Channel Metadata
// ============================================================================
@@ -215,14 +196,6 @@ struct TelegramConfig {
#[serde(default)]
owner_id: Option<i64>,
/// DM policy: "pairing" (default), "allowlist", or "open".
#[serde(default)]
dm_policy: Option<String>,
/// Allowed sender IDs/usernames from config (merged with pairing-approved store).
#[serde(default)]
allow_from: Option<Vec<String>>,
/// Whether to respond to all group messages (not just mentions).
#[serde(default)]
respond_to_all_group_messages: bool,
@@ -284,24 +257,6 @@ impl Guest for TelegramChannel {
);
}
// Persist dm_policy and allow_from for DM pairing in handle_message
let dm_policy = config.dm_policy.as_deref().unwrap_or("pairing").to_string();
let _ = channel_host::workspace_write(DM_POLICY_PATH, &dm_policy);
let allow_from_json = serde_json::to_string(&config.allow_from.unwrap_or_default())
.unwrap_or_else(|_| "[]".to_string());
let _ = channel_host::workspace_write(ALLOW_FROM_PATH, &allow_from_json);
// Persist bot_username and respond_to_all_group_messages for group handling
let _ = channel_host::workspace_write(
BOT_USERNAME_PATH,
&config.bot_username.unwrap_or_default(),
);
let _ = channel_host::workspace_write(
RESPOND_TO_ALL_GROUP_PATH,
&config.respond_to_all_group_messages.to_string(),
);
// Mode is determined by whether the host injected a tunnel_url
// If tunnel is configured, use webhooks. Otherwise, use polling.
let webhook_mode = config.tunnel_url.is_some();
@@ -433,9 +388,7 @@ impl Guest for TelegramChannel {
let headers = serde_json::json!({});
// 35s HTTP timeout outlives Telegram's 30s server-side long-poll
let result =
channel_host::http_request("GET", &url, &headers.to_string(), None, Some(35_000));
let result = channel_host::http_request("GET", &url, &headers.to_string(), None);
match result {
Ok(response) => {
@@ -508,52 +461,72 @@ impl Guest for TelegramChannel {
}
fn on_respond(response: AgentResponse) -> Result<(), String> {
// Parse metadata to get chat info
let metadata: TelegramMessageMetadata = serde_json::from_str(&response.metadata_json)
.map_err(|e| format!("Failed to parse metadata: {}", e))?;
// Try sending with Markdown first; fall back to plain text if Telegram
// can't parse the entities (e.g. model leaked <tool_call> with underscores).
let result = send_message(
metadata.chat_id,
&response.content,
metadata.message_id,
Some("Markdown"),
// Build sendMessage payload
let mut payload = serde_json::json!({
"chat_id": metadata.chat_id,
"text": response.content,
"parse_mode": "Markdown",
});
// Reply to the original message for context
payload["reply_to_message_id"] = serde_json::Value::Number(metadata.message_id.into());
let payload_bytes = serde_json::to_vec(&payload)
.map_err(|e| format!("Failed to serialize payload: {}", e))?;
// Make HTTP request to Telegram API
// The bot token is injected into the URL by the host
let headers = serde_json::json!({
"Content-Type": "application/json"
});
let result = channel_host::http_request(
"POST",
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage",
&headers.to_string(),
Some(&payload_bytes),
);
match result {
Ok(msg_id) => {
Ok(http_response) => {
if http_response.status != 200 {
let body_str = String::from_utf8_lossy(&http_response.body);
return Err(format!(
"Telegram API returned status {}: {}",
http_response.status, body_str
));
}
// Parse Telegram response
let api_response: TelegramApiResponse<SentMessage> =
serde_json::from_slice(&http_response.body)
.map_err(|e| format!("Failed to parse Telegram response: {}", e))?;
if !api_response.ok {
return Err(format!(
"Telegram API error: {}",
api_response
.description
.unwrap_or_else(|| "unknown".to_string())
));
}
channel_host::log(
channel_host::LogLevel::Debug,
&format!(
"Sent message to chat {}: message_id={}",
metadata.chat_id, msg_id
metadata.chat_id,
api_response.result.map(|r| r.message_id).unwrap_or(0)
),
);
Ok(())
}
Err(SendError::ParseEntities(detail)) => {
channel_host::log(
channel_host::LogLevel::Warn,
&format!("Markdown parse failed ({}), retrying as plain text", detail),
);
let msg_id = send_message(
metadata.chat_id,
&response.content,
metadata.message_id,
None,
)
.map_err(|e| format!("Plain-text retry also failed: {}", e))?;
channel_host::log(
channel_host::LogLevel::Debug,
&format!(
"Sent plain-text message to chat {}: message_id={}",
metadata.chat_id, msg_id
),
);
Ok(())
}
Err(e) => Err(e.to_string()),
Err(e) => Err(format!("HTTP request failed: {}", e)),
}
}
@@ -595,7 +568,6 @@ impl Guest for TelegramChannel {
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendChatAction",
&headers.to_string(),
Some(&payload_bytes),
None,
);
if let Err(e) = result {
@@ -614,101 +586,6 @@ impl Guest for TelegramChannel {
}
}
// ============================================================================
// Send Message Helper
// ============================================================================
/// Errors from send_message, split so callers can match on parse-entity failures.
enum SendError {
/// Telegram returned 400 with "can't parse entities" (Markdown issue).
ParseEntities(String),
/// Any other failure.
Other(String),
}
impl std::fmt::Display for SendError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
SendError::ParseEntities(detail) => write!(f, "parse entities error: {}", detail),
SendError::Other(msg) => write!(f, "{}", msg),
}
}
}
/// Send a message via the Telegram Bot API.
///
/// Returns the sent message_id on success. When `parse_mode` is set and
/// Telegram returns a 400 "can't parse entities" error, returns
/// `SendError::ParseEntities` so the caller can retry without formatting.
fn send_message(
chat_id: i64,
text: &str,
reply_to_message_id: i64,
parse_mode: Option<&str>,
) -> Result<i64, SendError> {
let mut payload = serde_json::json!({
"chat_id": chat_id,
"text": text,
"reply_to_message_id": reply_to_message_id,
});
if let Some(mode) = parse_mode {
payload["parse_mode"] = serde_json::Value::String(mode.to_string());
}
let payload_bytes = serde_json::to_vec(&payload)
.map_err(|e| SendError::Other(format!("Failed to serialize payload: {}", e)))?;
let headers = serde_json::json!({ "Content-Type": "application/json" });
let result = channel_host::http_request(
"POST",
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage",
&headers.to_string(),
Some(&payload_bytes),
None,
);
match result {
Ok(http_response) => {
if http_response.status == 400 {
let body_str = String::from_utf8_lossy(&http_response.body);
if body_str.contains("can't parse entities") {
return Err(SendError::ParseEntities(body_str.to_string()));
}
return Err(SendError::Other(format!(
"Telegram API returned 400: {}",
body_str
)));
}
if http_response.status != 200 {
let body_str = String::from_utf8_lossy(&http_response.body);
return Err(SendError::Other(format!(
"Telegram API returned status {}: {}",
http_response.status, body_str
)));
}
let api_response: TelegramApiResponse<SentMessage> =
serde_json::from_slice(&http_response.body)
.map_err(|e| SendError::Other(format!("Failed to parse response: {}", e)))?;
if !api_response.ok {
return Err(SendError::Other(format!(
"Telegram API error: {}",
api_response
.description
.unwrap_or_else(|| "unknown".to_string())
)));
}
Ok(api_response.result.map(|r| r.message_id).unwrap_or(0))
}
Err(e) => Err(SendError::Other(format!("HTTP request failed: {}", e))),
}
}
// ============================================================================
// Webhook Management
// ============================================================================
@@ -727,7 +604,6 @@ fn delete_webhook() -> Result<(), String> {
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/deleteWebhook",
&headers.to_string(),
None,
None,
);
match result {
@@ -790,7 +666,6 @@ fn register_webhook(tunnel_url: &str, webhook_secret: Option<&str>) -> Result<()
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/setWebhook",
&headers.to_string(),
Some(&body_bytes),
None,
);
match result {
@@ -825,48 +700,6 @@ fn register_webhook(tunnel_url: &str, webhook_secret: Option<&str>) -> Result<()
}
}
// ============================================================================
// Pairing Reply
// ============================================================================
/// Send a pairing code message to a chat. Used when an unknown user DMs the bot.
fn send_pairing_reply(chat_id: i64, code: &str) -> Result<(), String> {
let payload = serde_json::json!({
"chat_id": chat_id,
"text": format!(
"To pair with this bot, run: `ironclaw pairing approve telegram {}`",
code
),
"parse_mode": "Markdown",
});
let payload_bytes =
serde_json::to_vec(&payload).map_err(|e| format!("Failed to serialize payload: {}", e))?;
let headers = serde_json::json!({
"Content-Type": "application/json"
});
let result = channel_host::http_request(
"POST",
"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage",
&headers.to_string(),
Some(&payload_bytes),
None,
);
match result {
Ok(response) => {
if response.status != 200 {
let body_str = String::from_utf8_lossy(&response.body);
return Err(format!("HTTP {}: {}", response.status, body_str));
}
Ok(())
}
Err(e) => Err(format!("HTTP request failed: {}", e)),
}
}
// ============================================================================
// Update Handling
// ============================================================================
@@ -886,16 +719,11 @@ fn handle_update(update: TelegramUpdate) {
/// Process a single message.
fn handle_message(message: TelegramMessage) {
// Use text or caption (for media messages)
let content = message
.text
.filter(|t| !t.is_empty())
.or_else(|| message.caption.filter(|c| !c.is_empty()))
.unwrap_or_default();
if content.is_empty() {
return;
}
// Skip messages without text
let text = match message.text {
Some(t) if !t.is_empty() => t,
_ => return,
};
// Skip messages without a sender (channel posts)
let from = match message.from {
@@ -908,105 +736,41 @@ fn handle_message(message: TelegramMessage) {
return;
}
let is_private = message.chat.chat_type == "private";
// Owner validation: when owner_id is set, only that user can message
let owner_id_str = channel_host::workspace_read(OWNER_ID_PATH).filter(|s| !s.is_empty());
if let Some(ref id_str) = owner_id_str {
if let Ok(owner_id) = id_str.parse::<i64>() {
if from.id != owner_id {
channel_host::log(
channel_host::LogLevel::Debug,
&format!(
"Dropping message from non-owner user {} (owner: {})",
from.id, owner_id
),
);
return;
}
}
} else if is_private {
// No owner_id: apply dm_policy for private chats
let dm_policy =
channel_host::workspace_read(DM_POLICY_PATH).unwrap_or_else(|| "pairing".to_string());
if dm_policy != "open" {
// Build effective allow list: config allow_from + pairing store
let mut allowed: Vec<String> = channel_host::workspace_read(ALLOW_FROM_PATH)
.and_then(|s| serde_json::from_str(&s).ok())
.unwrap_or_default();
if let Ok(store_allowed) = channel_host::pairing_read_allow_from(CHANNEL_NAME) {
allowed.extend(store_allowed);
}
let id_str = from.id.to_string();
let username_opt = from.username.as_deref();
let is_allowed = allowed.contains(&"*".to_string())
|| allowed.contains(&id_str)
|| username_opt.map_or(false, |u| allowed.contains(&u.to_string()));
if !is_allowed {
if dm_policy == "pairing" {
// Upsert pairing request and send reply
let meta = serde_json::json!({
"chat_id": message.chat.id,
"user_id": from.id,
"username": username_opt,
})
.to_string();
match channel_host::pairing_upsert_request(CHANNEL_NAME, &id_str, &meta) {
Ok(result) => {
channel_host::log(
channel_host::LogLevel::Info,
&format!(
"Pairing request for user {} (chat {}): code {}",
from.id, message.chat.id, result.code
),
);
if result.created {
let _ = send_pairing_reply(message.chat.id, &result.code);
}
}
Err(e) => {
channel_host::log(
channel_host::LogLevel::Error,
&format!("Pairing upsert failed: {}", e),
);
}
}
// Owner validation: silently drop messages from non-owner users
if let Some(owner_id_str) = channel_host::workspace_read(OWNER_ID_PATH) {
if !owner_id_str.is_empty() {
if let Ok(owner_id) = owner_id_str.parse::<i64>() {
if from.id != owner_id {
channel_host::log(
channel_host::LogLevel::Debug,
&format!(
"Dropping message from non-owner user {} (owner: {})",
from.id, owner_id
),
);
return;
}
return;
}
}
}
// For group chats, only respond if bot was mentioned or respond_to_all is enabled
let is_private = message.chat.chat_type == "private";
// For group chats, check if the bot was mentioned
// TODO: Read bot_username from config and check mentions
// For now, process all messages in private chats and groups
if !is_private {
let respond_to_all = channel_host::workspace_read(RESPOND_TO_ALL_GROUP_PATH)
.as_deref()
.unwrap_or("false")
== "true";
// In groups, only respond if there's a bot mention or command
// This is a simplified check - proper implementation would use entities
let has_command = text.starts_with('/');
let has_mention = text.contains('@');
if !respond_to_all {
let has_command = content.starts_with('/');
let bot_username = channel_host::workspace_read(BOT_USERNAME_PATH).unwrap_or_default();
let has_bot_mention = if bot_username.is_empty() {
content.contains('@')
} else {
let mention = format!("@{}", bot_username);
content.to_lowercase().contains(&mention.to_lowercase())
};
if !has_command && !has_bot_mention {
channel_host::log(
channel_host::LogLevel::Debug,
&format!("Ignoring group message without mention: {}", content),
);
return;
}
if !has_command && !has_mention {
channel_host::log(
channel_host::LogLevel::Debug,
&format!("Ignoring group message without mention: {}", text),
);
return;
}
}
@@ -1028,30 +792,17 @@ fn handle_message(message: TelegramMessage) {
let metadata_json = serde_json::to_string(&metadata).unwrap_or_else(|_| "{}".to_string());
// Clean the message text (strip bot mentions and commands)
let bot_username = channel_host::workspace_read(BOT_USERNAME_PATH).unwrap_or_default();
let cleaned_text = clean_message_text(
&content,
if bot_username.is_empty() {
None
} else {
Some(bot_username.as_str())
},
);
let cleaned_text = clean_message_text(&text);
// For /start with no args, emit placeholder so agent can respond with welcome
let content_to_emit = if cleaned_text.is_empty() && content.trim().starts_with('/') {
"[User started the bot]".to_string()
} else if cleaned_text.is_empty() {
if cleaned_text.is_empty() {
return;
} else {
cleaned_text
};
}
// Emit the message to the agent
channel_host::emit_message(&EmittedMessage {
user_id: from.id.to_string(),
user_name: Some(user_name),
content: content_to_emit,
content: cleaned_text,
thread_id: None, // Telegram doesn't have threads in the same way
metadata_json,
});
@@ -1066,8 +817,7 @@ fn handle_message(message: TelegramMessage) {
}
/// Clean message text by removing bot commands and @mentions at the start.
/// When bot_username is set, only strips that specific mention; otherwise strips any leading @mention.
fn clean_message_text(text: &str, bot_username: Option<&str>) -> String {
fn clean_message_text(text: &str) -> String {
let mut result = text.trim().to_string();
// Remove leading /command
@@ -1082,30 +832,11 @@ fn clean_message_text(text: &str, bot_username: Option<&str>) -> String {
// Remove leading @mention
if result.starts_with('@') {
if let Some(bot) = bot_username {
let mention = format!("@{}", bot);
let mention_lower = mention.to_lowercase();
let result_lower = result.to_lowercase();
if result_lower.starts_with(&mention_lower) {
let rest = result[mention.len()..].trim_start();
if rest.is_empty() {
return String::new();
}
result = rest.to_string();
} else if let Some(space_idx) = result.find(' ') {
// Different leading @mention - only strip if it's the bot
let first_word = &result[..space_idx];
if first_word.eq_ignore_ascii_case(&mention) {
result = result[space_idx..].trim_start().to_string();
}
}
if let Some(space_idx) = result.find(' ') {
result = result[space_idx..].trim_start().to_string();
} else {
// No bot_username: strip any leading @mention
if let Some(space_idx) = result.find(' ') {
result = result[space_idx..].trim_start().to_string();
} else {
return String::new();
}
// Just a mention with no text
return String::new();
}
}
@@ -1141,22 +872,12 @@ mod tests {
#[test]
fn test_clean_message_text() {
// Without bot_username: strips any leading @mention
assert_eq!(clean_message_text("/start hello", None), "hello");
assert_eq!(clean_message_text("@bot hello world", None), "hello world");
assert_eq!(clean_message_text("/start", None), "");
assert_eq!(clean_message_text("@botname", None), "");
assert_eq!(clean_message_text("just text", None), "just text");
assert_eq!(clean_message_text(" spaced ", None), "spaced");
// With bot_username: only strips @MyBot, not @alice
assert_eq!(clean_message_text("@MyBot hello", Some("MyBot")), "hello");
assert_eq!(clean_message_text("@mybot hi", Some("MyBot")), "hi");
assert_eq!(
clean_message_text("@alice hello", Some("MyBot")),
"@alice hello"
);
assert_eq!(clean_message_text("@MyBot", Some("MyBot")), "");
assert_eq!(clean_message_text("/start hello"), "hello");
assert_eq!(clean_message_text("@bot hello world"), "hello world");
assert_eq!(clean_message_text("/start"), "");
assert_eq!(clean_message_text("@botname"), "");
assert_eq!(clean_message_text("just text"), "just text");
assert_eq!(clean_message_text(" spaced "), "spaced");
}
#[test]
@@ -1224,17 +945,4 @@ mod tests {
assert_eq!(from.id, 789);
assert_eq!(from.first_name, "John");
}
#[test]
fn test_parse_message_with_caption() {
let json = r#"{
"message_id": 1,
"from": {"id": 1, "is_bot": false, "first_name": "A"},
"chat": {"id": 1, "type": "private"},
"caption": "What's in this image?"
}"#;
let msg: TelegramMessage = serde_json::from_str(json).unwrap();
assert_eq!(msg.text, None);
assert_eq!(msg.caption.as_deref(), Some("What's in this image?"));
}
}
@@ -1 +1,43 @@
{"type":"channel","name":"telegram","description":"Telegram Bot API channel for receiving and responding to Telegram messages","capabilities":{"http":{"allowlist":[{"host":"api.telegram.org","path_prefix":"/bot"}],"credentials":{"telegram_bot":{"secret_name":"telegram_bot_token","location":{"type":"url_path","placeholder":"{TELEGRAM_BOT_TOKEN}"},"host_patterns":["api.telegram.org"]}},"rate_limit":{"requests_per_minute":30,"requests_per_hour":1000}},"secrets":{"allowed_names":["telegram_*"]},"channel":{"allowed_paths":["/webhook/telegram"],"allow_polling":true,"min_poll_interval_ms":30000,"workspace_prefix":"channels/telegram/","emit_rate_limit":{"messages_per_minute":100,"messages_per_hour":5000}}},"config":{"bot_username":null,"owner_id":null,"respond_to_all_group_messages":false,"polling_enabled":false,"poll_interval_ms":30000,"dm_policy":"pairing","allow_from":[]}}
{
"type": "channel",
"name": "telegram",
"description": "Telegram Bot API channel for receiving and responding to Telegram messages",
"capabilities": {
"http": {
"allowlist": [
{ "host": "api.telegram.org", "path_prefix": "/bot" }
],
"credentials": {
"telegram_bot": {
"secret_name": "telegram_bot_token",
"location": { "type": "url_path", "placeholder": "{TELEGRAM_BOT_TOKEN}" },
"host_patterns": ["api.telegram.org"]
}
},
"rate_limit": {
"requests_per_minute": 30,
"requests_per_hour": 1000
}
},
"secrets": {
"allowed_names": ["telegram_*"]
},
"channel": {
"allowed_paths": ["/webhook/telegram"],
"allow_polling": true,
"min_poll_interval_ms": 30000,
"workspace_prefix": "channels/telegram/",
"emit_rate_limit": {
"messages_per_minute": 100,
"messages_per_hour": 5000
}
}
},
"config": {
"bot_username": null,
"owner_id": null,
"respond_to_all_group_messages": false,
"polling_enabled": false,
"poll_interval_ms": 30000
}
}
Binary file not shown.
@@ -30,7 +30,7 @@ use serde::{Deserialize, Serialize};
// Re-export generated types
use exports::near::agent::channel::{
AgentResponse, ChannelConfig, Guest, HttpEndpointConfig, IncomingHttpRequest,
OutgoingHttpResponse, StatusUpdate,
OutgoingHttpResponse,
};
use near::agent::channel_host::{self, EmittedMessage};
@@ -254,19 +254,10 @@ struct WhatsAppChannel;
impl Guest for WhatsAppChannel {
fn on_start(config_json: String) -> Result<ChannelConfig, String> {
let config: WhatsAppConfig = match serde_json::from_str(&config_json) {
Ok(c) => c,
Err(e) => {
channel_host::log(
channel_host::LogLevel::Warn,
&format!("Failed to parse WhatsApp config, using defaults: {}", e),
);
WhatsAppConfig {
api_version: default_api_version(),
reply_to_message: default_reply_to_message(),
}
}
};
let config: WhatsAppConfig = serde_json::from_str(&config_json).unwrap_or(WhatsAppConfig {
api_version: default_api_version(),
reply_to_message: default_reply_to_message(),
});
channel_host::log(
channel_host::LogLevel::Info,
@@ -276,9 +267,6 @@ impl Guest for WhatsAppChannel {
),
);
// Persist api_version in workspace so on_respond() can read it
let _ = channel_host::workspace_write("channels/whatsapp/api_version", &config.api_version);
// WhatsApp Cloud API is webhook-only, no polling available
Ok(ChannelConfig {
display_name: "WhatsApp".to_string(),
@@ -339,16 +327,11 @@ impl Guest for WhatsAppChannel {
let metadata: WhatsAppMessageMetadata = serde_json::from_str(&response.metadata_json)
.map_err(|e| format!("Failed to parse metadata: {}", e))?;
// Read api_version from workspace (set during on_start), fallback to default
let api_version = channel_host::workspace_read("channels/whatsapp/api_version")
.filter(|s| !s.is_empty())
.unwrap_or_else(|| "v18.0".to_string());
// Build WhatsApp API URL with token placeholder
// Host will replace {WHATSAPP_ACCESS_TOKEN} with actual token in Authorization header
let api_url = format!(
"https://graph.facebook.com/{}/{}/messages",
api_version, metadata.phone_number_id
"https://graph.facebook.com/v18.0/{}/messages",
metadata.phone_number_id
);
// Build sendMessage payload
@@ -378,7 +361,6 @@ impl Guest for WhatsAppChannel {
&api_url,
&headers.to_string(),
Some(&payload_bytes),
None,
);
match result {
@@ -435,8 +417,6 @@ impl Guest for WhatsAppChannel {
}
}
fn on_status(_update: StatusUpdate) {}
fn on_shutdown() {
channel_host::log(
channel_host::LogLevel::Info,
-13
View File
@@ -1,13 +0,0 @@
[Unit]
Description=Cloud SQL Auth Proxy
After=network.target
[Service]
Type=simple
DynamicUser=yes
ExecStart=/usr/local/bin/cloud-sql-proxy ironclaw-prod:us-central1:ironclaw-db --port=5432
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
-27
View File
@@ -1,27 +0,0 @@
# WARNING: Replace all CHANGE_ME values before deploying.
# Do not use placeholder passwords in production.
DATABASE_URL=postgres://ironclaw:CHANGE_ME@localhost:5432/ironclaw
# NEAR AI
NEARAI_SESSION_TOKEN=CHANGE_ME
NEARAI_MODEL=claude-3-5-sonnet-20241022
NEARAI_BASE_URL=https://cloud-api.near.ai
NEARAI_AUTH_URL=https://private.near.ai
NEARAI_API_MODE=chat_completions
# Agent
AGENT_NAME=ironclaw
CLI_ENABLED=false
# Web Gateway
GATEWAY_ENABLED=true
# 0.0.0.0 binds to all interfaces (required for Docker --network=host).
# Use 127.0.0.1 if running outside Docker or for local-only access.
GATEWAY_HOST=0.0.0.0
GATEWAY_PORT=3000
GATEWAY_AUTH_TOKEN=CHANGE_ME
# Disabled for initial deploy
SANDBOX_ENABLED=false
HEARTBEAT_ENABLED=false
EMBEDDING_ENABLED=false
-20
View File
@@ -1,20 +0,0 @@
[Unit]
Description=IronClaw AI Assistant
After=cloud-sql-proxy.service docker.service
Requires=cloud-sql-proxy.service
[Service]
Type=simple
ExecStartPre=/usr/bin/docker pull us-central1-docker.pkg.dev/ironclaw-prod/ironclaw/agent:latest
ExecStart=/usr/bin/docker run --rm \
--name ironclaw \
--env-file /opt/ironclaw/.env \
--network=host \
us-central1-docker.pkg.dev/ironclaw-prod/ironclaw/agent:latest \
--no-onboard
ExecStop=/usr/bin/docker stop ironclaw
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
-68
View File
@@ -1,68 +0,0 @@
#!/usr/bin/env bash
# VM bootstrap script for IronClaw on GCP Compute Engine.
#
# Run on a fresh Debian 12 VM after SSH:
# sudo bash setup.sh
#
# Prerequisites:
# - VM has the ironclaw-vm service account attached
# - Cloud SQL Auth Proxy accessible via IAM
# - Artifact Registry image pushed
set -euo pipefail
# Must run as root
if [ "$(id -u)" -ne 0 ]; then
echo "ERROR: This script must be run as root (sudo bash setup.sh)"
exit 1
fi
echo "==> Installing Docker"
apt-get update
apt-get install -y docker.io
systemctl enable docker
systemctl start docker
echo "==> Installing Cloud SQL Auth Proxy"
curl -fsSL -o /usr/local/bin/cloud-sql-proxy \
https://storage.googleapis.com/cloud-sql-connectors/cloud-sql-proxy/v2.14.3/cloud-sql-proxy.linux.amd64
chmod +x /usr/local/bin/cloud-sql-proxy
echo "==> Installing systemd services"
cp /tmp/deploy/cloud-sql-proxy.service /etc/systemd/system/
cp /tmp/deploy/ironclaw.service /etc/systemd/system/
systemctl daemon-reload
echo "==> Starting Cloud SQL Auth Proxy"
systemctl enable cloud-sql-proxy
systemctl start cloud-sql-proxy
echo "==> Configuring Docker registry auth"
# The VM service account provides Artifact Registry access
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
echo "==> Creating config directory"
# Owned by root, readable only by root. Docker reads --env-file as root
# before dropping to uid 1000 (ironclaw) inside the container.
mkdir -p /opt/ironclaw
chmod 700 /opt/ironclaw
if [ ! -f /opt/ironclaw/.env ]; then
echo "WARNING: /opt/ironclaw/.env does not exist."
echo "Create it with your configuration before starting IronClaw."
echo "See deploy/env.example for the required variables."
echo ""
echo "Then run: systemctl enable ironclaw && systemctl start ironclaw"
else
chmod 600 /opt/ironclaw/.env
echo "==> Starting IronClaw"
systemctl enable ironclaw
systemctl start ironclaw
fi
echo "==> Setup complete"
echo ""
echo "Verify with:"
echo " systemctl status cloud-sql-proxy"
echo " systemctl status ironclaw"
echo " docker logs ironclaw"
-20
View File
@@ -1,20 +0,0 @@
# Local development only — do NOT use these credentials in production.
services:
postgres:
image: pgvector/pgvector:pg16
ports:
- "5432:5432"
environment:
POSTGRES_DB: ironclaw
POSTGRES_USER: ironclaw
POSTGRES_PASSWORD: ironclaw # dev-only, change for any non-local deployment
volumes:
- pgdata:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ironclaw"]
interval: 5s
timeout: 3s
retries: 5
volumes:
pgdata:
+3 -36
View File
@@ -246,46 +246,13 @@ Create `my-channel.capabilities.json`:
## Building and Deploying
### Supply Chain Security: No Committed Binaries
**Do not commit compiled WASM binaries.** They are a supply chain risk — the binary in a PR may not match the source. IronClaw builds channels from source:
- `cargo build` automatically builds `telegram.wasm` via `build.rs`
- The built binary is in `.gitignore` and is not committed
- CI should run `cargo build` (or `./scripts/build-all.sh`) to produce releases
**Reproducible build:**
```bash
cargo build --release
```
Prerequisites: `rustup target add wasm32-wasip2`, `cargo install wasm-tools` (optional; fallback copies raw WASM if unavailable).
### Telegram Channel (Manual Build)
```bash
# Add WASM target if needed
rustup target add wasm32-wasip2
# Build Telegram channel
./channels-src/telegram/build.sh
# Install (or use ironclaw onboard to install bundled channel)
mkdir -p ~/.ironclaw/channels
cp channels-src/telegram/telegram.wasm channels-src/telegram/telegram.capabilities.json ~/.ironclaw/channels/
```
**Note**: The main IronClaw binary bundles `telegram.wasm` via `include_bytes!`. When modifying the Telegram channel source, run `./channels-src/telegram/build.sh` **before** building the main crate, so the updated WASM is included.
### Other Channels
```bash
# Build the WASM component
cd channels-src/my-channel
cargo build --release --target wasm32-wasip2
cd channels/my-channel
cargo component build --release
# Deploy to ~/.ironclaw/channels/
cp target/wasm32-wasip2/release/my_channel.wasm ~/.ironclaw/channels/my-channel.wasm
cp target/wasm32-wasip1/release/my_channel.wasm ~/.ironclaw/channels/my-channel.wasm
cp my-channel.capabilities.json ~/.ironclaw/channels/
```
-135
View File
@@ -1,135 +0,0 @@
# Telegram Channel Setup
This guide covers configuring the Telegram channel for IronClaw, including DM pairing for access control.
## Overview
The Telegram channel lets you interact with IronClaw via Telegram DMs and groups. It supports:
- **Webhook mode** (recommended): Instant delivery via tunnel
- **Polling mode**: No tunnel required; ~30s delay
- **DM pairing**: Approve unknown users before they can message the agent
- **Group mentions**: `@YourBot` or `/command` to trigger in groups
## Prerequisites
- IronClaw installed and configured (`ironclaw onboard`)
- A Telegram bot token from [@BotFather](https://t.me/BotFather)
## Quick Start
### 1. Create a Bot
1. Message [@BotFather](https://t.me/BotFather) on Telegram
2. Send `/newbot` and follow the prompts
3. Copy the bot token (e.g., `123456789:ABCdefGHIjklMNOpqrsTUVwxyz`)
### 2. Configure via Setup Wizard
```bash
ironclaw onboard
```
When prompted, enable the Telegram channel and paste your bot token. The wizard will:
- Validate the token
- Optionally configure a webhook secret
- Set up tunnel (if you want webhook mode)
### 3. (Optional) Configure Tunnel for Webhooks
For instant message delivery, expose your agent via a tunnel:
```bash
# ngrok
ngrok http 8080
# Cloudflare
cloudflared tunnel --url http://localhost:8080
```
Set the tunnel URL in settings or via `TUNNEL_URL` env var. Without a tunnel, the channel uses polling (~30s delay).
## DM Pairing
When an unknown user DMs your bot, they receive a pairing code. You must approve them before they can message the agent.
### Flow
1. Unknown user sends a message to your bot
2. Bot replies: `To pair with this bot, run: ironclaw pairing approve telegram ABC12345`
3. You run: `ironclaw pairing approve telegram ABC12345`
4. User is added to the allow list; future messages are delivered
### Commands
```bash
# List pending pairing requests
ironclaw pairing list telegram
# List as JSON
ironclaw pairing list telegram --json
# Approve a user by code
ironclaw pairing approve telegram ABC12345
```
### Configuration
Edit `~/.ironclaw/channels/telegram.capabilities.json` (or the config injected by the host):
| Option | Values | Default | Description |
|--------|--------|---------|-------------|
| `dm_policy` | `open`, `allowlist`, `pairing` | `pairing` | `open` = allow all; `allowlist` = config + approved only; `pairing` = allowlist + send pairing reply to unknown |
| `allow_from` | `["user_id", "username", "*"]` | `[]` | Pre-approved IDs/usernames. `*` allows everyone. |
| `owner_id` | Telegram user ID | `null` | When set, only this user can message (overrides dm_policy) |
| `bot_username` | Bot username (no @) | `null` | Used for mention detection in groups; when set, only strips this mention from messages |
| `respond_to_all_group_messages` | `true`/`false` | `false` | When true, respond to all group messages; when false, only @mentions and /commands |
## Manual Installation
If the channel isn't installed via the wizard:
```bash
# Build the Telegram channel (requires wasm32-wasip2 target)
rustup target add wasm32-wasip2
./channels-src/telegram/build.sh
# Install
mkdir -p ~/.ironclaw/channels
cp channels-src/telegram/telegram.wasm channels-src/telegram/telegram.capabilities.json ~/.ironclaw/channels/
```
## Secrets
The channel expects a secret named `telegram_bot_token`. Configure via:
- **Setup wizard**: Saves to encrypted secrets store
- **Environment**: `TELEGRAM_BOT_TOKEN=your_token`
- **Secrets store**: `ironclaw` CLI (if available)
## Webhook Secret (Optional)
For webhook validation, set `telegram_webhook_secret` in secrets. Telegram will send `X-Telegram-Bot-Api-Secret-Token` with each request; the host validates it before forwarding.
## Troubleshooting
### Messages not delivered
- **Polling mode**: Check logs for `getUpdates` errors. Ensure the bot token is valid.
- **Webhook mode**: Verify tunnel is running and `TUNNEL_URL` is correct. Telegram requires HTTPS.
### Pairing code not received
- Verify the channel can send messages (HTTP allowlist includes `api.telegram.org`)
- Check `dm_policy` is `pairing` (not `allowlist` which blocks without reply)
### Group mentions not working
- Set `bot_username` in config to your bot's username (e.g., `MyIronClawBot`)
- Ensure the message contains `@YourBot` or starts with `/`
### "Connection refused" when starting
- For webhook mode: Start your tunnel before `ironclaw run`
- For polling only: No tunnel needed; ignore tunnel-related warnings
-121
View File
@@ -1,121 +0,0 @@
//! Standalone heartbeat test.
//!
//! Exercises the heartbeat system in isolation: connects to the real
//! database, reads the real HEARTBEAT.md, calls the real LLM, and prints
//! every step so you can see exactly where it breaks.
//!
//! Usage:
//! cargo run --example test_heartbeat
use std::sync::Arc;
use ironclaw::{
agent::HeartbeatRunner,
config::Config,
history::Store,
llm::{SessionConfig, create_llm_provider, create_session_manager},
workspace::Workspace,
};
#[tokio::main]
async fn main() -> anyhow::Result<()> {
// Load .env and set up logging
let _ = dotenvy::dotenv();
tracing_subscriber::fmt()
.with_env_filter("ironclaw=debug")
.init();
println!("=== Heartbeat Integration Test ===\n");
// 1. Load config
let config = Config::from_env()
.await
.map_err(|e| anyhow::anyhow!("Config: {}", e))?;
println!("[1/6] Config loaded");
println!(" heartbeat.enabled = {}", config.heartbeat.enabled);
println!(
" heartbeat.interval_secs = {}",
config.heartbeat.interval_secs
);
println!(
" heartbeat.notify_channel = {:?}",
config.heartbeat.notify_channel
);
println!(
" heartbeat.notify_user = {:?}",
config.heartbeat.notify_user
);
// 2. Connect to database
let store = Store::new(&config.database).await?;
store.run_migrations().await?;
println!("[2/6] Database connected");
// 3. Create workspace
let workspace = Arc::new(Workspace::new("default", store.pool()));
println!("[3/6] Workspace created");
// 4. Read HEARTBEAT.md
let checklist = workspace.heartbeat_checklist().await;
match &checklist {
Ok(Some(content)) => {
let preview: String = content.chars().take(200).collect();
println!("[4/6] HEARTBEAT.md found ({} chars)", content.len());
println!(" Preview: {}...", preview);
}
Ok(None) => {
println!("[4/6] HEARTBEAT.md is None (no file, no seed fallback)");
println!(" Heartbeat will return Skipped.");
}
Err(e) => {
println!("[4/6] HEARTBEAT.md read error: {}", e);
}
}
// Check if the checklist would be considered "effectively empty"
if let Ok(Some(_)) = checklist {
println!(" (Will verify via runner below)");
}
// 5. Create LLM provider
let session = create_session_manager(SessionConfig {
auth_base_url: config.llm.nearai.auth_base_url.clone(),
session_path: config.llm.nearai.session_path.clone(),
})
.await;
let llm = create_llm_provider(&config.llm, session)?;
println!("[5/6] LLM provider created (model: {})", llm.model_name());
// 6. Run heartbeat check
println!("[6/6] Running check_heartbeat()...\n");
let hb_config = ironclaw::agent::HeartbeatConfig::default();
let runner = HeartbeatRunner::new(hb_config, workspace, llm);
let result = runner.check_heartbeat().await;
println!("=== Result ===\n");
match &result {
ironclaw::agent::HeartbeatResult::Ok => {
println!("HeartbeatResult::Ok");
println!(" LLM responded HEARTBEAT_OK, nothing needs attention.");
}
ironclaw::agent::HeartbeatResult::NeedsAttention(msg) => {
println!("HeartbeatResult::NeedsAttention");
println!(" Message:\n{}", msg);
}
ironclaw::agent::HeartbeatResult::Skipped => {
println!("HeartbeatResult::Skipped");
println!(" No checklist found, or checklist was effectively empty.");
println!(" This means the HEARTBEAT.md either:");
println!(" - Does not exist in the workspace database");
println!(" - Contains only headers, comments, and empty checkboxes");
}
ironclaw::agent::HeartbeatResult::Failed(err) => {
println!("HeartbeatResult::Failed");
println!(" Error: {}", err);
}
}
Ok(())
}
@@ -10,7 +10,7 @@ publish = false
crate-type = ["cdylib"]
[dependencies]
wit-bindgen = "=0.36"
wit-bindgen = "0.36"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
@@ -34,7 +34,7 @@ A standalone WASM component that provides Slack integration for IronClaw. This s
## Building
```bash
cd tools-src/slack
cd examples/wasm-tools/slack
cargo component build --release
```
@@ -0,0 +1,26 @@
{
"http": {
"allowlist": [
{
"host": "slack.com",
"path_prefix": "/api/",
"methods": ["GET", "POST"]
}
],
"credentials": {
"slack_bot_token": {
"secret_name": "slack_bot_token",
"location": { "type": "bearer" },
"host_patterns": ["slack.com"]
}
},
"rate_limit": {
"requests_per_minute": 50,
"requests_per_hour": 1000
},
"timeout_secs": 30
},
"secrets": {
"allowed_names": ["slack_bot_token"]
}
}
@@ -9,24 +9,6 @@ use crate::types::*;
const SLACK_API_BASE: &str = "https://slack.com/api";
/// Percent-encode a string for use as a URL query parameter value.
fn url_encode(s: &str) -> String {
let mut out = String::with_capacity(s.len());
for b in s.bytes() {
match b {
b'A'..=b'Z' | b'a'..=b'z' | b'0'..=b'9' | b'-' | b'_' | b'.' | b'~' => {
out.push(b as char);
}
_ => {
out.push('%');
out.push(char::from(b"0123456789ABCDEF"[(b >> 4) as usize]));
out.push(char::from(b"0123456789ABCDEF"[(b & 0xf) as usize]));
}
}
}
out
}
/// Make a Slack API call.
fn slack_api_call(method: &str, endpoint: &str, body: Option<&str>) -> Result<String, String> {
let url = format!("{}/{}", SLACK_API_BASE, endpoint);
@@ -40,12 +22,9 @@ fn slack_api_call(method: &str, endpoint: &str, body: Option<&str>) -> Result<St
let body_bytes = body.map(|b| b.as_bytes().to_vec());
host::log(
host::LogLevel::Debug,
&format!("Slack API: {} {}", method, endpoint),
);
host::log(host::LogLevel::Debug, &format!("Slack API: {} {}", method, endpoint));
let response = host::http_request(method, &url, headers, body_bytes.as_deref(), None)?;
let response = host::http_request(method, &url, headers, body_bytes.as_deref())?;
if response.status < 200 || response.status >= 300 {
return Err(format!(
@@ -134,11 +113,7 @@ pub fn list_channels(limit: u32) -> Result<ListChannelsResult, String> {
/// Get message history from a channel.
pub fn get_channel_history(channel: &str, limit: u32) -> Result<ChannelHistoryResult, String> {
let url = format!(
"conversations.history?channel={}&limit={}",
url_encode(channel),
limit
);
let url = format!("conversations.history?channel={}&limit={}", channel, limit);
let response = slack_api_call("GET", &url, None)?;
@@ -168,11 +143,7 @@ pub fn get_channel_history(channel: &str, limit: u32) -> Result<ChannelHistoryRe
}
/// Add a reaction to a message.
pub fn post_reaction(
channel: &str,
timestamp: &str,
emoji: &str,
) -> Result<PostReactionResult, String> {
pub fn post_reaction(channel: &str, timestamp: &str, emoji: &str) -> Result<PostReactionResult, String> {
let payload = serde_json::json!({
"channel": channel,
"timestamp": timestamp,
@@ -198,7 +169,7 @@ pub fn post_reaction(
/// Get information about a user.
pub fn get_user_info(user_id: &str) -> Result<GetUserInfoResult, String> {
let url = format!("users.info?user={}", url_encode(user_id));
let url = format!("users.info?user={}", user_id);
let response = slack_api_call("GET", &url, None)?;
@@ -32,7 +32,7 @@ use types::SlackAction;
// This creates the `bindings` module with types and traits.
wit_bindgen::generate!({
world: "sandboxed-tool",
path: "../../wit/tool.wit",
path: "../../../wit/tool.wit",
});
/// Implementation of the tool interface.
@@ -53,44 +53,84 @@ impl exports::near::agent::tool::Guest for SlackTool {
}
fn schema() -> String {
// JSON Schema for the tool's parameters
r#"{
"type": "object",
"required": ["action"],
"properties": {
"action": {
"type": "string",
"enum": ["send_message", "list_channels", "get_channel_history", "post_reaction", "get_user_info"],
"description": "The Slack operation to perform"
"oneOf": [
{
"properties": {
"action": { "const": "send_message" },
"channel": {
"type": "string",
"description": "Channel ID or name (e.g., '#general' or 'C1234567890')"
},
"text": {
"type": "string",
"description": "Message text (supports Slack mrkdwn formatting)"
},
"thread_ts": {
"type": "string",
"description": "Optional thread timestamp to reply in a thread"
}
},
"required": ["action", "channel", "text"]
},
"channel": {
"type": "string",
"description": "Channel ID or name (e.g., '#general' or 'C1234567890'). Required for: send_message, get_channel_history, post_reaction"
{
"properties": {
"action": { "const": "list_channels" },
"limit": {
"type": "integer",
"description": "Maximum number of channels to return (default: 100)",
"default": 100
}
},
"required": ["action"]
},
"text": {
"type": "string",
"description": "Message text (supports Slack mrkdwn formatting). Required for: send_message"
{
"properties": {
"action": { "const": "get_channel_history" },
"channel": {
"type": "string",
"description": "Channel ID (e.g., 'C1234567890')"
},
"limit": {
"type": "integer",
"description": "Maximum number of messages to return (default: 20)",
"default": 20
}
},
"required": ["action", "channel"]
},
"thread_ts": {
"type": "string",
"description": "Thread timestamp to reply in a thread. Used by: send_message"
{
"properties": {
"action": { "const": "post_reaction" },
"channel": {
"type": "string",
"description": "Channel ID containing the message"
},
"timestamp": {
"type": "string",
"description": "Timestamp of the message to react to"
},
"emoji": {
"type": "string",
"description": "Emoji name without colons (e.g., 'thumbsup')"
}
},
"required": ["action", "channel", "timestamp", "emoji"]
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return. Used by: list_channels, get_channel_history"
},
"timestamp": {
"type": "string",
"description": "Timestamp of the message to react to. Required for: post_reaction"
},
"emoji": {
"type": "string",
"description": "Emoji name without colons (e.g., 'thumbsup'). Required for: post_reaction"
},
"user_id": {
"type": "string",
"description": "User ID (e.g., 'U1234567890'). Required for: get_user_info"
{
"properties": {
"action": { "const": "get_user_info" },
"user_id": {
"type": "string",
"description": "User ID (e.g., 'U1234567890')"
}
},
"required": ["action", "user_id"]
}
}
]
}"#
.to_string()
}
@@ -138,3 +138,10 @@ pub struct GetUserInfoResult {
pub ok: bool,
pub user: UserInfo,
}
/// Generic Slack API error response.
#[derive(Debug, Deserialize)]
pub struct SlackApiError {
pub ok: bool,
pub error: String,
}
-10
View File
@@ -1,10 +0,0 @@
-- Add project_dir and user_id columns for sandbox job tracking.
-- user_id was previously hardcoded to "default" in the Rust layer;
-- now it's persisted so we can filter per-user.
ALTER TABLE agent_jobs ADD COLUMN IF NOT EXISTS project_dir TEXT;
ALTER TABLE agent_jobs ADD COLUMN IF NOT EXISTS user_id TEXT NOT NULL DEFAULT 'default';
CREATE INDEX IF NOT EXISTS idx_agent_jobs_source ON agent_jobs(source);
CREATE INDEX IF NOT EXISTS idx_agent_jobs_user ON agent_jobs(user_id);
CREATE INDEX IF NOT EXISTS idx_agent_jobs_created ON agent_jobs(created_at DESC);
-14
View File
@@ -1,14 +0,0 @@
-- Track which mode a sandbox job uses (worker vs claude_code).
ALTER TABLE agent_jobs ADD COLUMN IF NOT EXISTS job_mode TEXT NOT NULL DEFAULT 'worker';
-- Persist Claude Code streaming events so they survive restarts and can be
-- loaded when the frontend opens a job detail view after the fact.
CREATE TABLE IF NOT EXISTS claude_code_events (
id BIGSERIAL PRIMARY KEY,
job_id UUID NOT NULL REFERENCES agent_jobs(id),
event_type TEXT NOT NULL,
data JSONB NOT NULL,
created_at TIMESTAMPTZ NOT NULL DEFAULT now()
);
CREATE INDEX IF NOT EXISTS idx_cc_events_job ON claude_code_events(job_id, id);
-73
View File
@@ -1,73 +0,0 @@
-- Routines: scheduled and reactive job system.
--
-- A routine is a named, persistent, user-owned task with a trigger and an action.
-- Triggers fire independently (cron, event, webhook, manual) so only the
-- relevant routine's prompt hits the LLM, not the whole checklist.
CREATE TABLE routines (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
name TEXT NOT NULL,
description TEXT NOT NULL DEFAULT '',
user_id TEXT NOT NULL,
enabled BOOLEAN NOT NULL DEFAULT true,
-- Trigger definition
trigger_type TEXT NOT NULL, -- 'cron', 'event', 'webhook', 'manual'
trigger_config JSONB NOT NULL, -- type-specific config (schedule, pattern, etc.)
-- Action definition
action_type TEXT NOT NULL, -- 'lightweight', 'full_job'
action_config JSONB NOT NULL, -- prompt, context_paths, max_tokens / title, max_iterations
-- Guardrails
cooldown_secs INTEGER NOT NULL DEFAULT 300,
max_concurrent INTEGER NOT NULL DEFAULT 1,
dedup_window_secs INTEGER, -- NULL = no dedup
-- Notification preferences
notify_channel TEXT, -- NULL = use default
notify_user TEXT NOT NULL DEFAULT 'default',
notify_on_success BOOLEAN NOT NULL DEFAULT false,
notify_on_failure BOOLEAN NOT NULL DEFAULT true,
notify_on_attention BOOLEAN NOT NULL DEFAULT true,
-- Runtime state (updated by engine)
state JSONB NOT NULL DEFAULT '{}',
last_run_at TIMESTAMPTZ,
next_fire_at TIMESTAMPTZ, -- pre-computed for cron triggers
run_count BIGINT NOT NULL DEFAULT 0,
consecutive_failures INTEGER NOT NULL DEFAULT 0,
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
updated_at TIMESTAMPTZ NOT NULL DEFAULT now(),
UNIQUE (user_id, name)
);
-- Fast lookup: "which cron routines need to fire right now?"
CREATE INDEX idx_routines_next_fire
ON routines (next_fire_at)
WHERE enabled AND next_fire_at IS NOT NULL;
-- Fast lookup: event triggers for a user
CREATE INDEX idx_routines_event_triggers
ON routines (user_id)
WHERE enabled AND trigger_type = 'event';
-- Audit log of individual routine executions.
CREATE TABLE routine_runs (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
routine_id UUID NOT NULL REFERENCES routines(id) ON DELETE CASCADE,
trigger_type TEXT NOT NULL,
trigger_detail TEXT, -- e.g. matched message preview, cron expression
started_at TIMESTAMPTZ NOT NULL DEFAULT now(),
completed_at TIMESTAMPTZ,
status TEXT NOT NULL DEFAULT 'running', -- running, ok, attention, failed
result_summary TEXT,
tokens_used INTEGER,
job_id UUID REFERENCES agent_jobs(id), -- non-NULL for full_job runs
created_at TIMESTAMPTZ NOT NULL DEFAULT now()
);
CREATE INDEX idx_routine_runs_routine ON routine_runs (routine_id);
CREATE INDEX idx_routine_runs_status ON routine_runs (status) WHERE status = 'running';
-3
View File
@@ -1,3 +0,0 @@
-- Rename claude_code_events to job_events (generic for all sandbox job types).
ALTER TABLE claude_code_events RENAME TO job_events;
ALTER INDEX idx_cc_events_job RENAME TO idx_job_events_job;
-16
View File
@@ -1,16 +0,0 @@
-- Settings table: key-value store for all user configuration.
--
-- Replaces ~/.ironclaw/settings.json, session.json, and mcp-servers.json.
-- Keys use dotted paths matching the existing Settings.get()/set() convention
-- (e.g., "agent.name", "sandbox.enabled", "mcp_servers").
-- One row per setting so individual values can be updated atomically.
CREATE TABLE IF NOT EXISTS settings (
user_id TEXT NOT NULL,
key TEXT NOT NULL,
value JSONB NOT NULL,
updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
PRIMARY KEY (user_id, key)
);
CREATE INDEX IF NOT EXISTS idx_settings_user ON settings (user_id);
-2
View File
@@ -1,2 +0,0 @@
[workspace]
git_release_enable = false
-21
View File
@@ -1,21 +0,0 @@
#!/usr/bin/env bash
# Build IronClaw and all bundled channels.
#
# Run this before release or when channel sources have changed.
# The main binary bundles telegram.wasm via include_bytes!; it must exist.
set -euo pipefail
cd "$(dirname "$0")/.."
echo "Building bundled channels..."
if [ -d "channels-src/telegram" ]; then
./channels-src/telegram/build.sh
fi
echo ""
echo "Building IronClaw..."
cargo build --release
echo ""
echo "Done. Binary: target/release/ironclaw"
+700 -1335
View File
File diff suppressed because it is too large Load Diff
+4 -177
View File
@@ -29,7 +29,7 @@ use std::time::Duration;
use tokio::sync::mpsc;
use crate::channels::OutgoingResponse;
use crate::llm::{ChatMessage, CompletionRequest, FinishReason, LlmProvider};
use crate::llm::{ChatMessage, CompletionRequest, LlmProvider};
use crate::workspace::Workspace;
/// Configuration for the heartbeat runner.
@@ -178,7 +178,7 @@ impl HeartbeatRunner {
pub async fn check_heartbeat(&self) -> HeartbeatResult {
// Get the heartbeat checklist
let checklist = match self.workspace.heartbeat_checklist().await {
Ok(Some(content)) if !is_effectively_empty(&content) => content,
Ok(Some(content)) if !content.trim().is_empty() => content,
Ok(_) => return HeartbeatResult::Skipped,
Err(e) => return HeartbeatResult::Failed(format!("Failed to read checklist: {}", e)),
};
@@ -217,26 +217,9 @@ impl HeartbeatRunner {
]
};
// Use the model's context_length to set max_tokens. The API returns
// the total context window; we cap output at half of that (the rest is
// the prompt) with a floor of 4096.
let max_tokens = match self.llm.model_metadata().await {
Ok(meta) => {
let from_api = meta.context_length.map(|ctx| ctx / 2).unwrap_or(4096);
from_api.max(4096)
}
Err(e) => {
tracing::warn!(
"Could not fetch model metadata, using default max_tokens: {}",
e
);
4096
}
};
let request = CompletionRequest::new(messages)
.with_max_tokens(max_tokens)
.with_temperature(0.3);
.with_max_tokens(1024)
.with_temperature(0.3); // Lower temperature for more focused responses
let response = match self.llm.complete(request).await {
Ok(r) => r,
@@ -245,20 +228,6 @@ impl HeartbeatRunner {
let content = response.content.trim();
// Guard against empty content. Reasoning models (e.g. GLM-4.7) may
// burn all output tokens on chain-of-thought and return content: null.
if content.is_empty() {
return if response.finish_reason == FinishReason::Length {
HeartbeatResult::Failed(
"LLM response was truncated (finish_reason=length) with no content. \
The model may have exhausted its token budget on reasoning."
.to_string(),
)
} else {
HeartbeatResult::Failed("LLM returned empty content.".to_string())
};
}
// Check if nothing needs attention
if content == "HEARTBEAT_OK" || content.contains("HEARTBEAT_OK") {
return HeartbeatResult::Ok;
@@ -288,45 +257,6 @@ impl HeartbeatRunner {
}
}
/// Check if heartbeat content is effectively empty.
///
/// Returns true if the content contains only:
/// - Whitespace
/// - Markdown headers (lines starting with #)
/// - HTML comments (`<!-- ... -->`)
/// - Empty list items (`- [ ]`, `- [x]`, `-`, `*`)
///
/// This skips the LLM call when the user hasn't added real tasks yet,
/// saving API costs.
fn is_effectively_empty(content: &str) -> bool {
let without_comments = strip_html_comments(content);
without_comments.lines().all(|line| {
let trimmed = line.trim();
trimmed.is_empty()
|| trimmed.starts_with('#')
|| trimmed == "- [ ]"
|| trimmed == "- [x]"
|| trimmed == "-"
|| trimmed == "*"
})
}
/// Remove HTML comments from content.
fn strip_html_comments(content: &str) -> String {
let mut result = String::with_capacity(content.len());
let mut rest = content;
while let Some(start) = rest.find("<!--") {
result.push_str(&rest[..start]);
match rest[start..].find("-->") {
Some(end) => rest = &rest[start + end + 3..],
None => return result, // unclosed comment, treat rest as comment
}
}
result.push_str(rest);
result
}
/// Spawn the heartbeat runner as a background task.
///
/// Returns a handle that can be used to stop the runner.
@@ -371,107 +301,4 @@ mod tests {
let disabled = HeartbeatConfig::default().disabled();
assert!(!disabled.enabled);
}
// ==================== strip_html_comments ====================
#[test]
fn test_strip_html_comments_no_comments() {
assert_eq!(strip_html_comments("hello world"), "hello world");
}
#[test]
fn test_strip_html_comments_single() {
assert_eq!(
strip_html_comments("before<!-- gone -->after"),
"beforeafter"
);
}
#[test]
fn test_strip_html_comments_multiple() {
let input = "a<!-- 1 -->b<!-- 2 -->c";
assert_eq!(strip_html_comments(input), "abc");
}
#[test]
fn test_strip_html_comments_multiline() {
let input = "# Title\n<!-- multi\nline\ncomment -->\nreal content";
assert_eq!(strip_html_comments(input), "# Title\n\nreal content");
}
#[test]
fn test_strip_html_comments_unclosed() {
let input = "before<!-- never closed";
assert_eq!(strip_html_comments(input), "before");
}
// ==================== is_effectively_empty ====================
#[test]
fn test_effectively_empty_empty_string() {
assert!(is_effectively_empty(""));
}
#[test]
fn test_effectively_empty_whitespace() {
assert!(is_effectively_empty(" \n\n \n "));
}
#[test]
fn test_effectively_empty_headers_only() {
assert!(is_effectively_empty("# Title\n## Subtitle\n### Section"));
}
#[test]
fn test_effectively_empty_html_comments_only() {
assert!(is_effectively_empty("<!-- this is a comment -->"));
}
#[test]
fn test_effectively_empty_empty_checkboxes() {
assert!(is_effectively_empty("# Checklist\n- [ ]\n- [x]"));
}
#[test]
fn test_effectively_empty_bare_list_markers() {
assert!(is_effectively_empty("-\n*\n-"));
}
#[test]
fn test_effectively_empty_seeded_template() {
let template = "\
# Heartbeat Checklist
<!-- Keep this file empty to skip heartbeat API calls.
Add tasks below when you want the agent to check something periodically.
Example:
- [ ] Check for unread emails needing a reply
- [ ] Review today's calendar for upcoming meetings
- [ ] Check CI build status for main branch
-->";
assert!(is_effectively_empty(template));
}
#[test]
fn test_effectively_empty_real_checklist() {
let content = "\
# Heartbeat Checklist
- [ ] Check for unread emails needing a reply
- [ ] Review today's calendar for upcoming meetings";
assert!(!is_effectively_empty(content));
}
#[test]
fn test_effectively_empty_mixed_real_and_headers() {
let content = "# Title\n\nDo something important";
assert!(!is_effectively_empty(content));
}
#[test]
fn test_effectively_empty_comment_plus_real_content() {
let content = "<!-- comment -->\nActual task here";
assert!(!is_effectively_empty(content));
}
}
+1 -7
View File
@@ -6,7 +6,6 @@
//! - Tool invocation with safety
//! - Self-repair for stuck jobs
//! - Proactive heartbeat execution
//! - Routine-based scheduled and reactive jobs
//! - Turn-based session management with undo
//! - Context compaction for long conversations
@@ -15,8 +14,6 @@ pub mod compaction;
pub mod context_monitor;
mod heartbeat;
mod router;
pub mod routine;
pub mod routine_engine;
mod scheduler;
mod self_repair;
pub mod session;
@@ -26,17 +23,14 @@ pub mod task;
pub mod undo;
pub mod worker;
pub(crate) use agent_loop::truncate_for_preview;
pub use agent_loop::{Agent, AgentDeps};
pub use compaction::{CompactionResult, ContextCompactor};
pub use context_monitor::{CompactionStrategy, ContextBreakdown, ContextMonitor};
pub use heartbeat::{HeartbeatConfig, HeartbeatResult, HeartbeatRunner, spawn_heartbeat};
pub use router::{MessageIntent, Router};
pub use routine::{Routine, RoutineAction, RoutineRun, Trigger};
pub use routine_engine::RoutineEngine;
pub use scheduler::Scheduler;
pub use self_repair::{BrokenTool, RepairResult, RepairTask, SelfRepair, StuckJob};
pub use session::{PendingApproval, PendingAuth, Session, Thread, ThreadState, Turn, TurnState};
pub use session::{PendingApproval, Session, Thread, ThreadState, Turn, TurnState};
pub use session_manager::SessionManager;
pub use submission::{Submission, SubmissionParser, SubmissionResult};
pub use task::{Task, TaskContext, TaskHandler, TaskOutput, TaskStatus};
-509
View File
@@ -1,509 +0,0 @@
//! Core types for the routines system.
//!
//! A routine is a named, persistent, user-owned task with a trigger and an action.
//! Each routine fires independently when its trigger condition is met, with only
//! that routine's prompt and context sent to the LLM.
//!
//! ```text
//! ┌──────────┐ ┌─────────┐ ┌──────────────────┐
//! │ Trigger │────▶│ Engine │────▶│ Execution Mode │
//! │ cron/event│ │guardrail│ │lightweight│full_job│
//! │ webhook │ │ check │ └──────────────────┘
//! │ manual │ └─────────┘ │
//! └──────────┘ ▼
//! ┌──────────────┐
//! │ Notify user │
//! │ if needed │
//! └──────────────┘
//! ```
use std::collections::hash_map::DefaultHasher;
use std::hash::{Hash, Hasher};
use std::str::FromStr;
use std::time::Duration;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use uuid::Uuid;
/// A routine is a named, persistent, user-owned task with a trigger and an action.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Routine {
pub id: Uuid,
pub name: String,
pub description: String,
pub user_id: String,
pub enabled: bool,
pub trigger: Trigger,
pub action: RoutineAction,
pub guardrails: RoutineGuardrails,
pub notify: NotifyConfig,
// Runtime state (DB-managed)
pub last_run_at: Option<DateTime<Utc>>,
pub next_fire_at: Option<DateTime<Utc>>,
pub run_count: u64,
pub consecutive_failures: u32,
pub state: serde_json::Value,
pub created_at: DateTime<Utc>,
pub updated_at: DateTime<Utc>,
}
/// When a routine should fire.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(tag = "type", rename_all = "snake_case")]
pub enum Trigger {
/// Fire on a cron schedule (e.g. "0 9 * * MON-FRI" or "every 2h").
Cron { schedule: String },
/// Fire when a channel message matches a pattern.
Event {
/// Optional channel filter (e.g. "telegram", "slack").
channel: Option<String>,
/// Regex pattern to match against message content.
pattern: String,
},
/// Fire on incoming webhook POST to /hooks/routine/{id}.
Webhook {
/// Optional webhook path suffix (defaults to routine id).
path: Option<String>,
/// Optional shared secret for HMAC validation.
secret: Option<String>,
},
/// Only fires via tool call or CLI.
Manual,
}
impl Trigger {
/// The string tag stored in the DB trigger_type column.
pub fn type_tag(&self) -> &'static str {
match self {
Trigger::Cron { .. } => "cron",
Trigger::Event { .. } => "event",
Trigger::Webhook { .. } => "webhook",
Trigger::Manual => "manual",
}
}
/// Parse a trigger from its DB representation.
pub fn from_db(trigger_type: &str, config: serde_json::Value) -> Result<Self, String> {
match trigger_type {
"cron" => {
let schedule = config
.get("schedule")
.and_then(|v| v.as_str())
.ok_or("cron trigger missing 'schedule'")?
.to_string();
Ok(Trigger::Cron { schedule })
}
"event" => {
let pattern = config
.get("pattern")
.and_then(|v| v.as_str())
.ok_or("event trigger missing 'pattern'")?
.to_string();
let channel = config
.get("channel")
.and_then(|v| v.as_str())
.map(String::from);
Ok(Trigger::Event { channel, pattern })
}
"webhook" => {
let path = config
.get("path")
.and_then(|v| v.as_str())
.map(String::from);
let secret = config
.get("secret")
.and_then(|v| v.as_str())
.map(String::from);
Ok(Trigger::Webhook { path, secret })
}
"manual" => Ok(Trigger::Manual),
other => Err(format!("unknown trigger type: {other}")),
}
}
/// Serialize trigger-specific config to JSON for DB storage.
pub fn to_config_json(&self) -> serde_json::Value {
match self {
Trigger::Cron { schedule } => serde_json::json!({ "schedule": schedule }),
Trigger::Event { channel, pattern } => serde_json::json!({
"pattern": pattern,
"channel": channel,
}),
Trigger::Webhook { path, secret } => serde_json::json!({
"path": path,
"secret": secret,
}),
Trigger::Manual => serde_json::json!({}),
}
}
}
/// What happens when a routine fires.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(tag = "type", rename_all = "snake_case")]
pub enum RoutineAction {
/// Single LLM call, no tools. Cheap and fast.
Lightweight {
/// The prompt sent to the LLM.
prompt: String,
/// Workspace paths to load as context (e.g. ["context/priorities.md"]).
#[serde(default)]
context_paths: Vec<String>,
/// Max output tokens (default: 4096).
#[serde(default = "default_max_tokens")]
max_tokens: u32,
},
/// Full multi-turn worker job with tool access.
FullJob {
/// Job title for the scheduler.
title: String,
/// Job description / initial prompt.
description: String,
/// Max reasoning iterations (default: 10).
#[serde(default = "default_max_iterations")]
max_iterations: u32,
},
}
fn default_max_tokens() -> u32 {
4096
}
fn default_max_iterations() -> u32 {
10
}
impl RoutineAction {
/// The string tag stored in the DB action_type column.
pub fn type_tag(&self) -> &'static str {
match self {
RoutineAction::Lightweight { .. } => "lightweight",
RoutineAction::FullJob { .. } => "full_job",
}
}
/// Parse an action from its DB representation.
pub fn from_db(action_type: &str, config: serde_json::Value) -> Result<Self, String> {
match action_type {
"lightweight" => {
let prompt = config
.get("prompt")
.and_then(|v| v.as_str())
.ok_or("lightweight action missing 'prompt'")?
.to_string();
let context_paths = config
.get("context_paths")
.and_then(|v| v.as_array())
.map(|arr| {
arr.iter()
.filter_map(|v| v.as_str().map(String::from))
.collect()
})
.unwrap_or_default();
let max_tokens = config
.get("max_tokens")
.and_then(|v| v.as_u64())
.unwrap_or(default_max_tokens() as u64) as u32;
Ok(RoutineAction::Lightweight {
prompt,
context_paths,
max_tokens,
})
}
"full_job" => {
let title = config
.get("title")
.and_then(|v| v.as_str())
.ok_or("full_job action missing 'title'")?
.to_string();
let description = config
.get("description")
.and_then(|v| v.as_str())
.ok_or("full_job action missing 'description'")?
.to_string();
let max_iterations = config
.get("max_iterations")
.and_then(|v| v.as_u64())
.unwrap_or(default_max_iterations() as u64)
as u32;
Ok(RoutineAction::FullJob {
title,
description,
max_iterations,
})
}
other => Err(format!("unknown action type: {other}")),
}
}
/// Serialize action config to JSON for DB storage.
pub fn to_config_json(&self) -> serde_json::Value {
match self {
RoutineAction::Lightweight {
prompt,
context_paths,
max_tokens,
} => serde_json::json!({
"prompt": prompt,
"context_paths": context_paths,
"max_tokens": max_tokens,
}),
RoutineAction::FullJob {
title,
description,
max_iterations,
} => serde_json::json!({
"title": title,
"description": description,
"max_iterations": max_iterations,
}),
}
}
}
/// Guardrails to prevent runaway execution.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct RoutineGuardrails {
/// Minimum time between fires.
pub cooldown: Duration,
/// Max simultaneous runs of this routine.
pub max_concurrent: u32,
/// Window for content-hash dedup (event triggers). None = no dedup.
pub dedup_window: Option<Duration>,
}
impl Default for RoutineGuardrails {
fn default() -> Self {
Self {
cooldown: Duration::from_secs(300),
max_concurrent: 1,
dedup_window: None,
}
}
}
/// Notification preferences for a routine.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct NotifyConfig {
/// Channel to notify on (None = default/broadcast all).
pub channel: Option<String>,
/// User to notify.
pub user: String,
/// Notify when routine produces actionable output.
pub on_attention: bool,
/// Notify when routine errors.
pub on_failure: bool,
/// Notify when routine runs with no findings.
pub on_success: bool,
}
impl Default for NotifyConfig {
fn default() -> Self {
Self {
channel: None,
user: "default".to_string(),
on_attention: true,
on_failure: true,
on_success: false,
}
}
}
/// Status of a routine run.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum RunStatus {
Running,
Ok,
Attention,
Failed,
}
impl std::fmt::Display for RunStatus {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
RunStatus::Running => write!(f, "running"),
RunStatus::Ok => write!(f, "ok"),
RunStatus::Attention => write!(f, "attention"),
RunStatus::Failed => write!(f, "failed"),
}
}
}
impl FromStr for RunStatus {
type Err = String;
fn from_str(s: &str) -> Result<Self, Self::Err> {
match s {
"running" => Ok(RunStatus::Running),
"ok" => Ok(RunStatus::Ok),
"attention" => Ok(RunStatus::Attention),
"failed" => Ok(RunStatus::Failed),
other => Err(format!("unknown run status: {other}")),
}
}
}
/// A single execution of a routine.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct RoutineRun {
pub id: Uuid,
pub routine_id: Uuid,
pub trigger_type: String,
pub trigger_detail: Option<String>,
pub started_at: DateTime<Utc>,
pub completed_at: Option<DateTime<Utc>>,
pub status: RunStatus,
pub result_summary: Option<String>,
pub tokens_used: Option<i32>,
pub job_id: Option<Uuid>,
pub created_at: DateTime<Utc>,
}
/// Compute a content hash for event dedup.
pub fn content_hash(content: &str) -> u64 {
let mut hasher = DefaultHasher::new();
content.hash(&mut hasher);
hasher.finish()
}
/// Parse a cron expression and compute the next fire time from now.
pub fn next_cron_fire(schedule: &str) -> Result<Option<DateTime<Utc>>, String> {
let cron_schedule =
cron::Schedule::from_str(schedule).map_err(|e| format!("invalid cron: {e}"))?;
Ok(cron_schedule.upcoming(Utc).next())
}
#[cfg(test)]
mod tests {
use crate::agent::routine::{
RoutineAction, RoutineGuardrails, RunStatus, Trigger, content_hash, next_cron_fire,
};
#[test]
fn test_trigger_roundtrip() {
let trigger = Trigger::Cron {
schedule: "0 9 * * MON-FRI".to_string(),
};
let json = trigger.to_config_json();
let parsed = Trigger::from_db("cron", json).expect("parse cron");
assert!(matches!(parsed, Trigger::Cron { schedule } if schedule == "0 9 * * MON-FRI"));
}
#[test]
fn test_event_trigger_roundtrip() {
let trigger = Trigger::Event {
channel: Some("telegram".to_string()),
pattern: r"deploy\s+\w+".to_string(),
};
let json = trigger.to_config_json();
let parsed = Trigger::from_db("event", json).expect("parse event");
assert!(matches!(parsed, Trigger::Event { channel, pattern }
if channel == Some("telegram".to_string()) && pattern == r"deploy\s+\w+"));
}
#[test]
fn test_action_lightweight_roundtrip() {
let action = RoutineAction::Lightweight {
prompt: "Check PRs".to_string(),
context_paths: vec!["context/priorities.md".to_string()],
max_tokens: 2048,
};
let json = action.to_config_json();
let parsed = RoutineAction::from_db("lightweight", json).expect("parse lightweight");
assert!(
matches!(parsed, RoutineAction::Lightweight { prompt, context_paths, max_tokens }
if prompt == "Check PRs" && context_paths.len() == 1 && max_tokens == 2048)
);
}
#[test]
fn test_action_full_job_roundtrip() {
let action = RoutineAction::FullJob {
title: "Deploy review".to_string(),
description: "Review and deploy pending changes".to_string(),
max_iterations: 5,
};
let json = action.to_config_json();
let parsed = RoutineAction::from_db("full_job", json).expect("parse full_job");
assert!(
matches!(parsed, RoutineAction::FullJob { title, max_iterations, .. }
if title == "Deploy review" && max_iterations == 5)
);
}
#[test]
fn test_run_status_display_parse() {
for status in [
RunStatus::Running,
RunStatus::Ok,
RunStatus::Attention,
RunStatus::Failed,
] {
let s = status.to_string();
let parsed: RunStatus = s.parse().expect("parse status");
assert_eq!(parsed, status);
}
}
#[test]
fn test_content_hash_deterministic() {
let h1 = content_hash("deploy production");
let h2 = content_hash("deploy production");
assert_eq!(h1, h2);
let h3 = content_hash("deploy staging");
assert_ne!(h1, h3);
}
#[test]
fn test_next_cron_fire_valid() {
// Every minute should always have a next fire
let next = next_cron_fire("* * * * * *").expect("valid cron");
assert!(next.is_some());
}
#[test]
fn test_next_cron_fire_invalid() {
let result = next_cron_fire("not a cron");
assert!(result.is_err());
}
#[test]
fn test_guardrails_default() {
let g = RoutineGuardrails::default();
assert_eq!(g.cooldown.as_secs(), 300);
assert_eq!(g.max_concurrent, 1);
assert!(g.dedup_window.is_none());
}
#[test]
fn test_trigger_type_tag() {
assert_eq!(
Trigger::Cron {
schedule: String::new()
}
.type_tag(),
"cron"
);
assert_eq!(
Trigger::Event {
channel: None,
pattern: String::new()
}
.type_tag(),
"event"
);
assert_eq!(
Trigger::Webhook {
path: None,
secret: None
}
.type_tag(),
"webhook"
);
assert_eq!(Trigger::Manual.type_tag(), "manual");
}
}
-601
View File
@@ -1,601 +0,0 @@
//! Routine execution engine.
//!
//! Handles loading routines, checking triggers, enforcing guardrails,
//! and executing both lightweight (single LLM call) and full-job routines.
//!
//! The engine runs two independent loops:
//! - A **cron ticker** that polls the DB every N seconds for due cron routines
//! - An **event matcher** called synchronously from the agent main loop
//!
//! Lightweight routines execute inline (single LLM call, no scheduler slot).
//! Full-job routines are delegated to the existing `Scheduler`.
use std::sync::Arc;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::time::Duration;
use chrono::Utc;
use regex::Regex;
use tokio::sync::{RwLock, mpsc};
use uuid::Uuid;
use crate::agent::routine::{
NotifyConfig, Routine, RoutineAction, RoutineRun, RunStatus, Trigger, next_cron_fire,
};
use crate::channels::{IncomingMessage, OutgoingResponse};
use crate::config::RoutineConfig;
use crate::db::Database;
use crate::llm::{ChatMessage, CompletionRequest, FinishReason, LlmProvider};
use crate::workspace::Workspace;
/// The routine execution engine.
pub struct RoutineEngine {
config: RoutineConfig,
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
/// Sender for notifications (routed to channel manager).
notify_tx: mpsc::Sender<OutgoingResponse>,
/// Currently running routine count (across all routines).
running_count: Arc<AtomicUsize>,
/// Compiled event regex cache: routine_id -> compiled regex.
event_cache: Arc<RwLock<Vec<(Uuid, Routine, Regex)>>>,
}
impl RoutineEngine {
pub fn new(
config: RoutineConfig,
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
) -> Self {
Self {
config,
store,
llm,
workspace,
notify_tx,
running_count: Arc::new(AtomicUsize::new(0)),
event_cache: Arc::new(RwLock::new(Vec::new())),
}
}
/// Refresh the in-memory event trigger cache from DB.
pub async fn refresh_event_cache(&self) {
match self.store.list_event_routines().await {
Ok(routines) => {
let mut cache = Vec::new();
for routine in routines {
if let Trigger::Event { ref pattern, .. } = routine.trigger {
match Regex::new(pattern) {
Ok(re) => cache.push((routine.id, routine.clone(), re)),
Err(e) => {
tracing::warn!(
routine = %routine.name,
"Invalid event regex '{}': {}",
pattern, e
);
}
}
}
}
let count = cache.len();
*self.event_cache.write().await = cache;
tracing::debug!("Refreshed event cache: {} routines", count);
}
Err(e) => {
tracing::error!("Failed to refresh event cache: {}", e);
}
}
}
/// Check incoming message against event triggers. Returns number of routines fired.
///
/// Called synchronously from the main loop after handle_message(). The actual
/// execution is spawned async so this returns quickly.
pub async fn check_event_triggers(&self, message: &IncomingMessage) -> usize {
let cache = self.event_cache.read().await;
let mut fired = 0;
for (_, routine, re) in cache.iter() {
// Channel filter
if let Trigger::Event {
channel: Some(ch), ..
} = &routine.trigger
&& ch != &message.channel
{
continue;
}
// Regex match
if !re.is_match(&message.content) {
continue;
}
// Cooldown check
if !self.check_cooldown(routine) {
tracing::debug!(routine = %routine.name, "Skipped: cooldown active");
continue;
}
// Concurrent run check
if !self.check_concurrent(routine).await {
tracing::debug!(routine = %routine.name, "Skipped: max concurrent reached");
continue;
}
// Global capacity check
if self.running_count.load(Ordering::Relaxed) >= self.config.max_concurrent_routines {
tracing::warn!(routine = %routine.name, "Skipped: global max concurrent reached");
continue;
}
let detail = truncate(&message.content, 200);
self.spawn_fire(routine.clone(), "event", Some(detail));
fired += 1;
}
fired
}
/// Check all due cron routines and fire them. Called by the cron ticker.
pub async fn check_cron_triggers(&self) {
let routines = match self.store.list_due_cron_routines().await {
Ok(r) => r,
Err(e) => {
tracing::error!("Failed to load due cron routines: {}", e);
return;
}
};
for routine in routines {
if self.running_count.load(Ordering::Relaxed) >= self.config.max_concurrent_routines {
tracing::warn!("Global max concurrent routines reached, skipping remaining");
break;
}
if !self.check_cooldown(&routine) {
continue;
}
if !self.check_concurrent(&routine).await {
continue;
}
let detail = if let Trigger::Cron { ref schedule } = routine.trigger {
Some(schedule.clone())
} else {
None
};
self.spawn_fire(routine, "cron", detail);
}
}
/// Fire a routine manually (from tool call or CLI).
pub async fn fire_manual(&self, routine_id: Uuid) -> Result<Uuid, String> {
let routine = self
.store
.get_routine(routine_id)
.await
.map_err(|e| format!("DB error: {e}"))?
.ok_or_else(|| format!("routine {routine_id} not found"))?;
if !routine.enabled {
return Err(format!("routine '{}' is disabled", routine.name));
}
if !self.check_concurrent(&routine).await {
return Err(format!(
"routine '{}' already at max concurrent runs",
routine.name
));
}
let run_id = Uuid::new_v4();
let run = RoutineRun {
id: run_id,
routine_id: routine.id,
trigger_type: "manual".to_string(),
trigger_detail: None,
started_at: Utc::now(),
completed_at: None,
status: RunStatus::Running,
result_summary: None,
tokens_used: None,
job_id: None,
created_at: Utc::now(),
};
if let Err(e) = self.store.create_routine_run(&run).await {
return Err(format!("failed to create run record: {e}"));
}
// Execute inline for manual triggers (caller wants to wait)
let engine = EngineContext {
store: self.store.clone(),
llm: self.llm.clone(),
workspace: self.workspace.clone(),
notify_tx: self.notify_tx.clone(),
running_count: self.running_count.clone(),
max_lightweight_tokens: self.config.max_lightweight_tokens,
};
tokio::spawn(async move {
execute_routine(engine, routine, run).await;
});
Ok(run_id)
}
/// Spawn a fire in a background task.
fn spawn_fire(&self, routine: Routine, trigger_type: &str, trigger_detail: Option<String>) {
let run = RoutineRun {
id: Uuid::new_v4(),
routine_id: routine.id,
trigger_type: trigger_type.to_string(),
trigger_detail,
started_at: Utc::now(),
completed_at: None,
status: RunStatus::Running,
result_summary: None,
tokens_used: None,
job_id: None,
created_at: Utc::now(),
};
let engine = EngineContext {
store: self.store.clone(),
llm: self.llm.clone(),
workspace: self.workspace.clone(),
notify_tx: self.notify_tx.clone(),
running_count: self.running_count.clone(),
max_lightweight_tokens: self.config.max_lightweight_tokens,
};
// Record the run in DB, then spawn execution
let store = self.store.clone();
tokio::spawn(async move {
if let Err(e) = store.create_routine_run(&run).await {
tracing::error!(routine = %routine.name, "Failed to record run: {}", e);
return;
}
execute_routine(engine, routine, run).await;
});
}
fn check_cooldown(&self, routine: &Routine) -> bool {
if let Some(last_run) = routine.last_run_at {
let elapsed = Utc::now().signed_duration_since(last_run);
let cooldown = chrono::Duration::from_std(routine.guardrails.cooldown)
.unwrap_or(chrono::Duration::seconds(300));
if elapsed < cooldown {
return false;
}
}
true
}
async fn check_concurrent(&self, routine: &Routine) -> bool {
match self.store.count_running_routine_runs(routine.id).await {
Ok(count) => count < routine.guardrails.max_concurrent as i64,
Err(e) => {
tracing::error!(
routine = %routine.name,
"Failed to check concurrent runs: {}", e
);
false
}
}
}
}
/// Shared context passed to the execution function.
struct EngineContext {
store: Arc<dyn Database>,
llm: Arc<dyn LlmProvider>,
workspace: Arc<Workspace>,
notify_tx: mpsc::Sender<OutgoingResponse>,
running_count: Arc<AtomicUsize>,
max_lightweight_tokens: u32,
}
/// Execute a routine run. Handles both lightweight and full_job modes.
async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun) {
// Increment running count (atomic: survives panics in the execution below)
ctx.running_count.fetch_add(1, Ordering::Relaxed);
let result = match &routine.action {
RoutineAction::Lightweight {
prompt,
context_paths,
max_tokens,
} => execute_lightweight(&ctx, &routine, prompt, context_paths, *max_tokens).await,
RoutineAction::FullJob { description, .. } => {
// Full job mode: for now, execute as lightweight with the description
// as prompt. Full scheduler integration will come as a follow-up.
tracing::info!(
routine = %routine.name,
"FullJob mode executing as lightweight (scheduler integration pending)"
);
execute_lightweight(&ctx, &routine, description, &[], ctx.max_lightweight_tokens).await
}
};
// Decrement running count
ctx.running_count.fetch_sub(1, Ordering::Relaxed);
// Process result
let (status, summary, tokens) = match result {
Ok(execution) => execution,
Err(e) => {
tracing::error!(routine = %routine.name, "Execution failed: {}", e);
(RunStatus::Failed, Some(e), None)
}
};
// Complete the run record
if let Err(e) = ctx
.store
.complete_routine_run(run.id, status, summary.as_deref(), tokens)
.await
{
tracing::error!(routine = %routine.name, "Failed to complete run record: {}", e);
}
// Update routine runtime state
let now = Utc::now();
let next_fire = if let Trigger::Cron { ref schedule } = routine.trigger {
next_cron_fire(schedule).unwrap_or(None)
} else {
None
};
let new_failures = if status == RunStatus::Failed {
routine.consecutive_failures + 1
} else {
0
};
if let Err(e) = ctx
.store
.update_routine_runtime(
routine.id,
now,
next_fire,
routine.run_count + 1,
new_failures,
&routine.state,
)
.await
{
tracing::error!(routine = %routine.name, "Failed to update runtime state: {}", e);
}
// Send notifications based on config
send_notification(
&ctx.notify_tx,
&routine.notify,
&routine.name,
status,
summary.as_deref(),
)
.await;
}
/// Execute a lightweight routine (single LLM call).
async fn execute_lightweight(
ctx: &EngineContext,
routine: &Routine,
prompt: &str,
context_paths: &[String],
max_tokens: u32,
) -> Result<(RunStatus, Option<String>, Option<i32>), String> {
// Load context from workspace
let mut context_parts = Vec::new();
for path in context_paths {
match ctx.workspace.read(path).await {
Ok(doc) => {
context_parts.push(format!("## {}\n\n{}", path, doc.content));
}
Err(e) => {
tracing::debug!(
routine = %routine.name,
"Failed to read context path {}: {}", path, e
);
}
}
}
// Load routine state from workspace
let state_path = format!("routines/{}/state.md", routine.name);
let state_content = match ctx.workspace.read(&state_path).await {
Ok(doc) => Some(doc.content),
Err(_) => None,
};
// Build the prompt
let mut full_prompt = String::new();
full_prompt.push_str(prompt);
if !context_parts.is_empty() {
full_prompt.push_str("\n\n---\n\n# Context\n\n");
full_prompt.push_str(&context_parts.join("\n\n"));
}
if let Some(state) = &state_content {
full_prompt.push_str("\n\n---\n\n# Previous State\n\n");
full_prompt.push_str(state);
}
full_prompt.push_str(
"\n\n---\n\nIf nothing needs attention, reply EXACTLY with: ROUTINE_OK\n\
If something needs attention, provide a concise summary.",
);
// Get system prompt
let system_prompt = match ctx.workspace.system_prompt().await {
Ok(p) => p,
Err(e) => {
tracing::warn!(routine = %routine.name, "Failed to get system prompt: {}", e);
String::new()
}
};
let messages = if system_prompt.is_empty() {
vec![ChatMessage::user(&full_prompt)]
} else {
vec![
ChatMessage::system(&system_prompt),
ChatMessage::user(&full_prompt),
]
};
// Determine max_tokens from model metadata with fallback
let effective_max_tokens = match ctx.llm.model_metadata().await {
Ok(meta) => {
let from_api = meta.context_length.map(|ctx| ctx / 2).unwrap_or(max_tokens);
from_api.max(max_tokens)
}
Err(_) => max_tokens,
};
let request = CompletionRequest::new(messages)
.with_max_tokens(effective_max_tokens)
.with_temperature(0.3);
let response = ctx
.llm
.complete(request)
.await
.map_err(|e| format!("LLM call failed: {e}"))?;
let content = response.content.trim();
let tokens_used = Some((response.input_tokens + response.output_tokens) as i32);
// Empty content guard (same as heartbeat)
if content.is_empty() {
return if response.finish_reason == FinishReason::Length {
Err(
"LLM response truncated (finish_reason=length) with no content. \
Model may have exhausted token budget on reasoning."
.to_string(),
)
} else {
Err("LLM returned empty content.".to_string())
};
}
// Check for the "nothing to do" sentinel
if content == "ROUTINE_OK" || content.contains("ROUTINE_OK") {
return Ok((RunStatus::Ok, None, tokens_used));
}
Ok((RunStatus::Attention, Some(content.to_string()), tokens_used))
}
/// Send a notification based on the routine's notify config and run status.
async fn send_notification(
tx: &mpsc::Sender<OutgoingResponse>,
notify: &NotifyConfig,
routine_name: &str,
status: RunStatus,
summary: Option<&str>,
) {
let should_notify = match status {
RunStatus::Ok => notify.on_success,
RunStatus::Attention => notify.on_attention,
RunStatus::Failed => notify.on_failure,
RunStatus::Running => false,
};
if !should_notify {
return;
}
let icon = match status {
RunStatus::Ok => "",
RunStatus::Attention => "🔔",
RunStatus::Failed => "",
RunStatus::Running => "",
};
let message = match summary {
Some(s) => format!("{} *Routine '{}'*: {}\n\n{}", icon, routine_name, status, s),
None => format!("{} *Routine '{}'*: {}", icon, routine_name, status),
};
let response = OutgoingResponse {
content: message,
thread_id: None,
metadata: serde_json::json!({
"source": "routine",
"routine_name": routine_name,
"status": status.to_string(),
}),
};
if let Err(e) = tx.send(response).await {
tracing::error!(routine = %routine_name, "Failed to send notification: {}", e);
}
}
/// Spawn the cron ticker background task.
pub fn spawn_cron_ticker(
engine: Arc<RoutineEngine>,
interval: Duration,
) -> tokio::task::JoinHandle<()> {
tokio::spawn(async move {
let mut ticker = tokio::time::interval(interval);
// Skip immediate first tick
ticker.tick().await;
loop {
ticker.tick().await;
engine.check_cron_triggers().await;
}
})
}
fn truncate(s: &str, max: usize) -> String {
if s.len() <= max {
s.to_string()
} else {
let end = crate::util::floor_char_boundary(s, max);
format!("{}...", &s[..end])
}
}
#[cfg(test)]
mod tests {
use crate::agent::routine::{NotifyConfig, RunStatus};
#[test]
fn test_notification_gating() {
let config = NotifyConfig {
on_success: false,
on_failure: true,
on_attention: true,
..Default::default()
};
// on_success = false means Ok status should not notify
assert!(!config.on_success);
assert!(config.on_failure);
assert!(config.on_attention);
}
#[test]
fn test_run_status_icons() {
// Just verify the mapping doesn't panic
for status in [
RunStatus::Ok,
RunStatus::Attention,
RunStatus::Failed,
RunStatus::Running,
] {
let _ = status.to_string();
}
}
}
+76 -81
View File
@@ -12,9 +12,8 @@ use crate::agent::task::{Task, TaskContext, TaskOutput};
use crate::agent::worker::{Worker, WorkerDeps};
use crate::config::AgentConfig;
use crate::context::{ContextManager, JobContext, JobState};
use crate::db::Database;
use crate::error::{Error, JobError};
use crate::hooks::HookRegistry;
use crate::history::Store;
use crate::llm::LlmProvider;
use crate::safety::SafetyLayer;
use crate::tools::ToolRegistry;
@@ -49,8 +48,7 @@ pub struct Scheduler {
llm: Arc<dyn LlmProvider>,
safety: Arc<SafetyLayer>,
tools: Arc<ToolRegistry>,
store: Option<Arc<dyn Database>>,
hooks: Arc<HookRegistry>,
store: Option<Arc<Store>>,
/// Running jobs (main LLM-driven jobs).
jobs: Arc<RwLock<HashMap<Uuid, ScheduledJob>>>,
/// Running sub-tasks (tool executions, background tasks).
@@ -65,8 +63,7 @@ impl Scheduler {
llm: Arc<dyn LlmProvider>,
safety: Arc<SafetyLayer>,
tools: Arc<ToolRegistry>,
store: Option<Arc<dyn Database>>,
hooks: Arc<HookRegistry>,
store: Option<Arc<Store>>,
) -> Self {
Self {
config,
@@ -75,7 +72,6 @@ impl Scheduler {
safety,
tools,
store,
hooks,
jobs: Arc::new(RwLock::new(HashMap::new())),
subtasks: Arc::new(RwLock::new(HashMap::new())),
}
@@ -83,65 +79,64 @@ impl Scheduler {
/// Schedule a job for execution.
pub async fn schedule(&self, job_id: Uuid) -> Result<(), JobError> {
// Hold write lock for the entire check-insert sequence to prevent
// TOCTOU races where two concurrent calls both pass the checks.
{
let mut jobs = self.jobs.write().await;
if jobs.contains_key(&job_id) {
return Ok(());
}
if jobs.len() >= self.config.max_parallel_jobs {
return Err(JobError::MaxJobsExceeded {
max: self.config.max_parallel_jobs,
});
}
// Transition job to in_progress
self.context_manager
.update_context(job_id, |ctx| {
ctx.transition_to(
JobState::InProgress,
Some("Scheduled for execution".to_string()),
)
})
.await?
.map_err(|s| JobError::ContextError {
id: job_id,
reason: s,
})?;
// Create worker channel
let (tx, rx) = mpsc::channel(16);
// Create worker with shared dependencies
let deps = WorkerDeps {
context_manager: self.context_manager.clone(),
llm: self.llm.clone(),
safety: self.safety.clone(),
tools: self.tools.clone(),
store: self.store.clone(),
hooks: self.hooks.clone(),
timeout: self.config.job_timeout,
use_planning: self.config.use_planning,
};
let worker = Worker::new(job_id, deps);
// Spawn worker task
let handle = tokio::spawn(async move {
if let Err(e) = worker.run(rx).await {
tracing::error!("Worker for job {} failed: {}", job_id, e);
}
});
// Start the worker
let _ = tx.send(WorkerMessage::Start).await;
// Insert while still holding the write lock
jobs.insert(job_id, ScheduledJob { handle, tx });
// Check if already scheduled
if self.jobs.read().await.contains_key(&job_id) {
return Ok(());
}
// Check capacity
let current_count = self.jobs.read().await.len();
if current_count >= self.config.max_parallel_jobs {
return Err(JobError::MaxJobsExceeded {
max: self.config.max_parallel_jobs,
});
}
// Transition job to in_progress
self.context_manager
.update_context(job_id, |ctx| {
ctx.transition_to(
JobState::InProgress,
Some("Scheduled for execution".to_string()),
)
})
.await?
.map_err(|s| JobError::ContextError {
id: job_id,
reason: s,
})?;
// Create worker channel
let (tx, rx) = mpsc::channel(16);
// Create worker with shared dependencies
let deps = WorkerDeps {
context_manager: self.context_manager.clone(),
llm: self.llm.clone(),
safety: self.safety.clone(),
tools: self.tools.clone(),
store: self.store.clone(),
timeout: self.config.job_timeout,
use_planning: self.config.use_planning,
};
let worker = Worker::new(job_id, deps);
// Spawn worker task
let handle = tokio::spawn(async move {
if let Err(e) = worker.run(rx).await {
tracing::error!("Worker for job {} failed: {}", job_id, e);
}
});
// Start the worker
let _ = tx.send(WorkerMessage::Start).await;
// Store the scheduled job
self.jobs
.write()
.await
.insert(job_id, ScheduledJob { handle, tx });
// Cleanup task for this job to avoid capacity leaks
let jobs = Arc::clone(&self.jobs);
tokio::spawn(async move {
@@ -378,23 +373,23 @@ impl Scheduler {
.into());
}
// Execute with per-tool timeout
let tool_timeout = tool.execution_timeout();
let result =
tokio::time::timeout(tool_timeout, async { tool.execute(params, &job_ctx).await })
.await
.map_err(|_| {
Error::Tool(crate::error::ToolError::Timeout {
name: tool_name.to_string(),
timeout: tool_timeout,
})
})?
.map_err(|e| {
Error::Tool(crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
reason: e.to_string(),
})
})?;
// Execute with timeout
let result = tokio::time::timeout(Duration::from_secs(60), async {
tool.execute(params, &job_ctx).await
})
.await
.map_err(|_| {
Error::Tool(crate::error::ToolError::Timeout {
name: tool_name.to_string(),
timeout: Duration::from_secs(60),
})
})?
.map_err(|e| {
Error::Tool(crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
reason: e.to_string(),
})
})?;
Ok(TaskOutput::new(result.result, start.elapsed()))
}
+21 -21
View File
@@ -8,8 +8,8 @@ use chrono::{DateTime, Utc};
use uuid::Uuid;
use crate::context::{ContextManager, JobState};
use crate::db::Database;
use crate::error::RepairError;
use crate::history::Store;
use crate::tools::{BuildRequirement, Language, SoftwareBuilder, SoftwareType, ToolRegistry};
/// A job that has been detected as stuck.
@@ -69,7 +69,7 @@ pub struct DefaultSelfRepair {
#[allow(dead_code)] // Will be used for time-based stuck detection
stuck_threshold: Duration,
max_repair_attempts: u32,
store: Option<Arc<dyn Database>>,
store: Option<Arc<Store>>,
builder: Option<Arc<dyn SoftwareBuilder>>,
#[allow(dead_code)] // Will be used for tool hot-reload after repair
tools: Option<Arc<ToolRegistry>>,
@@ -94,7 +94,7 @@ impl DefaultSelfRepair {
/// Add a Store for tool failure tracking.
#[allow(dead_code)] // Public API for configuring repair with persistence
pub fn with_store(mut self, store: Arc<dyn Database>) -> Self {
pub fn with_store(mut self, store: Arc<Store>) -> Self {
self.store = Some(store);
self
}
@@ -119,25 +119,25 @@ impl SelfRepair for DefaultSelfRepair {
let mut stuck_jobs = Vec::new();
for job_id in stuck_ids {
if let Ok(ctx) = self.context_manager.get_context(job_id).await
&& ctx.state == JobState::Stuck
{
let stuck_duration = ctx
.started_at
.map(|start| {
let now = Utc::now();
let duration = now.signed_duration_since(start);
Duration::from_secs(duration.num_seconds().max(0) as u64)
})
.unwrap_or_default();
if let Ok(ctx) = self.context_manager.get_context(job_id).await {
if ctx.state == JobState::Stuck {
let stuck_duration = ctx
.started_at
.map(|start| {
let now = Utc::now();
let duration = now.signed_duration_since(start);
Duration::from_secs(duration.num_seconds().max(0) as u64)
})
.unwrap_or_default();
stuck_jobs.push(StuckJob {
job_id,
last_activity: ctx.started_at.unwrap_or(ctx.created_at),
stuck_duration,
last_error: None,
repair_attempts: ctx.repair_attempts,
});
stuck_jobs.push(StuckJob {
job_id,
last_activity: ctx.started_at.unwrap_or(ctx.created_at),
stuck_duration,
last_error: None,
repair_attempts: ctx.repair_attempts,
});
}
}
}
+5 -491
View File
@@ -121,18 +121,6 @@ pub enum ThreadState {
Interrupted,
}
/// Pending auth token request.
///
/// When `tool_auth` returns `awaiting_token`, the thread enters auth mode.
/// The next user message is intercepted before entering the normal pipeline
/// (no logging, no turn creation, no history) and routed directly to the
/// credential store.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PendingAuth {
/// Extension name to authenticate.
pub extension_name: String,
}
/// Pending tool approval request stored on a thread.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PendingApproval {
@@ -170,13 +158,6 @@ pub struct Thread {
/// Pending approval request (when state is AwaitingApproval).
#[serde(default)]
pub pending_approval: Option<PendingApproval>,
/// Pending auth token request (thread is in auth mode).
#[serde(default)]
pub pending_auth: Option<PendingAuth>,
/// Last NEAR AI response ID for response chaining. Persisted to DB
/// metadata so we can resume chaining across restarts.
#[serde(default)]
pub last_response_id: Option<String>,
}
impl Thread {
@@ -192,25 +173,6 @@ impl Thread {
updated_at: now,
metadata: serde_json::Value::Null,
pending_approval: None,
pending_auth: None,
last_response_id: None,
}
}
/// Create a thread with a specific ID (for DB hydration).
pub fn with_id(id: Uuid, session_id: Uuid) -> Self {
let now = Utc::now();
Self {
id,
session_id,
state: ThreadState::Idle,
turns: Vec::new(),
created_at: now,
updated_at: now,
metadata: serde_json::Value::Null,
pending_approval: None,
pending_auth: None,
last_response_id: None,
}
}
@@ -276,18 +238,6 @@ impl Thread {
self.updated_at = Utc::now();
}
/// Enter auth mode: next user message will be routed directly to
/// the credential store, bypassing the normal pipeline entirely.
pub fn enter_auth_mode(&mut self, extension_name: String) {
self.pending_auth = Some(PendingAuth { extension_name });
self.updated_at = Utc::now();
}
/// Take the pending auth (clearing auth mode).
pub fn take_pending_auth(&mut self) -> Option<PendingAuth> {
self.pending_auth.take()
}
/// Interrupt the current turn.
pub fn interrupt(&mut self) {
if let Some(turn) = self.turns.last_mut() {
@@ -346,11 +296,11 @@ impl Thread {
let mut turn = Turn::new(turn_number, &msg.content);
// Check if next is assistant response
if let Some(next) = iter.peek()
&& next.role == crate::llm::Role::Assistant
{
let response = iter.next().expect("peeked");
turn.complete(&response.content);
if let Some(next) = iter.peek() {
if next.role == crate::llm::Role::Assistant {
let response = iter.next().expect("peeked");
turn.complete(&response.content);
}
}
self.turns.push(turn);
@@ -561,440 +511,4 @@ mod tests {
assert_eq!(thread.turns[1].user_input, "How are you?");
assert!(thread.turns[1].response.is_none());
}
#[test]
fn test_enter_auth_mode() {
let mut thread = Thread::new(Uuid::new_v4());
assert!(thread.pending_auth.is_none());
thread.enter_auth_mode("telegram".to_string());
assert!(thread.pending_auth.is_some());
assert_eq!(
thread.pending_auth.as_ref().unwrap().extension_name,
"telegram"
);
}
#[test]
fn test_take_pending_auth() {
let mut thread = Thread::new(Uuid::new_v4());
thread.enter_auth_mode("notion".to_string());
let pending = thread.take_pending_auth();
assert!(pending.is_some());
assert_eq!(pending.unwrap().extension_name, "notion");
// Should be cleared after take
assert!(thread.pending_auth.is_none());
assert!(thread.take_pending_auth().is_none());
}
#[test]
fn test_pending_auth_serialization() {
let mut thread = Thread::new(Uuid::new_v4());
thread.enter_auth_mode("openai".to_string());
let json = serde_json::to_string(&thread).expect("should serialize");
assert!(json.contains("pending_auth"));
assert!(json.contains("openai"));
let restored: Thread = serde_json::from_str(&json).expect("should deserialize");
assert!(restored.pending_auth.is_some());
assert_eq!(restored.pending_auth.unwrap().extension_name, "openai");
}
#[test]
fn test_pending_auth_default_none() {
// Deserialization of old data without pending_auth should default to None
let mut thread = Thread::new(Uuid::new_v4());
thread.pending_auth = None;
let json = serde_json::to_string(&thread).expect("serialize");
// Remove the pending_auth field to simulate old data
let json = json.replace(",\"pending_auth\":null", "");
let restored: Thread = serde_json::from_str(&json).expect("should deserialize");
assert!(restored.pending_auth.is_none());
}
#[test]
fn test_thread_with_id() {
let specific_id = Uuid::new_v4();
let session_id = Uuid::new_v4();
let thread = Thread::with_id(specific_id, session_id);
assert_eq!(thread.id, specific_id);
assert_eq!(thread.session_id, session_id);
assert_eq!(thread.state, ThreadState::Idle);
assert!(thread.turns.is_empty());
}
#[test]
fn test_thread_with_id_restore_messages() {
let thread_id = Uuid::new_v4();
let session_id = Uuid::new_v4();
let mut thread = Thread::with_id(thread_id, session_id);
let messages = vec![
ChatMessage::user("Hello from DB"),
ChatMessage::assistant("Restored response"),
];
thread.restore_from_messages(messages);
assert_eq!(thread.id, thread_id);
assert_eq!(thread.turns.len(), 1);
assert_eq!(thread.turns[0].user_input, "Hello from DB");
assert_eq!(
thread.turns[0].response,
Some("Restored response".to_string())
);
}
#[test]
fn test_restore_from_messages_empty() {
let mut thread = Thread::new(Uuid::new_v4());
// Add a turn first, then restore with empty vec
thread.start_turn("hello");
thread.complete_turn("hi");
assert_eq!(thread.turns.len(), 1);
thread.restore_from_messages(Vec::new());
// Should clear all turns and stay idle
assert!(thread.turns.is_empty());
assert_eq!(thread.state, ThreadState::Idle);
}
#[test]
fn test_restore_from_messages_only_assistant_messages() {
let mut thread = Thread::new(Uuid::new_v4());
// Only assistant messages (no user messages to anchor turns)
let messages = vec![
ChatMessage::assistant("I'm here"),
ChatMessage::assistant("Still here"),
];
thread.restore_from_messages(messages);
// Assistant-only messages have no user turn to attach to, so
// they should be skipped entirely.
assert!(thread.turns.is_empty());
}
#[test]
fn test_restore_from_messages_multiple_user_messages_in_a_row() {
let mut thread = Thread::new(Uuid::new_v4());
// Two user messages with no assistant response between them
let messages = vec![
ChatMessage::user("first"),
ChatMessage::user("second"),
ChatMessage::assistant("reply to second"),
];
thread.restore_from_messages(messages);
// First user message becomes a turn with no response,
// second user message pairs with the assistant response.
assert_eq!(thread.turns.len(), 2);
assert_eq!(thread.turns[0].user_input, "first");
assert!(thread.turns[0].response.is_none());
assert_eq!(thread.turns[1].user_input, "second");
assert_eq!(
thread.turns[1].response,
Some("reply to second".to_string())
);
}
#[test]
fn test_thread_switch() {
let mut session = Session::new("user-1");
let t1_id = session.create_thread().id;
let t2_id = session.create_thread().id;
// After creating two threads, active should be the last one
assert_eq!(session.active_thread, Some(t2_id));
// Switch back to the first
assert!(session.switch_thread(t1_id));
assert_eq!(session.active_thread, Some(t1_id));
// Switching to a nonexistent thread should fail
let fake_id = Uuid::new_v4();
assert!(!session.switch_thread(fake_id));
// Active thread should remain unchanged
assert_eq!(session.active_thread, Some(t1_id));
}
#[test]
fn test_get_or_create_thread_idempotent() {
let mut session = Session::new("user-1");
let tid1 = session.get_or_create_thread().id;
let tid2 = session.get_or_create_thread().id;
// Should return the same thread (not create a new one each time)
assert_eq!(tid1, tid2);
assert_eq!(session.threads.len(), 1);
}
#[test]
fn test_truncate_turns() {
let mut thread = Thread::new(Uuid::new_v4());
for i in 0..5 {
thread.start_turn(format!("msg-{}", i));
thread.complete_turn(format!("resp-{}", i));
}
assert_eq!(thread.turns.len(), 5);
thread.truncate_turns(3);
assert_eq!(thread.turns.len(), 3);
// Should keep the most recent turns
assert_eq!(thread.turns[0].user_input, "msg-2");
assert_eq!(thread.turns[1].user_input, "msg-3");
assert_eq!(thread.turns[2].user_input, "msg-4");
// Turn numbers should be re-indexed
assert_eq!(thread.turns[0].turn_number, 0);
assert_eq!(thread.turns[1].turn_number, 1);
assert_eq!(thread.turns[2].turn_number, 2);
}
#[test]
fn test_truncate_turns_noop_when_fewer() {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("only one");
thread.complete_turn("response");
thread.truncate_turns(10);
assert_eq!(thread.turns.len(), 1);
assert_eq!(thread.turns[0].user_input, "only one");
}
#[test]
fn test_thread_interrupt_and_resume() {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("do something");
assert_eq!(thread.state, ThreadState::Processing);
thread.interrupt();
assert_eq!(thread.state, ThreadState::Interrupted);
let last_turn = thread.last_turn().unwrap();
assert_eq!(last_turn.state, TurnState::Interrupted);
assert!(last_turn.completed_at.is_some());
thread.resume();
assert_eq!(thread.state, ThreadState::Idle);
}
#[test]
fn test_resume_only_from_interrupted() {
let mut thread = Thread::new(Uuid::new_v4());
// Idle thread: resume should be a no-op
assert_eq!(thread.state, ThreadState::Idle);
thread.resume();
assert_eq!(thread.state, ThreadState::Idle);
// Processing thread: resume should not change state
thread.start_turn("work");
assert_eq!(thread.state, ThreadState::Processing);
thread.resume();
assert_eq!(thread.state, ThreadState::Processing);
}
#[test]
fn test_turn_fail() {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("risky operation");
thread.fail_turn("connection timed out");
assert_eq!(thread.state, ThreadState::Idle);
let turn = thread.last_turn().unwrap();
assert_eq!(turn.state, TurnState::Failed);
assert_eq!(turn.error, Some("connection timed out".to_string()));
assert!(turn.response.is_none());
assert!(turn.completed_at.is_some());
}
#[test]
fn test_messages_with_incomplete_last_turn() {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("first");
thread.complete_turn("first reply");
thread.start_turn("second (in progress)");
let messages = thread.messages();
// Should have 3 messages: user, assistant, user (no assistant for in-progress)
assert_eq!(messages.len(), 3);
assert_eq!(messages[0].content, "first");
assert_eq!(messages[1].content, "first reply");
assert_eq!(messages[2].content, "second (in progress)");
}
#[test]
fn test_thread_serialization_round_trip() {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("hello");
thread.complete_turn("world");
thread.last_response_id = Some("resp_abc123".to_string());
let json = serde_json::to_string(&thread).unwrap();
let restored: Thread = serde_json::from_str(&json).unwrap();
assert_eq!(restored.id, thread.id);
assert_eq!(restored.session_id, thread.session_id);
assert_eq!(restored.turns.len(), 1);
assert_eq!(restored.turns[0].user_input, "hello");
assert_eq!(restored.turns[0].response, Some("world".to_string()));
assert_eq!(restored.last_response_id, Some("resp_abc123".to_string()));
}
#[test]
fn test_session_serialization_round_trip() {
let mut session = Session::new("user-ser");
session.create_thread();
session.auto_approve_tool("echo");
let json = serde_json::to_string(&session).unwrap();
let restored: Session = serde_json::from_str(&json).unwrap();
assert_eq!(restored.user_id, "user-ser");
assert_eq!(restored.threads.len(), 1);
assert!(restored.is_tool_auto_approved("echo"));
assert!(!restored.is_tool_auto_approved("shell"));
}
#[test]
fn test_auto_approved_tools() {
let mut session = Session::new("user-1");
assert!(!session.is_tool_auto_approved("shell"));
session.auto_approve_tool("shell");
assert!(session.is_tool_auto_approved("shell"));
// Idempotent
session.auto_approve_tool("shell");
assert_eq!(session.auto_approved_tools.len(), 1);
}
#[test]
fn test_turn_tool_call_error() {
let mut turn = Turn::new(0, "test");
turn.record_tool_call("http", serde_json::json!({"url": "example.com"}));
turn.record_tool_error("timeout");
assert_eq!(turn.tool_calls.len(), 1);
assert_eq!(turn.tool_calls[0].error, Some("timeout".to_string()));
assert!(turn.tool_calls[0].result.is_none());
}
#[test]
fn test_turn_number_increments() {
let mut thread = Thread::new(Uuid::new_v4());
// Before any turns, turn_number() is 1 (1-indexed for display)
assert_eq!(thread.turn_number(), 1);
thread.start_turn("first");
thread.complete_turn("done");
assert_eq!(thread.turn_number(), 2);
thread.start_turn("second");
assert_eq!(thread.turn_number(), 3);
}
#[test]
fn test_complete_turn_on_empty_thread() {
let mut thread = Thread::new(Uuid::new_v4());
// Completing a turn when there are no turns should be a safe no-op
thread.complete_turn("phantom response");
assert_eq!(thread.state, ThreadState::Idle);
assert!(thread.turns.is_empty());
}
#[test]
fn test_fail_turn_on_empty_thread() {
let mut thread = Thread::new(Uuid::new_v4());
// Failing a turn when there are no turns should be a safe no-op
thread.fail_turn("phantom error");
assert_eq!(thread.state, ThreadState::Idle);
assert!(thread.turns.is_empty());
}
#[test]
fn test_pending_approval_flow() {
let mut thread = Thread::new(Uuid::new_v4());
let approval = PendingApproval {
request_id: Uuid::new_v4(),
tool_name: "shell".to_string(),
parameters: serde_json::json!({"command": "rm -rf /"}),
description: "dangerous command".to_string(),
tool_call_id: "call_123".to_string(),
context_messages: vec![ChatMessage::user("do it")],
};
thread.await_approval(approval);
assert_eq!(thread.state, ThreadState::AwaitingApproval);
assert!(thread.pending_approval.is_some());
let taken = thread.take_pending_approval();
assert!(taken.is_some());
assert_eq!(taken.unwrap().tool_name, "shell");
assert!(thread.pending_approval.is_none());
}
#[test]
fn test_clear_pending_approval() {
let mut thread = Thread::new(Uuid::new_v4());
let approval = PendingApproval {
request_id: Uuid::new_v4(),
tool_name: "http".to_string(),
parameters: serde_json::json!({}),
description: "test".to_string(),
tool_call_id: "call_456".to_string(),
context_messages: vec![],
};
thread.await_approval(approval);
thread.clear_pending_approval();
assert_eq!(thread.state, ThreadState::Idle);
assert!(thread.pending_approval.is_none());
}
#[test]
fn test_active_thread_accessors() {
let mut session = Session::new("user-1");
assert!(session.active_thread().is_none());
assert!(session.active_thread_mut().is_none());
let tid = session.create_thread().id;
assert!(session.active_thread().is_some());
assert_eq!(session.active_thread().unwrap().id, tid);
// Mutably modify through accessor
session.active_thread_mut().unwrap().start_turn("test");
assert_eq!(
session.active_thread().unwrap().state,
ThreadState::Processing
);
}
}
+8 -436
View File
@@ -11,7 +11,6 @@ use uuid::Uuid;
use crate::agent::session::Session;
use crate::agent::undo::UndoManager;
use crate::hooks::HookRegistry;
/// Key for mapping external thread IDs to internal ones.
#[derive(Clone, Hash, Eq, PartialEq)]
@@ -26,7 +25,6 @@ pub struct SessionManager {
sessions: RwLock<HashMap<String, Arc<Mutex<Session>>>>,
thread_map: RwLock<HashMap<ThreadKey, Uuid>>,
undo_managers: RwLock<HashMap<Uuid, Arc<Mutex<UndoManager>>>>,
hooks: Option<Arc<HookRegistry>>,
}
impl SessionManager {
@@ -36,16 +34,9 @@ impl SessionManager {
sessions: RwLock::new(HashMap::new()),
thread_map: RwLock::new(HashMap::new()),
undo_managers: RwLock::new(HashMap::new()),
hooks: None,
}
}
/// Attach a hook registry for session lifecycle events.
pub fn with_hooks(mut self, hooks: Arc<HookRegistry>) -> Self {
self.hooks = Some(hooks);
self
}
/// Get or create a session for a user.
pub async fn get_or_create_session(&self, user_id: &str) -> Arc<Mutex<Session>> {
// Fast path: check if session exists
@@ -63,28 +54,8 @@ impl SessionManager {
return Arc::clone(session);
}
let new_session = Session::new(user_id);
let session_id = new_session.id.to_string();
let session = Arc::new(Mutex::new(new_session));
let session = Arc::new(Mutex::new(Session::new(user_id)));
sessions.insert(user_id.to_string(), Arc::clone(&session));
// Fire OnSessionStart hook (fire-and-forget)
if let Some(ref hooks) = self.hooks {
let hooks = hooks.clone();
let uid = user_id.to_string();
let sid = session_id;
tokio::spawn(async move {
use crate::hooks::HookEvent;
let event = HookEvent::SessionStart {
user_id: uid,
session_id: sid,
};
if let Err(e) = hooks.run(&event).await {
tracing::warn!("OnSessionStart hook error: {}", e);
}
});
}
session
}
@@ -139,41 +110,6 @@ impl SessionManager {
(session, thread_id)
}
/// Register a hydrated thread so subsequent `resolve_thread` calls find it.
///
/// Inserts into the thread_map and creates an undo manager for the thread.
pub async fn register_thread(
&self,
user_id: &str,
channel: &str,
thread_id: Uuid,
session: Arc<Mutex<Session>>,
) {
let key = ThreadKey {
user_id: user_id.to_string(),
channel: channel.to_string(),
external_thread_id: Some(thread_id.to_string()),
};
{
let mut thread_map = self.thread_map.write().await;
thread_map.insert(key, thread_id);
}
{
let mut undo_managers = self.undo_managers.write().await;
undo_managers
.entry(thread_id)
.or_insert_with(|| Arc::new(Mutex::new(UndoManager::new())));
}
// Ensure the session is tracked
{
let mut sessions = self.sessions.write().await;
sessions.entry(user_id.to_string()).or_insert(session);
}
}
/// Get undo manager for a thread.
pub async fn get_undo_manager(&self, thread_id: Uuid) -> Arc<Mutex<UndoManager>> {
// Fast path
@@ -202,8 +138,8 @@ impl SessionManager {
pub async fn prune_stale_sessions(&self, max_idle: std::time::Duration) -> usize {
let cutoff = chrono::Utc::now() - chrono::TimeDelta::seconds(max_idle.as_secs() as i64);
// Find stale sessions (user_id + session_id)
let stale_sessions: Vec<(String, String)> = {
// Find stale session user_ids
let stale_users: Vec<String> = {
let sessions = self.sessions.read().await;
sessions
.iter()
@@ -211,7 +147,7 @@ impl SessionManager {
// Try to lock; skip if contended (someone is actively using it)
let sess = session.try_lock().ok()?;
if sess.last_active_at < cutoff {
Some((user_id.clone(), sess.id.to_string()))
Some(user_id.clone())
} else {
None
}
@@ -219,11 +155,6 @@ impl SessionManager {
.collect()
};
let stale_users: Vec<String> = stale_sessions
.iter()
.map(|(user_id, _)| user_id.clone())
.collect();
if stale_users.is_empty() {
return 0;
}
@@ -233,30 +164,11 @@ impl SessionManager {
{
let sessions = self.sessions.read().await;
for user_id in &stale_users {
if let Some(session) = sessions.get(user_id)
&& let Ok(sess) = session.try_lock()
{
stale_thread_ids.extend(sess.threads.keys());
}
}
}
// Fire OnSessionEnd hooks for stale sessions (fire-and-forget)
if let Some(ref hooks) = self.hooks {
for (user_id, session_id) in &stale_sessions {
let hooks = hooks.clone();
let uid = user_id.clone();
let sid = session_id.clone();
tokio::spawn(async move {
use crate::hooks::HookEvent;
let event = HookEvent::SessionEnd {
user_id: uid,
session_id: sid,
};
if let Err(e) = hooks.run(&event).await {
tracing::warn!("OnSessionEnd hook error: {}", e);
if let Some(session) = sessions.get(user_id) {
if let Ok(sess) = session.try_lock() {
stale_thread_ids.extend(sess.threads.keys());
}
});
}
}
}
@@ -384,344 +296,4 @@ mod tests {
.await;
assert_eq!(pruned, 0);
}
#[tokio::test]
async fn test_register_thread() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let thread_id = Uuid::new_v4();
// Create a session with a hydrated thread
let session = Arc::new(Mutex::new(Session::new("user-hydrate")));
{
let mut sess = session.lock().await;
let thread = Thread::with_id(thread_id, sess.id);
sess.threads.insert(thread_id, thread);
sess.active_thread = Some(thread_id);
}
// Register the thread
manager
.register_thread("user-hydrate", "gateway", thread_id, Arc::clone(&session))
.await;
// resolve_thread should find it (using the UUID as external_thread_id)
let (resolved_session, resolved_tid) = manager
.resolve_thread("user-hydrate", "gateway", Some(&thread_id.to_string()))
.await;
assert_eq!(resolved_tid, thread_id);
// Should be the same session object
let sess = resolved_session.lock().await;
assert!(sess.threads.contains_key(&thread_id));
}
#[tokio::test]
async fn test_resolve_thread_with_explicit_external_id() {
let manager = SessionManager::new();
// Two calls with the same explicit external thread ID should resolve
// to the same internal thread.
let (_, t1) = manager
.resolve_thread("user-1", "gateway", Some("ext-abc"))
.await;
let (_, t2) = manager
.resolve_thread("user-1", "gateway", Some("ext-abc"))
.await;
assert_eq!(t1, t2);
// A different external ID on the same channel/user gets a new thread.
let (_, t3) = manager
.resolve_thread("user-1", "gateway", Some("ext-xyz"))
.await;
assert_ne!(t1, t3);
}
#[tokio::test]
async fn test_resolve_thread_none_vs_some_external_id() {
let manager = SessionManager::new();
// None external_thread_id is a distinct key from Some("ext-1").
let (_, t_none) = manager.resolve_thread("user-1", "cli", None).await;
let (_, t_some) = manager.resolve_thread("user-1", "cli", Some("ext-1")).await;
assert_ne!(t_none, t_some);
}
#[tokio::test]
async fn test_resolve_thread_different_users_isolated() {
let manager = SessionManager::new();
let (_, t1) = manager
.resolve_thread("user-a", "gateway", Some("same-ext"))
.await;
let (_, t2) = manager
.resolve_thread("user-b", "gateway", Some("same-ext"))
.await;
// Same channel + same external ID but different users = different threads
assert_ne!(t1, t2);
}
#[tokio::test]
async fn test_resolve_thread_different_channels_isolated() {
let manager = SessionManager::new();
let (_, t1) = manager
.resolve_thread("user-1", "gateway", Some("thread-x"))
.await;
let (_, t2) = manager
.resolve_thread("user-1", "telegram", Some("thread-x"))
.await;
// Same user + same external ID but different channels = different threads
assert_ne!(t1, t2);
}
#[tokio::test]
async fn test_resolve_thread_stale_mapping_creates_new_thread() {
let manager = SessionManager::new();
// Create a thread normally
let (session, original_tid) = manager
.resolve_thread("user-1", "gateway", Some("ext-1"))
.await;
// Simulate the thread being removed from the session (e.g. pruned)
{
let mut sess = session.lock().await;
sess.threads.remove(&original_tid);
}
// Next resolve should detect the stale mapping and create a fresh thread
let (_, new_tid) = manager
.resolve_thread("user-1", "gateway", Some("ext-1"))
.await;
assert_ne!(original_tid, new_tid);
// The new thread should actually exist in the session
let sess = session.lock().await;
assert!(sess.threads.contains_key(&new_tid));
}
#[tokio::test]
async fn test_register_thread_preserves_uuid_on_resolve() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let known_uuid = Uuid::new_v4();
let session = Arc::new(Mutex::new(Session::new("user-web")));
let session_id = {
let sess = session.lock().await;
sess.id
};
// Simulate hydration: create thread with a known UUID
{
let mut sess = session.lock().await;
let thread = Thread::with_id(known_uuid, session_id);
sess.threads.insert(known_uuid, thread);
}
// Register it
manager
.register_thread("user-web", "gateway", known_uuid, Arc::clone(&session))
.await;
// resolve_thread with UUID as external_thread_id MUST return the same UUID,
// not mint a new one (this was the root cause of the "wrong conversation" bug)
let (_, resolved) = manager
.resolve_thread("user-web", "gateway", Some(&known_uuid.to_string()))
.await;
assert_eq!(resolved, known_uuid);
}
#[tokio::test]
async fn test_register_thread_idempotent() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let tid = Uuid::new_v4();
let session = Arc::new(Mutex::new(Session::new("user-idem")));
{
let mut sess = session.lock().await;
let thread = Thread::with_id(tid, sess.id);
sess.threads.insert(tid, thread);
}
// Register twice
manager
.register_thread("user-idem", "gateway", tid, Arc::clone(&session))
.await;
manager
.register_thread("user-idem", "gateway", tid, Arc::clone(&session))
.await;
// Should still resolve to the same thread
let (_, resolved) = manager
.resolve_thread("user-idem", "gateway", Some(&tid.to_string()))
.await;
assert_eq!(resolved, tid);
}
#[tokio::test]
async fn test_register_thread_creates_undo_manager() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let tid = Uuid::new_v4();
let session = Arc::new(Mutex::new(Session::new("user-undo")));
{
let mut sess = session.lock().await;
let thread = Thread::with_id(tid, sess.id);
sess.threads.insert(tid, thread);
}
manager
.register_thread("user-undo", "gateway", tid, Arc::clone(&session))
.await;
// Undo manager should exist for the registered thread
let undo = manager.get_undo_manager(tid).await;
let undo2 = manager.get_undo_manager(tid).await;
assert!(Arc::ptr_eq(&undo, &undo2));
}
#[tokio::test]
async fn test_register_thread_stores_session() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let tid = Uuid::new_v4();
let session = Arc::new(Mutex::new(Session::new("user-new")));
{
let mut sess = session.lock().await;
let thread = Thread::with_id(tid, sess.id);
sess.threads.insert(tid, thread);
}
// The user has no session yet in the manager
{
let sessions = manager.sessions.read().await;
assert!(!sessions.contains_key("user-new"));
}
manager
.register_thread("user-new", "gateway", tid, Arc::clone(&session))
.await;
// Now the session should be tracked
{
let sessions = manager.sessions.read().await;
assert!(sessions.contains_key("user-new"));
}
}
#[tokio::test]
async fn test_multiple_threads_per_user() {
let manager = SessionManager::new();
let (_, t1) = manager
.resolve_thread("user-1", "gateway", Some("thread-a"))
.await;
let (_, t2) = manager
.resolve_thread("user-1", "gateway", Some("thread-b"))
.await;
let (session, t3) = manager
.resolve_thread("user-1", "gateway", Some("thread-c"))
.await;
// All three should be distinct
assert_ne!(t1, t2);
assert_ne!(t2, t3);
assert_ne!(t1, t3);
// All three should exist in the same session
let sess = session.lock().await;
assert!(sess.threads.contains_key(&t1));
assert!(sess.threads.contains_key(&t2));
assert!(sess.threads.contains_key(&t3));
}
#[tokio::test]
async fn test_prune_cleans_thread_map_and_undo_managers() {
let manager = SessionManager::new();
let (stale_session, stale_tid) = manager.resolve_thread("user-stale", "cli", None).await;
// Backdate the session
{
let mut sess = stale_session.lock().await;
sess.last_active_at = chrono::Utc::now() - chrono::TimeDelta::seconds(86400 * 30);
}
// Verify thread_map and undo_managers have entries
{
let tm = manager.thread_map.read().await;
assert!(!tm.is_empty());
}
{
let um = manager.undo_managers.read().await;
assert!(um.contains_key(&stale_tid));
}
let pruned = manager
.prune_stale_sessions(std::time::Duration::from_secs(86400 * 7))
.await;
assert_eq!(pruned, 1);
// Thread map and undo managers should be cleaned up
{
let tm = manager.thread_map.read().await;
assert!(tm.is_empty());
}
{
let um = manager.undo_managers.read().await;
assert!(!um.contains_key(&stale_tid));
}
}
#[tokio::test]
async fn test_resolve_thread_active_thread_set() {
let manager = SessionManager::new();
let (session, thread_id) = manager
.resolve_thread("user-1", "gateway", Some("ext-1"))
.await;
// The resolved thread should be set as the active thread
let sess = session.lock().await;
assert_eq!(sess.active_thread, Some(thread_id));
}
#[tokio::test]
async fn test_register_then_resolve_different_channel_creates_new() {
use crate::agent::session::{Session, Thread};
let manager = SessionManager::new();
let tid = Uuid::new_v4();
let session = Arc::new(Mutex::new(Session::new("user-cross")));
{
let mut sess = session.lock().await;
let thread = Thread::with_id(tid, sess.id);
sess.threads.insert(tid, thread);
}
// Register on "gateway" channel
manager
.register_thread("user-cross", "gateway", tid, Arc::clone(&session))
.await;
// Resolve on a different channel with the same UUID string should NOT
// find the registered thread (channel is part of the key)
let (_, resolved) = manager
.resolve_thread("user-cross", "telegram", Some(&tid.to_string()))
.await;
assert_ne!(resolved, tid);
}
}
+252 -220
View File
@@ -11,7 +11,16 @@ pub struct SubmissionParser;
impl SubmissionParser {
/// Parse message content into a Submission.
///
/// If `skill_commands` is provided (list of registered skill command names),
/// unrecognized `/foo` commands will be checked against it to enable
/// `/review <args>` style skill activation.
pub fn parse(content: &str) -> Submission {
Self::parse_with_skill_commands(content, &[])
}
/// Parse with awareness of registered skill slash commands.
pub fn parse_with_skill_commands(content: &str, skill_commands: &[String]) -> Submission {
let trimmed = content.trim();
let lower = trimmed.to_lowercase();
@@ -43,76 +52,39 @@ impl SubmissionParser {
if lower == "/thread new" || lower == "/new" {
return Submission::NewThread;
}
// System commands (bypass thread-state checks)
if lower == "/help" || lower == "/?" {
return Submission::SystemCommand {
command: "help".to_string(),
args: vec![],
};
}
if lower == "/version" {
return Submission::SystemCommand {
command: "version".to_string(),
args: vec![],
};
}
if lower == "/tools" {
return Submission::SystemCommand {
command: "tools".to_string(),
args: vec![],
};
}
if lower == "/ping" {
return Submission::SystemCommand {
command: "ping".to_string(),
args: vec![],
};
}
if lower == "/debug" {
return Submission::SystemCommand {
command: "debug".to_string(),
args: vec![],
};
}
if lower.starts_with("/model") {
let args: Vec<String> = trimmed
.split_whitespace()
.skip(1)
.map(|s| s.to_string())
.collect();
return Submission::SystemCommand {
command: "model".to_string(),
args,
};
}
if lower == "/quit" || lower == "/exit" || lower == "/shutdown" {
return Submission::Quit;
}
// /thread <uuid> - switch thread
if let Some(rest) = lower.strip_prefix("/thread ") {
let rest = rest.trim();
if rest != "new"
&& let Ok(id) = Uuid::parse_str(rest)
{
return Submission::SwitchThread { thread_id: id };
if rest != "new" {
if let Ok(id) = Uuid::parse_str(rest) {
return Submission::SwitchThread { thread_id: id };
}
}
}
// /resume <uuid> - resume from checkpoint
if let Some(rest) = lower.strip_prefix("/resume ")
&& let Ok(id) = Uuid::parse_str(rest.trim())
{
return Submission::Resume { checkpoint_id: id };
if let Some(rest) = lower.strip_prefix("/resume ") {
if let Ok(id) = Uuid::parse_str(rest.trim()) {
return Submission::Resume { checkpoint_id: id };
}
}
// Try structured JSON approval (from web gateway's /api/chat/approval endpoint)
if trimmed.starts_with('{')
&& let Ok(submission) = serde_json::from_str::<Submission>(trimmed)
&& matches!(submission, Submission::ExecApproval { .. })
{
return submission;
// Skill commands
if let Some(rest) = lower.strip_prefix("/skill ") {
let rest = rest.trim();
if let Some(submission) = Self::parse_skill_command(rest, trimmed) {
return submission;
}
}
// Check if this is a dynamic skill slash command (e.g. /review <args>)
if lower.starts_with('/') {
if let Some(submission) =
Self::parse_dynamic_skill_command(&lower, trimmed, skill_commands)
{
return submission;
}
}
// Approval responses (simple yes/no/always for pending approvals)
@@ -144,6 +116,110 @@ impl SubmissionParser {
content: content.to_string(),
}
}
/// Parse `/skill <subcommand>` forms.
fn parse_skill_command(rest: &str, _original: &str) -> Option<Submission> {
// /skill list
if rest == "list" {
return Some(Submission::SkillList);
}
// /skill deactivate
if rest == "deactivate" || rest == "off" {
return Some(Submission::SkillDeactivate);
}
// /skill load <url>
if let Some(url) = rest.strip_prefix("load ") {
let url = url.trim();
if !url.is_empty() {
return Some(Submission::SkillLoad {
url: url.to_string(),
});
}
}
// /skill remove <name>
if let Some(name) = rest.strip_prefix("remove ") {
let name = name.trim();
if !name.is_empty() {
return Some(Submission::SkillRemove {
name: name.to_string(),
});
}
}
// /skill info <name>
if let Some(name) = rest.strip_prefix("info ") {
let name = name.trim();
if !name.is_empty() {
return Some(Submission::SkillInfo {
name: name.to_string(),
});
}
}
// /skill activate <name> [args]
if let Some(rest) = rest.strip_prefix("activate ") {
let rest = rest.trim();
if !rest.is_empty() {
let (name, args) = split_first_word(rest);
return Some(Submission::SkillActivate {
name: name.to_string(),
args: args.map(|s| s.to_string()),
});
}
}
// /skill <name> [args] (shorthand for activate)
if !rest.is_empty() {
let (name, args) = split_first_word(rest);
return Some(Submission::SkillActivate {
name: name.to_string(),
args: args.map(|s| s.to_string()),
});
}
None
}
/// Check if a `/command args` matches a registered skill command.
fn parse_dynamic_skill_command(
lower: &str,
original: &str,
skill_commands: &[String],
) -> Option<Submission> {
// Extract the command word (without the leading /)
let without_slash = &lower[1..];
let (cmd, _) = split_first_word(without_slash);
if skill_commands.iter().any(|sc| sc == cmd) {
// Get args from the original (preserving case)
let original_without_slash = &original.trim()[1..];
let (_, args) = split_first_word(original_without_slash);
return Some(Submission::SkillActivateByCommand {
command: cmd.to_string(),
args: args.map(|s| s.to_string()),
});
}
None
}
}
/// Split a string into the first word and the rest.
fn split_first_word(s: &str) -> (&str, Option<&str>) {
match s.find(char::is_whitespace) {
Some(idx) => {
let rest = s[idx..].trim();
if rest.is_empty() {
(&s[..idx], None)
} else {
(&s[..idx], Some(rest))
}
}
None => (s, None),
}
}
/// A submission to the agent.
@@ -212,16 +288,44 @@ pub enum Submission {
/// Suggest next steps based on the current thread.
Suggest,
/// Quit the agent. Bypasses thread-state checks.
Quit,
/// Load a skill from a URL.
SkillLoad {
/// URL to load the skill manifest from.
url: String,
},
/// System command (help, model, version, tools, ping, debug).
/// Bypasses thread-state checks and safety validation.
SystemCommand {
/// The command name (e.g. "help", "model", "version").
/// Activate a skill by name.
SkillActivate {
/// Skill name.
name: String,
/// Optional arguments.
args: Option<String>,
},
/// Activate a skill via its registered slash command.
SkillActivateByCommand {
/// The slash command that matched.
command: String,
/// Arguments to the command.
args: Vec<String>,
/// Optional arguments.
args: Option<String>,
},
/// Deactivate the currently active skill.
SkillDeactivate,
/// List installed skills.
SkillList,
/// Remove an installed skill.
SkillRemove {
/// Skill name.
name: String,
},
/// Show info about an installed skill.
SkillInfo {
/// Skill name.
name: String,
},
}
@@ -289,7 +393,11 @@ impl Submission {
| Self::Heartbeat
| Self::Summarize
| Self::Suggest
| Self::SystemCommand { .. }
| Self::SkillLoad { .. }
| Self::SkillDeactivate
| Self::SkillList
| Self::SkillRemove { .. }
| Self::SkillInfo { .. }
)
}
}
@@ -476,173 +584,97 @@ mod tests {
}
#[test]
fn test_parser_json_exec_approval() {
let req_id = Uuid::new_v4();
let json = serde_json::to_string(&Submission::ExecApproval {
request_id: req_id,
approved: true,
always: false,
})
.expect("serialize");
fn test_parser_skill_list() {
let submission = SubmissionParser::parse("/skill list");
assert!(matches!(submission, Submission::SkillList));
}
let submission = SubmissionParser::parse(&json);
#[test]
fn test_parser_skill_load() {
let submission = SubmissionParser::parse(
"/skill load https://github.com/alice/skills/blob/main/review.toml",
);
assert!(matches!(submission, Submission::SkillLoad { url } if url.contains("github.com")));
}
#[test]
fn test_parser_skill_activate() {
let submission = SubmissionParser::parse("/skill activate pr-review");
assert!(
matches!(submission, Submission::ExecApproval { request_id, approved, always }
if request_id == req_id && approved && !always)
matches!(submission, Submission::SkillActivate { name, args } if name == "pr-review" && args.is_none())
);
}
#[test]
fn test_parser_json_exec_approval_always() {
let req_id = Uuid::new_v4();
let json = serde_json::to_string(&Submission::ExecApproval {
request_id: req_id,
approved: true,
always: true,
})
.expect("serialize");
let submission = SubmissionParser::parse(&json);
fn test_parser_skill_activate_with_args() {
let submission = SubmissionParser::parse(
"/skill activate pr-review https://github.com/org/repo/pull/123",
);
assert!(
matches!(submission, Submission::ExecApproval { request_id, approved, always }
if request_id == req_id && approved && always)
matches!(submission, Submission::SkillActivate { name, args } if name == "pr-review" && args.is_some())
);
}
#[test]
fn test_parser_json_exec_approval_deny() {
let req_id = Uuid::new_v4();
let json = serde_json::to_string(&Submission::ExecApproval {
request_id: req_id,
approved: false,
always: false,
})
.expect("serialize");
let submission = SubmissionParser::parse(&json);
fn test_parser_skill_shorthand() {
// /skill <name> is shorthand for /skill activate <name>
let submission = SubmissionParser::parse("/skill pr-review");
assert!(
matches!(submission, Submission::ExecApproval { request_id, approved, always }
if request_id == req_id && !approved && !always)
matches!(submission, Submission::SkillActivate { name, .. } if name == "pr-review")
);
}
#[test]
fn test_parser_json_non_approval_stays_user_input() {
// A JSON UserInput should NOT be intercepted, it should be treated as text
let json = r#"{"UserInput":{"content":"hello"}}"#;
let submission = SubmissionParser::parse(json);
fn test_parser_skill_deactivate() {
let submission = SubmissionParser::parse("/skill deactivate");
assert!(matches!(submission, Submission::SkillDeactivate));
let submission = SubmissionParser::parse("/skill off");
assert!(matches!(submission, Submission::SkillDeactivate));
}
#[test]
fn test_parser_skill_remove() {
let submission = SubmissionParser::parse("/skill remove pr-review");
assert!(matches!(submission, Submission::SkillRemove { name } if name == "pr-review"));
}
#[test]
fn test_parser_skill_info() {
let submission = SubmissionParser::parse("/skill info pr-review");
assert!(matches!(submission, Submission::SkillInfo { name } if name == "pr-review"));
}
#[test]
fn test_parser_dynamic_skill_command() {
let skill_commands = vec!["review".to_string(), "debug".to_string()];
let submission = SubmissionParser::parse_with_skill_commands(
"/review https://github.com/org/repo/pull/123",
&skill_commands,
);
assert!(matches!(
submission,
Submission::SkillActivateByCommand { command, args }
if command == "review" && args.as_deref() == Some("https://github.com/org/repo/pull/123")
));
}
#[test]
fn test_parser_dynamic_skill_command_no_args() {
let skill_commands = vec!["debug".to_string()];
let submission = SubmissionParser::parse_with_skill_commands("/debug", &skill_commands);
assert!(matches!(
submission,
Submission::SkillActivateByCommand { command, args }
if command == "debug" && args.is_none()
));
}
#[test]
fn test_parser_unknown_slash_not_skill() {
let skill_commands = vec!["review".to_string()];
// /unknown is not a skill command, becomes user input
let submission = SubmissionParser::parse_with_skill_commands("/unknown", &skill_commands);
assert!(matches!(submission, Submission::UserInput { .. }));
}
#[test]
fn test_parser_json_roundtrip_matches_approval_handler() {
// Simulate exactly what chat_approval_handler does: serialize a Submission::ExecApproval
// and verify the parser picks it up correctly.
let request_id = Uuid::new_v4();
let approval = Submission::ExecApproval {
request_id,
approved: true,
always: false,
};
let json = serde_json::to_string(&approval).expect("serialize");
eprintln!("Serialized approval JSON: {}", json);
let parsed = SubmissionParser::parse(&json);
assert!(
matches!(parsed, Submission::ExecApproval { request_id: rid, approved, always }
if rid == request_id && approved && !always),
"Expected ExecApproval, got {:?}",
parsed
);
}
#[test]
fn test_parser_system_command_help() {
let submission = SubmissionParser::parse("/help");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "help" && args.is_empty())
);
let submission = SubmissionParser::parse("/?");
assert!(
matches!(submission, Submission::SystemCommand { command, .. } if command == "help")
);
let submission = SubmissionParser::parse("/HELP");
assert!(
matches!(submission, Submission::SystemCommand { command, .. } if command == "help")
);
}
#[test]
fn test_parser_system_command_model() {
// No args: show current model
let submission = SubmissionParser::parse("/model");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "model" && args.is_empty())
);
// With args: switch model
let submission = SubmissionParser::parse("/model gpt-4o");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "model" && args == vec!["gpt-4o"])
);
// Case insensitive command, preserves arg case
let submission = SubmissionParser::parse("/MODEL Claude-3.5");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "model" && args == vec!["Claude-3.5"])
);
}
#[test]
fn test_parser_system_command_version() {
let submission = SubmissionParser::parse("/version");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "version" && args.is_empty())
);
}
#[test]
fn test_parser_system_command_tools() {
let submission = SubmissionParser::parse("/tools");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "tools" && args.is_empty())
);
}
#[test]
fn test_parser_system_command_ping() {
let submission = SubmissionParser::parse("/ping");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "ping" && args.is_empty())
);
}
#[test]
fn test_parser_system_command_debug() {
let submission = SubmissionParser::parse("/debug");
assert!(
matches!(submission, Submission::SystemCommand { command, args } if command == "debug" && args.is_empty())
);
}
#[test]
fn test_parser_system_command_is_control() {
let submission = SubmissionParser::parse("/help");
assert!(submission.is_control());
assert!(!submission.starts_turn());
}
#[test]
fn test_parser_quit() {
assert!(matches!(SubmissionParser::parse("/quit"), Submission::Quit));
assert!(matches!(SubmissionParser::parse("/exit"), Submission::Quit));
assert!(matches!(
SubmissionParser::parse("/shutdown"),
Submission::Quit
));
assert!(matches!(SubmissionParser::parse("/QUIT"), Submission::Quit));
assert!(matches!(SubmissionParser::parse("/Exit"), Submission::Quit));
}
}
+16 -136
View File
@@ -43,10 +43,6 @@ impl Checkpoint {
}
/// Manager for undo/redo functionality.
///
/// Each undo/redo operation pops from one stack and pushes the current state
/// onto the other, so `undo_count() + redo_count()` stays constant across
/// undo/redo cycles (only `checkpoint()` and `clear()` change the total).
pub struct UndoManager {
/// Stack of past checkpoints (for undo).
undo_stack: VecDeque<Checkpoint>,
@@ -72,14 +68,6 @@ impl UndoManager {
self
}
/// Push a checkpoint onto the undo stack, trimming oldest entries if over limit.
fn push_undo(&mut self, checkpoint: Checkpoint) {
self.undo_stack.push_back(checkpoint);
while self.undo_stack.len() > self.max_checkpoints {
self.undo_stack.pop_front();
}
}
/// Create a checkpoint at the current state.
///
/// This clears the redo stack since we're creating a new history branch.
@@ -92,23 +80,24 @@ impl UndoManager {
// Clear redo stack (new branch of history)
self.redo_stack.clear();
// Create and push checkpoint
let checkpoint = Checkpoint::new(turn_number, messages, description);
self.push_undo(checkpoint);
self.undo_stack.push_back(checkpoint);
// Trim if over limit
while self.undo_stack.len() > self.max_checkpoints {
self.undo_stack.pop_front();
}
}
/// Undo: pop the last checkpoint and return it.
///
/// Saves the current state to the redo stack and pops the most recent
/// checkpoint from the undo stack so that repeated undos walk backwards
/// through history.
///
/// Takes ownership of `current_messages`; callers must clone first if
/// they need to retain a copy.
/// The current state should be saved to redo stack before calling this.
pub fn undo(
&mut self,
current_turn: usize,
current_messages: Vec<ChatMessage>,
) -> Option<Checkpoint> {
) -> Option<&Checkpoint> {
if self.undo_stack.is_empty() {
return None;
}
@@ -121,8 +110,9 @@ impl UndoManager {
);
self.redo_stack.push(current);
// Pop and return the most recent checkpoint
self.undo_stack.pop_back()
// Return the most recent checkpoint without removing it
// (we keep it so multiple undos can work)
self.undo_stack.back()
}
/// Pop the last checkpoint from the undo stack.
@@ -131,29 +121,7 @@ impl UndoManager {
}
/// Redo: restore a previously undone state.
///
/// Saves the current state to the undo stack and pops the most recent
/// checkpoint from the redo stack.
///
/// Takes ownership of `current_messages`; callers must clone first if
/// they need to retain a copy.
pub fn redo(
&mut self,
current_turn: usize,
current_messages: Vec<ChatMessage>,
) -> Option<Checkpoint> {
if self.redo_stack.is_empty() {
return None;
}
// Save current state to undo stack
let current = Checkpoint::new(
current_turn,
current_messages,
format!("Turn {}", current_turn),
);
self.push_undo(current);
pub fn redo(&mut self) -> Option<Checkpoint> {
self.redo_stack.pop()
}
@@ -246,16 +214,14 @@ mod tests {
assert!(manager.can_undo());
assert!(!manager.can_redo());
// Undo - returns owned Checkpoint now
// Undo
let current = vec![ChatMessage::user("Hello"), ChatMessage::assistant("Hi")];
let checkpoint = manager.undo(2, current);
assert!(checkpoint.is_some());
let checkpoint = checkpoint.unwrap();
assert_eq!(checkpoint.turn_number, 1);
assert!(manager.can_redo());
// Redo - now requires current state parameters
let restored = manager.redo(checkpoint.turn_number, checkpoint.messages);
// Redo
let restored = manager.redo();
assert!(restored.is_some());
}
@@ -283,90 +249,4 @@ mod tests {
assert!(restored.is_some());
assert_eq!(manager.undo_count(), 0);
}
#[test]
fn test_repeated_undo_advances_through_stack() {
let mut manager = UndoManager::new();
// Create 3 checkpoints at turns 0, 1, 2
manager.checkpoint(0, vec![], "Turn 0");
manager.checkpoint(1, vec![ChatMessage::user("msg1")], "Turn 1");
manager.checkpoint(2, vec![ChatMessage::user("msg2")], "Turn 2");
assert_eq!(manager.undo_count(), 3);
// First undo: should return turn 2 checkpoint, stack shrinks to 2
let cp1 = manager
.undo(3, vec![ChatMessage::user("msg3")])
.expect("first undo should succeed");
assert_eq!(cp1.turn_number, 2);
assert_eq!(manager.undo_count(), 2);
// Second undo: should return turn 1 checkpoint (different!), stack shrinks to 1
let cp2 = manager
.undo(cp1.turn_number, cp1.messages)
.expect("second undo should succeed");
assert_eq!(cp2.turn_number, 1);
assert_eq!(manager.undo_count(), 1);
// Verify we walked backwards through distinct checkpoints
assert_ne!(cp1.turn_number, cp2.turn_number);
}
#[test]
fn test_undo_redo_cycle_preserves_state() {
let mut manager = UndoManager::new();
let msgs_t0: Vec<ChatMessage> = vec![];
let msgs_t1 = vec![ChatMessage::user("hello")];
let msgs_t2 = vec![ChatMessage::user("hello"), ChatMessage::assistant("hi")];
manager.checkpoint(0, msgs_t0, "Turn 0");
manager.checkpoint(1, msgs_t1, "Turn 1");
// Undo from turn 2 -> get turn 1 checkpoint
let cp_undo1 = manager
.undo(2, msgs_t2.clone())
.expect("undo should succeed");
assert_eq!(cp_undo1.turn_number, 1);
// Redo from turn 1 -> get turn 2 state back
let cp_redo = manager
.redo(cp_undo1.turn_number, cp_undo1.messages)
.expect("redo should succeed");
assert_eq!(cp_redo.turn_number, 2);
assert_eq!(cp_redo.messages.len(), 2);
// Undo again from turn 2 -> should go back to turn 1 again
let cp_undo2 = manager
.undo(cp_redo.turn_number, cp_redo.messages)
.expect("second undo should succeed");
assert_eq!(cp_undo2.turn_number, 1);
}
#[test]
fn test_undo_redo_stack_sizes_consistent() {
let mut manager = UndoManager::new();
manager.checkpoint(0, vec![], "Turn 0");
manager.checkpoint(1, vec![ChatMessage::user("a")], "Turn 1");
manager.checkpoint(2, vec![ChatMessage::user("b")], "Turn 2");
// Start: undo=3, redo=0, total=3
let total = manager.undo_count() + manager.redo_count();
assert_eq!(total, 3);
// After undo: total should still be 3 (one moved from undo to redo,
// plus the current state pushed to redo)
// Actually: undo pops one (3->2), pushes current to redo (0->1), total=3
let cp = manager.undo(3, vec![]).unwrap();
assert_eq!(manager.undo_count() + manager.redo_count(), 3);
// After redo: redo pops one (1->0), pushes current to undo (2->3), total=3
let cp2 = manager.redo(cp.turn_number, cp.messages).unwrap();
assert_eq!(manager.undo_count() + manager.redo_count(), 3);
// After another undo: same invariant
let _cp3 = manager.undo(cp2.turn_number, cp2.messages).unwrap();
assert_eq!(manager.undo_count() + manager.redo_count(), 3);
}
}
+76 -222
View File
@@ -10,9 +10,8 @@ use uuid::Uuid;
use crate::agent::scheduler::WorkerMessage;
use crate::agent::task::TaskOutput;
use crate::context::{ContextManager, JobState};
use crate::db::Database;
use crate::error::Error;
use crate::hooks::HookRegistry;
use crate::history::Store;
use crate::llm::{
ActionPlan, ChatMessage, LlmProvider, Reasoning, ReasoningContext, RespondResult, ToolSelection,
};
@@ -29,8 +28,7 @@ pub struct WorkerDeps {
pub llm: Arc<dyn LlmProvider>,
pub safety: Arc<SafetyLayer>,
pub tools: Arc<ToolRegistry>,
pub store: Option<Arc<dyn Database>>,
pub hooks: Arc<HookRegistry>,
pub store: Option<Arc<Store>>,
pub timeout: Duration,
pub use_planning: bool,
}
@@ -69,7 +67,7 @@ impl Worker {
&self.deps.tools
}
fn store(&self) -> Option<&Arc<dyn Database>> {
fn store(&self) -> Option<&Arc<Store>> {
self.deps.store.as_ref()
}
@@ -229,11 +227,11 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
}
// Check for cancellation
if let Ok(ctx) = self.context_manager().get_context(self.job_id).await
&& ctx.state == JobState::Cancelled
{
tracing::info!("Worker for job {} detected cancellation", self.job_id);
return Ok(());
if let Ok(ctx) = self.context_manager().get_context(self.job_id).await {
if ctx.state == JobState::Cancelled {
tracing::info!("Worker for job {} detected cancellation", self.job_id);
return Ok(());
}
}
iteration += 1;
@@ -250,15 +248,16 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
if selections.is_empty() {
// No tools from select_tools, ask LLM directly (may still return tool calls)
let respond_output = reasoning.respond_with_tools(reason_ctx).await?;
let respond_result = reasoning.respond_with_tools(reason_ctx).await?;
match respond_output.result {
match respond_result {
RespondResult::Text(response) => {
// Check for explicit completion phrases. Use word-boundary
// aware checks to avoid false positives like "incomplete",
// "not done", or "unfinished". Only the LLM's own response
// (not tool output) can trigger this.
if crate::util::llm_signals_completion(&response) {
// Check for completion keywords
let response_lower = response.to_lowercase();
if response_lower.contains("complete")
|| response_lower.contains("finished")
|| response_lower.contains("done")
{
self.mark_completed().await?;
return Ok(());
}
@@ -273,10 +272,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
));
}
}
RespondResult::ToolCalls {
tool_calls,
content,
} => {
RespondResult::ToolCalls(tool_calls) => {
// Model returned tool calls - execute them
tracing::debug!(
"Job {} respond_with_tools returned {} tool calls",
@@ -284,14 +280,6 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
tool_calls.len()
);
// Add assistant message with tool_calls (OpenAI protocol)
reason_ctx
.messages
.push(ChatMessage::assistant_with_tool_calls(
content,
tool_calls.clone(),
));
for tc in tool_calls {
let result = self.execute_tool(&tc.name, &tc.arguments).await;
@@ -301,7 +289,6 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
parameters: tc.arguments.clone(),
reasoning: String::new(),
alternatives: vec![],
tool_call_id: tc.id.clone(),
};
self.process_tool_result(reason_ctx, &selection, result)
@@ -354,11 +341,23 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
.map(|selection| {
let tool_name = selection.tool_name.clone();
let params = selection.parameters.clone();
let deps = self.deps.clone();
let tools = self.tools().clone();
let context_manager = self.context_manager().clone();
let safety = self.safety().clone();
let job_id = self.job_id;
let store = self.deps.store.clone();
async move {
let result = Self::execute_tool_inner(&deps, job_id, &tool_name, &params).await;
let result = Self::execute_tool_inner(
tools,
context_manager,
safety,
store,
job_id,
&tool_name,
&params,
)
.await;
ToolExecResult { result }
}
})
@@ -369,18 +368,20 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
/// Inner tool execution logic that can be called from both single and parallel paths.
async fn execute_tool_inner(
deps: &WorkerDeps,
tools: Arc<ToolRegistry>,
context_manager: Arc<ContextManager>,
safety: Arc<SafetyLayer>,
store: Option<Arc<Store>>,
job_id: Uuid,
tool_name: &str,
params: &serde_json::Value,
) -> Result<String, Error> {
let tool =
deps.tools
.get(tool_name)
.await
.ok_or_else(|| crate::error::ToolError::NotFound {
name: tool_name.to_string(),
})?;
let tool = tools
.get(tool_name)
.await
.ok_or_else(|| crate::error::ToolError::NotFound {
name: tool_name.to_string(),
})?;
// Tools requiring approval are blocked in autonomous jobs
if tool.requires_approval() {
@@ -390,46 +391,8 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
.into());
}
// Fetch job context early so we have the real user_id for hooks
let job_ctx = deps.context_manager.get_context(job_id).await?;
// Run BeforeToolCall hook
let params = {
use crate::hooks::{HookError, HookEvent, HookOutcome};
let event = HookEvent::ToolCall {
tool_name: tool_name.to_string(),
parameters: params.clone(),
user_id: job_ctx.user_id.clone(),
context: format!("job:{}", job_id),
};
match deps.hooks.run(&event).await {
Err(HookError::Rejected { reason }) => {
return Err(crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
reason: format!("Blocked by hook: {}", reason),
}
.into());
}
Err(err) => {
return Err(crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
reason: format!("Blocked by hook failure mode: {}", err),
}
.into());
}
Ok(HookOutcome::Continue {
modified: Some(new_params),
}) => serde_json::from_str(&new_params).unwrap_or_else(|e| {
tracing::warn!(
tool = %tool_name,
"Hook returned non-JSON modification for ToolCall, ignoring: {}",
e
);
params.clone()
}),
_ => params.clone(),
}
};
// Get job context for the tool
let job_ctx = context_manager.get_context(job_id).await?;
if job_ctx.state == JobState::Cancelled {
return Err(crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
@@ -439,7 +402,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
}
// Validate tool parameters
let validation = deps.safety.validator().validate_tool_params(&params);
let validation = safety.validator().validate_tool_params(params);
if !validation.is_valid {
let details = validation
.errors
@@ -454,58 +417,21 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
.into());
}
tracing::debug!(
tool = %tool_name,
params = %params,
job = %job_id,
"Tool call started"
);
// Execute with per-tool timeout and timing
let tool_timeout = tool.execution_timeout();
// Execute with timeout and timing
let start = std::time::Instant::now();
let result = tokio::time::timeout(tool_timeout, async {
let result = tokio::time::timeout(Duration::from_secs(60), async {
tool.execute(params.clone(), &job_ctx).await
})
.await;
let elapsed = start.elapsed();
match &result {
Ok(Ok(output)) => {
let result_str = serde_json::to_string(&output.result)
.unwrap_or_else(|_| "<serialize error>".to_string());
tracing::debug!(
tool = %tool_name,
elapsed_ms = elapsed.as_millis() as u64,
result = %result_str,
"Tool call succeeded"
);
}
Ok(Err(e)) => {
tracing::debug!(
tool = %tool_name,
elapsed_ms = elapsed.as_millis() as u64,
error = %e,
"Tool call failed"
);
}
Err(_) => {
tracing::debug!(
tool = %tool_name,
elapsed_ms = elapsed.as_millis() as u64,
timeout_secs = tool_timeout.as_secs(),
"Tool call timed out"
);
}
}
// Record action in memory and get the ActionRecord for persistence
let action = match &result {
Ok(Ok(output)) => {
let output_str = serde_json::to_string_pretty(&output.result)
.ok()
.map(|s| deps.safety.sanitize_tool_output(tool_name, &s).content);
deps.context_manager
.map(|s| safety.sanitize_tool_output(tool_name, &s).content);
context_manager
.update_memory(job_id, |mem| {
let rec = mem.create_action(tool_name, params.clone()).succeed(
output_str.clone(),
@@ -518,8 +444,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
.await
.ok()
}
Ok(Err(e)) => deps
.context_manager
Ok(Err(e)) => context_manager
.update_memory(job_id, |mem| {
let rec = mem
.create_action(tool_name, params.clone())
@@ -529,8 +454,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
})
.await
.ok(),
Err(_) => deps
.context_manager
Err(_) => context_manager
.update_memory(job_id, |mem| {
let rec = mem
.create_action(tool_name, params.clone())
@@ -543,7 +467,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
};
// Persist action to database (fire-and-forget)
if let (Some(action), Some(store)) = (action, deps.store.clone()) {
if let (Some(action), Some(store)) = (action, store) {
tokio::spawn(async move {
if let Err(e) = store.save_action(job_id, &action).await {
tracing::warn!("Failed to persist action for job {}: {}", job_id, e);
@@ -555,7 +479,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
let output = result
.map_err(|_| crate::error::ToolError::Timeout {
name: tool_name.to_string(),
timeout: tool_timeout,
timeout: Duration::from_secs(60),
})?
.map_err(|e| crate::error::ToolError::ExecutionFailed {
name: tool_name.to_string(),
@@ -594,14 +518,17 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
);
reason_ctx.messages.push(ChatMessage::tool_result(
&selection.tool_call_id,
"tool_call_id",
&selection.tool_name,
wrapped,
));
// Tool output never drives job completion. A malicious tool could
// emit "TASK_COMPLETE" to force premature completion. Only the LLM's
// own structured response (in execution_loop) can mark a job done.
// Check if job is complete
if output.contains("TASK_COMPLETE") || output.contains("JOB_DONE") {
self.mark_completed().await?;
return Ok(true);
}
Ok(false)
}
Err(e) => {
@@ -626,7 +553,7 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
}
reason_ctx.messages.push(ChatMessage::tool_result(
&selection.tool_call_id,
"tool_call_id",
&selection.tool_name,
format!("Error: {}", e),
));
@@ -676,15 +603,12 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
.execute_tool(&action.tool_name, &action.parameters)
.await;
// Create a synthetic ToolSelection for process_tool_result.
// Plan actions don't originate from an LLM tool_call response so
// there is no real tool_call_id; generate a unique one.
// Create a synthetic ToolSelection for process_tool_result
let selection = ToolSelection {
tool_name: action.tool_name.clone(),
parameters: action.parameters.clone(),
reasoning: action.reasoning.clone(),
alternatives: vec![],
tool_call_id: format!("plan_{}_{}", self.job_id, i),
};
// Process the result
@@ -708,7 +632,11 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
let response = reasoning.respond(reason_ctx).await?;
reason_ctx.messages.push(ChatMessage::assistant(&response));
if crate::util::llm_signals_completion(&response) {
let response_lower = response.to_lowercase();
if response_lower.contains("complete")
|| response_lower.contains("finished")
|| response_lower.contains("done")
{
self.mark_completed().await?;
} else {
// Job not complete, could re-plan or fall back to direct selection
@@ -729,7 +657,16 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
tool_name: &str,
params: &serde_json::Value,
) -> Result<String, Error> {
Self::execute_tool_inner(&self.deps, self.job_id, tool_name, params).await
Self::execute_tool_inner(
self.tools().clone(),
self.context_manager().clone(),
self.safety().clone(),
self.deps.store.clone(),
self.job_id,
tool_name,
params,
)
.await
}
async fn mark_completed(&self) -> Result<(), Error> {
@@ -794,86 +731,3 @@ impl From<TaskOutput> for Result<String, Error> {
})
}
}
#[cfg(test)]
mod tests {
use crate::llm::ToolSelection;
use crate::util::llm_signals_completion;
#[test]
fn test_tool_selection_preserves_call_id() {
let selection = ToolSelection {
tool_name: "memory_search".to_string(),
parameters: serde_json::json!({"query": "test"}),
reasoning: "Need to search memory".to_string(),
alternatives: vec![],
tool_call_id: "call_abc123".to_string(),
};
assert_eq!(selection.tool_call_id, "call_abc123");
assert_ne!(
selection.tool_call_id, "tool_call_id",
"tool_call_id must not be the hardcoded placeholder string"
);
}
#[test]
fn test_completion_positive_signals() {
assert!(llm_signals_completion("The job is complete."));
assert!(llm_signals_completion(
"I have completed the task successfully."
));
assert!(llm_signals_completion("The task is done."));
assert!(llm_signals_completion("The task is finished."));
assert!(llm_signals_completion(
"All steps are complete and verified."
));
assert!(llm_signals_completion(
"I've done all the work. The work is done."
));
assert!(llm_signals_completion(
"Successfully completed the migration."
));
}
#[test]
fn test_completion_negative_signals_block_false_positives() {
// These contain completion keywords but also negation, should NOT trigger.
assert!(!llm_signals_completion("The task is not complete yet."));
assert!(!llm_signals_completion("This is not done."));
assert!(!llm_signals_completion("The work is incomplete."));
assert!(!llm_signals_completion(
"The migration is not yet finished."
));
assert!(!llm_signals_completion("The job isn't done yet."));
assert!(!llm_signals_completion("This remains unfinished."));
}
#[test]
fn test_completion_does_not_match_bare_substrings() {
// Bare words embedded in other text should NOT trigger completion.
assert!(!llm_signals_completion(
"I need to complete more work first."
));
assert!(!llm_signals_completion(
"Let me finish the remaining steps."
));
assert!(!llm_signals_completion(
"I'm done analyzing, now let me fix it."
));
assert!(!llm_signals_completion(
"I completed step 1 but step 2 remains."
));
}
#[test]
fn test_completion_tool_output_injection() {
// A malicious tool output echoed by the LLM should not trigger
// completion unless it forms a genuine completion phrase.
assert!(!llm_signals_completion("TASK_COMPLETE"));
assert!(!llm_signals_completion("JOB_DONE"));
assert!(!llm_signals_completion(
"The tool returned: TASK_COMPLETE signal"
));
}
}
-208
View File
@@ -1,208 +0,0 @@
//! Boot screen displayed after all initialization completes.
//!
//! Shows a polished ANSI-styled status panel summarizing the agent's runtime
//! state: model, database, tool count, enabled features, active channels,
//! and the gateway URL.
/// All displayable fields for the boot screen.
pub struct BootInfo {
pub version: String,
pub agent_name: String,
pub llm_backend: String,
pub llm_model: String,
pub cheap_model: Option<String>,
pub db_backend: String,
pub db_connected: bool,
pub tool_count: usize,
pub gateway_url: Option<String>,
pub embeddings_enabled: bool,
pub embeddings_provider: Option<String>,
pub heartbeat_enabled: bool,
pub heartbeat_interval_secs: u64,
pub sandbox_enabled: bool,
pub claude_code_enabled: bool,
pub routines_enabled: bool,
pub channels: Vec<String>,
}
/// Print the boot screen to stdout.
pub fn print_boot_screen(info: &BootInfo) {
// ANSI codes matching existing REPL palette
let bold = "\x1b[1m";
let cyan = "\x1b[36m";
let dim = "\x1b[90m";
let yellow_underline = "\x1b[33;4m";
let reset = "\x1b[0m";
let border = format!(" {dim}{}{reset}", "\u{2576}".repeat(58));
println!();
println!("{border}");
println!();
println!(" {bold}{}{reset} v{}", info.agent_name, info.version);
println!();
// Model line
let model_display = if let Some(ref cheap) = info.cheap_model {
format!(
"{cyan}{}{reset} {dim}cheap{reset} {cyan}{}{reset}",
info.llm_model, cheap
)
} else {
format!("{cyan}{}{reset}", info.llm_model)
};
println!(
" {dim}model{reset} {model_display} {dim}via {}{reset}",
info.llm_backend
);
// Database line
let db_status = if info.db_connected {
"connected"
} else {
"none"
};
println!(
" {dim}database{reset} {cyan}{}{reset} {dim}({db_status}){reset}",
info.db_backend
);
// Tools line
println!(
" {dim}tools{reset} {cyan}{}{reset} {dim}registered{reset}",
info.tool_count
);
// Features line
let mut features = Vec::new();
if info.embeddings_enabled {
if let Some(ref provider) = info.embeddings_provider {
features.push(format!("embeddings ({provider})"));
} else {
features.push("embeddings".to_string());
}
}
if info.heartbeat_enabled {
let mins = info.heartbeat_interval_secs / 60;
features.push(format!("heartbeat ({mins}m)"));
}
if info.sandbox_enabled {
features.push("sandbox".to_string());
}
if info.claude_code_enabled {
features.push("claude-code".to_string());
}
if info.routines_enabled {
features.push("routines".to_string());
}
if !features.is_empty() {
println!(
" {dim}features{reset} {cyan}{}{reset}",
features.join(" ")
);
}
// Channels line
if !info.channels.is_empty() {
println!(
" {dim}channels{reset} {cyan}{}{reset}",
info.channels.join(" ")
);
}
// Gateway URL (highlighted)
if let Some(ref url) = info.gateway_url {
println!();
println!(" {dim}gateway{reset} {yellow_underline}{url}{reset}");
}
println!();
println!("{border}");
println!();
println!(" /help for commands, /quit to exit");
println!();
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_print_boot_screen_full() {
let info = BootInfo {
version: "0.2.0".to_string(),
agent_name: "ironclaw".to_string(),
llm_backend: "nearai".to_string(),
llm_model: "claude-3-5-sonnet-20241022".to_string(),
cheap_model: Some("gpt-4o-mini".to_string()),
db_backend: "libsql".to_string(),
db_connected: true,
tool_count: 24,
gateway_url: Some("http://127.0.0.1:3001/?token=abc123".to_string()),
embeddings_enabled: true,
embeddings_provider: Some("openai".to_string()),
heartbeat_enabled: true,
heartbeat_interval_secs: 1800,
sandbox_enabled: true,
claude_code_enabled: false,
routines_enabled: true,
channels: vec![
"repl".to_string(),
"gateway".to_string(),
"telegram".to_string(),
],
};
// Should not panic
print_boot_screen(&info);
}
#[test]
fn test_print_boot_screen_minimal() {
let info = BootInfo {
version: "0.2.0".to_string(),
agent_name: "ironclaw".to_string(),
llm_backend: "nearai".to_string(),
llm_model: "gpt-4o".to_string(),
cheap_model: None,
db_backend: "none".to_string(),
db_connected: false,
tool_count: 5,
gateway_url: None,
embeddings_enabled: false,
embeddings_provider: None,
heartbeat_enabled: false,
heartbeat_interval_secs: 0,
sandbox_enabled: false,
claude_code_enabled: false,
routines_enabled: false,
channels: vec![],
};
// Should not panic
print_boot_screen(&info);
}
#[test]
fn test_print_boot_screen_no_features() {
let info = BootInfo {
version: "0.1.0".to_string(),
agent_name: "test".to_string(),
llm_backend: "openai".to_string(),
llm_model: "gpt-4o".to_string(),
cheap_model: None,
db_backend: "postgres".to_string(),
db_connected: true,
tool_count: 10,
gateway_url: None,
embeddings_enabled: false,
embeddings_provider: None,
heartbeat_enabled: false,
heartbeat_interval_secs: 0,
sandbox_enabled: false,
claude_code_enabled: false,
routines_enabled: false,
channels: vec!["repl".to_string()],
};
// Should not panic
print_boot_screen(&info);
}
}
-464
View File
@@ -1,464 +0,0 @@
//! Bootstrap helpers for IronClaw.
//!
//! The only setting that truly needs disk persistence before the database is
//! available is `DATABASE_URL` (chicken-and-egg: can't connect to DB without
//! it). Everything else is auto-detected or read from env vars.
//!
//! File: `~/.ironclaw/.env` (standard dotenvy format)
use std::path::PathBuf;
/// Path to the IronClaw-specific `.env` file: `~/.ironclaw/.env`.
pub fn ironclaw_env_path() -> PathBuf {
dirs::home_dir()
.unwrap_or_else(|| PathBuf::from("."))
.join(".ironclaw")
.join(".env")
}
/// Load env vars from `~/.ironclaw/.env` (in addition to the standard `.env`).
///
/// Call this **after** `dotenvy::dotenv()` so that the standard `./.env`
/// takes priority over `~/.ironclaw/.env`. dotenvy never overwrites
/// existing env vars, so the effective priority is:
///
/// explicit env vars > `./.env` > `~/.ironclaw/.env`
///
/// If `~/.ironclaw/.env` doesn't exist but the legacy `bootstrap.json` does,
/// extracts `DATABASE_URL` from it and writes the `.env` file (one-time
/// upgrade from the old config format).
pub fn load_ironclaw_env() {
let path = ironclaw_env_path();
if !path.exists() {
// One-time upgrade: extract DATABASE_URL from legacy bootstrap.json
migrate_bootstrap_json_to_env(&path);
}
if path.exists() {
let _ = dotenvy::from_path(&path);
}
}
/// If `bootstrap.json` exists, pull `database_url` out of it and write `.env`.
fn migrate_bootstrap_json_to_env(env_path: &std::path::Path) {
let ironclaw_dir = env_path
.parent()
.unwrap_or_else(|| std::path::Path::new("."));
let bootstrap_path = ironclaw_dir.join("bootstrap.json");
if !bootstrap_path.exists() {
return;
}
let content = match std::fs::read_to_string(&bootstrap_path) {
Ok(c) => c,
Err(_) => return,
};
// Minimal parse: just grab database_url from the JSON
let parsed: serde_json::Value = match serde_json::from_str(&content) {
Ok(v) => v,
Err(_) => return,
};
if let Some(url) = parsed.get("database_url").and_then(|v| v.as_str()) {
if let Some(parent) = env_path.parent()
&& let Err(e) = std::fs::create_dir_all(parent)
{
eprintln!("Warning: failed to create {}: {}", parent.display(), e);
return;
}
if let Err(e) = std::fs::write(env_path, format!("DATABASE_URL=\"{}\"\n", url)) {
eprintln!("Warning: failed to migrate bootstrap.json to .env: {}", e);
return;
}
rename_to_migrated(&bootstrap_path);
eprintln!(
"Migrated DATABASE_URL from bootstrap.json to {}",
env_path.display()
);
}
}
/// Write database bootstrap vars to `~/.ironclaw/.env`.
///
/// These settings form the chicken-and-egg layer: they must be available
/// from the filesystem (env vars) BEFORE any database connection, because
/// they determine which database to connect to. Everything else is stored
/// in the database itself.
///
/// Creates the parent directory if it doesn't exist.
/// Values are double-quoted so that `#` (common in URL-encoded passwords)
/// and other shell-special characters are preserved by dotenvy.
pub fn save_bootstrap_env(vars: &[(&str, &str)]) -> std::io::Result<()> {
let path = ironclaw_env_path();
if let Some(parent) = path.parent() {
std::fs::create_dir_all(parent)?;
}
let mut content = String::new();
for (key, value) in vars {
content.push_str(&format!("{}=\"{}\"\n", key, value));
}
std::fs::write(&path, content)
}
/// Write `DATABASE_URL` to `~/.ironclaw/.env`.
///
/// Convenience wrapper around `save_bootstrap_env` for single-value migration
/// paths. Prefer `save_bootstrap_env` for new code.
pub fn save_database_url(url: &str) -> std::io::Result<()> {
save_bootstrap_env(&[("DATABASE_URL", url)])
}
/// One-time migration of legacy `~/.ironclaw/settings.json` into the database.
///
/// Only runs when a `settings.json` exists on disk AND the DB has no settings
/// yet. After the wizard writes directly to the DB, this path is only hit by
/// users upgrading from the old disk-only configuration.
///
/// After syncing, renames `settings.json` to `.migrated` so it won't trigger again.
pub async fn migrate_disk_to_db(
store: &dyn crate::db::Database,
user_id: &str,
) -> Result<(), MigrationError> {
let ironclaw_dir = dirs::home_dir()
.unwrap_or_else(|| PathBuf::from("."))
.join(".ironclaw");
let legacy_settings_path = ironclaw_dir.join("settings.json");
if !legacy_settings_path.exists() {
tracing::debug!("No legacy settings.json found, skipping disk-to-DB migration");
return Ok(());
}
// If DB already has settings, this is not a first boot, the wizard already
// wrote directly to the DB. Just clean up the stale file.
let has_settings = store.has_settings(user_id).await.map_err(|e| {
MigrationError::Database(format!("Failed to check existing settings: {}", e))
})?;
if has_settings {
tracing::info!("DB already has settings, renaming stale settings.json");
rename_to_migrated(&legacy_settings_path);
return Ok(());
}
tracing::info!("Migrating disk settings to database...");
// 1. Load and migrate settings.json
let settings = crate::settings::Settings::load_from(&legacy_settings_path);
let db_map = settings.to_db_map();
if !db_map.is_empty() {
store
.set_all_settings(user_id, &db_map)
.await
.map_err(|e| {
MigrationError::Database(format!("Failed to write settings to DB: {}", e))
})?;
tracing::info!("Migrated {} settings to database", db_map.len());
}
// 2. Write DATABASE_URL to ~/.ironclaw/.env
if let Some(ref url) = settings.database_url {
save_database_url(url)
.map_err(|e| MigrationError::Io(format!("Failed to write .env: {}", e)))?;
tracing::info!("Wrote DATABASE_URL to {}", ironclaw_env_path().display());
}
// 3. Migrate mcp-servers.json if it exists
let mcp_path = ironclaw_dir.join("mcp-servers.json");
if mcp_path.exists() {
match std::fs::read_to_string(&mcp_path) {
Ok(content) => match serde_json::from_str::<serde_json::Value>(&content) {
Ok(value) => {
store
.set_setting(user_id, "mcp_servers", &value)
.await
.map_err(|e| {
MigrationError::Database(format!(
"Failed to write MCP servers to DB: {}",
e
))
})?;
tracing::info!("Migrated mcp-servers.json to database");
rename_to_migrated(&mcp_path);
}
Err(e) => {
tracing::warn!("Failed to parse mcp-servers.json: {}", e);
}
},
Err(e) => {
tracing::warn!("Failed to read mcp-servers.json: {}", e);
}
}
}
// 4. Migrate session.json if it exists
let session_path = ironclaw_dir.join("session.json");
if session_path.exists() {
match std::fs::read_to_string(&session_path) {
Ok(content) => match serde_json::from_str::<serde_json::Value>(&content) {
Ok(value) => {
store
.set_setting(user_id, "nearai.session_token", &value)
.await
.map_err(|e| {
MigrationError::Database(format!(
"Failed to write session to DB: {}",
e
))
})?;
tracing::info!("Migrated session.json to database");
rename_to_migrated(&session_path);
}
Err(e) => {
tracing::warn!("Failed to parse session.json: {}", e);
}
},
Err(e) => {
tracing::warn!("Failed to read session.json: {}", e);
}
}
}
// 5. Rename settings.json to .migrated (don't delete, safety net)
rename_to_migrated(&legacy_settings_path);
// 6. Clean up old bootstrap.json if it exists (superseded by .env)
let old_bootstrap = ironclaw_dir.join("bootstrap.json");
if old_bootstrap.exists() {
rename_to_migrated(&old_bootstrap);
tracing::info!("Renamed old bootstrap.json to .migrated");
}
tracing::info!("Disk-to-DB migration complete");
Ok(())
}
/// Rename a file to `<name>.migrated` as a safety net.
fn rename_to_migrated(path: &std::path::Path) {
let mut migrated = path.as_os_str().to_owned();
migrated.push(".migrated");
if let Err(e) = std::fs::rename(path, &migrated) {
tracing::warn!("Failed to rename {} to .migrated: {}", path.display(), e);
}
}
/// Errors that can occur during disk-to-DB migration.
#[derive(Debug, thiserror::Error)]
pub enum MigrationError {
#[error("Database error: {0}")]
Database(String),
#[error("IO error: {0}")]
Io(String),
}
#[cfg(test)]
mod tests {
use super::*;
use tempfile::tempdir;
#[test]
fn test_save_and_load_database_url() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
// Write in the quoted format that save_database_url uses
let url = "postgres://localhost:5432/ironclaw_test";
std::fs::write(&env_path, format!("DATABASE_URL=\"{}\"\n", url)).unwrap();
// Verify the content is a valid dotenv line (quoted)
let content = std::fs::read_to_string(&env_path).unwrap();
assert_eq!(
content,
"DATABASE_URL=\"postgres://localhost:5432/ironclaw_test\"\n"
);
// Verify dotenvy can parse it (strips quotes automatically)
let parsed: Vec<(String, String)> = dotenvy::from_path_iter(&env_path)
.unwrap()
.filter_map(|r| r.ok())
.collect();
assert_eq!(parsed.len(), 1);
assert_eq!(parsed[0].0, "DATABASE_URL");
assert_eq!(parsed[0].1, url);
}
#[test]
fn test_save_database_url_with_hash_in_password() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
// URLs with # in the password are common (URL-encoded special chars).
// Without quoting, dotenvy treats # as a comment delimiter.
let url = "postgres://user:p%23ss@localhost:5432/ironclaw";
std::fs::write(&env_path, format!("DATABASE_URL=\"{}\"\n", url)).unwrap();
let parsed: Vec<(String, String)> = dotenvy::from_path_iter(&env_path)
.unwrap()
.filter_map(|r| r.ok())
.collect();
assert_eq!(parsed.len(), 1);
assert_eq!(parsed[0].0, "DATABASE_URL");
assert_eq!(parsed[0].1, url);
}
#[test]
fn test_save_database_url_creates_parent_dirs() {
let dir = tempdir().unwrap();
let nested = dir.path().join("deep").join("nested");
let env_path = nested.join(".env");
// Parent doesn't exist yet
assert!(!nested.exists());
// The global function uses a fixed path, so we test the logic directly
std::fs::create_dir_all(&nested).unwrap();
std::fs::write(&env_path, "DATABASE_URL=postgres://test\n").unwrap();
assert!(env_path.exists());
let content = std::fs::read_to_string(&env_path).unwrap();
assert!(content.contains("DATABASE_URL=postgres://test"));
}
#[test]
fn test_ironclaw_env_path() {
let path = ironclaw_env_path();
assert!(path.ends_with(".ironclaw/.env"));
}
#[test]
fn test_migrate_bootstrap_json_to_env() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
let bootstrap_path = dir.path().join("bootstrap.json");
// Write a legacy bootstrap.json
let bootstrap_json = serde_json::json!({
"database_url": "postgres://localhost/ironclaw_upgrade",
"database_pool_size": 5,
"secrets_master_key_source": "keychain",
"onboard_completed": true
});
std::fs::write(
&bootstrap_path,
serde_json::to_string_pretty(&bootstrap_json).unwrap(),
)
.unwrap();
assert!(!env_path.exists());
assert!(bootstrap_path.exists());
// Run the migration
migrate_bootstrap_json_to_env(&env_path);
// .env should now exist with DATABASE_URL
assert!(env_path.exists());
let content = std::fs::read_to_string(&env_path).unwrap();
assert_eq!(
content,
"DATABASE_URL=\"postgres://localhost/ironclaw_upgrade\"\n"
);
// bootstrap.json should be renamed to .migrated
assert!(!bootstrap_path.exists());
assert!(dir.path().join("bootstrap.json.migrated").exists());
}
#[test]
fn test_migrate_bootstrap_json_no_database_url() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
let bootstrap_path = dir.path().join("bootstrap.json");
// bootstrap.json with no database_url
let bootstrap_json = serde_json::json!({
"onboard_completed": false
});
std::fs::write(
&bootstrap_path,
serde_json::to_string_pretty(&bootstrap_json).unwrap(),
)
.unwrap();
migrate_bootstrap_json_to_env(&env_path);
// .env should NOT be created
assert!(!env_path.exists());
// bootstrap.json should remain (no migration happened)
assert!(bootstrap_path.exists());
}
#[test]
fn test_migrate_bootstrap_json_missing() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
// No bootstrap.json at all
migrate_bootstrap_json_to_env(&env_path);
// Nothing should happen
assert!(!env_path.exists());
}
#[test]
fn test_save_bootstrap_env_multiple_vars() {
let dir = tempdir().unwrap();
let env_path = dir.path().join("nested").join(".env");
std::fs::create_dir_all(env_path.parent().unwrap()).unwrap();
let vars = [
("DATABASE_BACKEND", "libsql"),
("LIBSQL_PATH", "/home/user/.ironclaw/ironclaw.db"),
];
// Write manually to the temp path (save_bootstrap_env uses the global path)
let mut content = String::new();
for (key, value) in &vars {
content.push_str(&format!("{}=\"{}\"\n", key, value));
}
std::fs::write(&env_path, &content).unwrap();
// Verify dotenvy can parse all entries
let parsed: Vec<(String, String)> = dotenvy::from_path_iter(&env_path)
.unwrap()
.filter_map(|r| r.ok())
.collect();
assert_eq!(parsed.len(), 2);
assert_eq!(
parsed[0],
("DATABASE_BACKEND".to_string(), "libsql".to_string())
);
assert_eq!(
parsed[1],
(
"LIBSQL_PATH".to_string(),
"/home/user/.ironclaw/ironclaw.db".to_string()
)
);
}
#[test]
fn test_save_bootstrap_env_overwrites_previous() {
let dir = tempdir().unwrap();
let env_path = dir.path().join(".env");
// Write initial content
std::fs::write(&env_path, "DATABASE_URL=\"postgres://old\"\n").unwrap();
// Overwrite with new vars (simulating save_bootstrap_env behavior)
let content = "DATABASE_BACKEND=\"libsql\"\nLIBSQL_PATH=\"/new/path.db\"\n";
std::fs::write(&env_path, content).unwrap();
let parsed: Vec<(String, String)> = dotenvy::from_path_iter(&env_path)
.unwrap()
.filter_map(|r| r.ok())
.collect();
// Old DATABASE_URL should be gone
assert_eq!(parsed.len(), 2);
assert!(parsed.iter().all(|(k, _)| k != "DATABASE_URL"));
}
}
-28
View File
@@ -108,38 +108,10 @@ pub enum StatusUpdate {
ToolStarted { name: String },
/// Tool execution completed.
ToolCompleted { name: String, success: bool },
/// Brief preview of tool execution output.
ToolResult { name: String, preview: String },
/// Streaming text chunk.
StreamChunk(String),
/// General status message.
Status(String),
/// A sandbox job has started (shown as a clickable card in the UI).
JobStarted {
job_id: String,
title: String,
browse_url: String,
},
/// Tool requires user approval before execution.
ApprovalNeeded {
request_id: String,
tool_name: String,
description: String,
parameters: serde_json::Value,
},
/// Extension needs user authentication (token or OAuth).
AuthRequired {
extension_name: String,
instructions: Option<String>,
auth_url: Option<String>,
setup_url: Option<String>,
},
/// Extension authentication completed.
AuthCompleted {
extension_name: String,
success: bool,
message: String,
},
}
/// Trait for message channels.
+359
View File
@@ -0,0 +1,359 @@
//! Application state for the TUI.
use std::collections::VecDeque;
use crate::channels::cli::composer::ChatComposer;
use crate::channels::cli::model_selector::{ModelSelectorOverlay, ModelSelectorRequest};
use crate::channels::cli::overlay::{ApprovalOverlay, ApprovalRequest};
/// Events that can occur in the TUI.
#[derive(Debug, Clone)]
pub enum AppEvent {
/// Keyboard/mouse input event.
Input(crossterm::event::Event),
/// Response from the agent.
Response(String),
/// Tool execution started.
ToolStarted { name: String },
/// Tool execution completed.
ToolCompleted { name: String, success: bool },
/// Request approval for a tool.
ApprovalRequested(ApprovalRequest),
/// Streaming chunk received.
StreamChunk(String),
/// Log message from the application (shown in status line).
LogMessage(String),
/// Thinking/status message (shown in chat window).
ThinkingMessage(String),
/// Error message (shown in chat window).
ErrorMessage(String),
/// Available models fetched from API.
AvailableModels(Vec<String>),
/// Force a redraw.
Redraw,
/// Quit the application.
Quit,
}
/// Current input mode.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum InputMode {
/// Normal input mode.
Normal,
/// Editing input.
Editing,
/// Approval overlay is active.
Approval,
/// Model selector overlay is active.
ModelSelector,
}
/// Message in the chat history.
#[derive(Debug, Clone)]
pub struct ChatMessage {
/// Who sent this message.
pub role: MessageRole,
/// The message content.
pub content: String,
/// Optional status indicator.
pub status: Option<MessageStatus>,
}
/// Who sent a message.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum MessageRole {
User,
Agent,
System,
}
/// Status of a message (for in-progress indicators).
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum MessageStatus {
Pending,
InProgress,
Complete,
Error,
}
impl ChatMessage {
pub fn user(content: impl Into<String>) -> Self {
Self {
role: MessageRole::User,
content: content.into(),
status: None,
}
}
pub fn agent(content: impl Into<String>) -> Self {
Self {
role: MessageRole::Agent,
content: content.into(),
status: None,
}
}
pub fn system(content: impl Into<String>) -> Self {
Self {
role: MessageRole::System,
content: content.into(),
status: None,
}
}
pub fn with_status(mut self, status: MessageStatus) -> Self {
self.status = Some(status);
self
}
}
/// Application state.
pub struct AppState {
/// Current input mode.
pub mode: InputMode,
/// Chat message history.
pub messages: Vec<ChatMessage>,
/// Input composer.
pub composer: ChatComposer,
/// Approval overlay (if active).
pub approval: Option<ApprovalOverlay>,
/// Model selector overlay (if active).
pub model_selector: Option<ModelSelectorOverlay>,
/// Scroll offset for messages.
pub scroll_offset: u16,
/// Whether the app should quit.
pub should_quit: bool,
/// Pending approvals queue.
pub pending_approvals: VecDeque<ApprovalRequest>,
/// Current streaming response buffer.
pub streaming_buffer: Option<String>,
/// Status line message.
pub status_message: Option<String>,
/// Whether Ctrl+D was pressed (waiting for second press to quit).
pub ctrl_d_pending: bool,
/// Currently selected model.
pub current_model: String,
/// Available models (fetched from API).
pub available_models: Vec<String>,
}
impl AppState {
/// Create a new app state.
pub fn new() -> Self {
// Load saved model from settings
let settings = crate::settings::Settings::load();
let current_model = settings.model_or("claude-3-5-sonnet-20241022");
Self {
mode: InputMode::Editing,
messages: vec![ChatMessage::system(
"Welcome to IronClaw. Type a message or /help for commands.",
)],
composer: ChatComposer::new(),
approval: None,
model_selector: None,
scroll_offset: 0,
should_quit: false,
pending_approvals: VecDeque::new(),
streaming_buffer: None,
status_message: None,
ctrl_d_pending: false,
current_model,
available_models: Vec::new(),
}
}
/// Show the model selector.
pub fn show_model_selector(&mut self) {
let request = ModelSelectorRequest {
current_model: self.current_model.clone(),
available_models: self.available_models.clone(),
};
self.model_selector = Some(ModelSelectorOverlay::new(request));
self.mode = InputMode::ModelSelector;
}
/// Handle model selection.
pub fn handle_model_selection(&mut self, selected: Option<String>) {
self.model_selector = None;
self.mode = InputMode::Editing;
if let Some(model) = selected {
if model != self.current_model {
self.current_model = model.clone();
// Save to settings
let mut settings = crate::settings::Settings::load();
if let Err(e) = settings.set_model(&model) {
tracing::warn!("Failed to save model setting: {}", e);
}
self.messages.push(ChatMessage::system(format!(
"Switched to model: {}",
ModelSelectorOverlay::format_model_name(&model)
)));
}
}
}
/// Set available models (also updates selector if open).
pub fn set_available_models(&mut self, models: Vec<String>) {
self.available_models = models.clone();
// Update the selector if it's currently open
if let Some(ref mut selector) = self.model_selector {
selector.request.available_models = models;
// Reset selection index if it's out of bounds
if selector.selection_index >= selector.request.available_models.len() {
selector.selection_index = 0;
}
}
}
/// Add a user message to history.
pub fn add_user_message(&mut self, content: impl Into<String>) {
self.messages.push(ChatMessage::user(content));
self.scroll_to_bottom();
}
/// Add an agent response to history.
pub fn add_agent_message(&mut self, content: impl Into<String>) {
// If we were streaming, finalize it
if self.streaming_buffer.is_some() {
self.streaming_buffer = None;
}
// Remove any pending thinking message before adding the response
self.clear_thinking();
self.messages.push(ChatMessage::agent(content));
self.scroll_to_bottom();
}
/// Add an error message to the chat.
pub fn add_error_message(&mut self, content: impl Into<String>) {
self.messages.push(
ChatMessage::system(format!("Error: {}", content.into()))
.with_status(MessageStatus::Error),
);
self.scroll_to_bottom();
}
/// Add or update a thinking/status message (shown as system message).
pub fn set_thinking(&mut self, content: impl Into<String>) {
let content = content.into();
// Check if last message is a thinking message (system with InProgress status)
if let Some(last) = self.messages.last_mut() {
if last.role == MessageRole::System && last.status == Some(MessageStatus::InProgress) {
last.content = content;
return;
}
}
// Add new thinking message
self.messages
.push(ChatMessage::system(content).with_status(MessageStatus::InProgress));
self.scroll_to_bottom();
}
/// Clear any thinking/status message.
pub fn clear_thinking(&mut self) {
// Remove any thinking messages (system with InProgress status)
self.messages.retain(|msg| {
!(msg.role == MessageRole::System && msg.status == Some(MessageStatus::InProgress))
});
}
/// Start streaming a response.
pub fn start_streaming(&mut self) {
self.streaming_buffer = Some(String::new());
self.messages
.push(ChatMessage::agent("").with_status(MessageStatus::InProgress));
}
/// Append to the streaming buffer.
pub fn append_stream(&mut self, chunk: &str) {
if let Some(ref mut buffer) = self.streaming_buffer {
buffer.push_str(chunk);
// Update the last message
if let Some(last) = self.messages.last_mut() {
if last.role == MessageRole::Agent {
last.content = buffer.clone();
}
}
}
}
/// Finalize streaming.
pub fn finish_streaming(&mut self) {
if let Some(last) = self.messages.last_mut() {
if last.role == MessageRole::Agent {
last.status = Some(MessageStatus::Complete);
}
}
self.streaming_buffer = None;
}
/// Show an approval request.
pub fn show_approval(&mut self, request: ApprovalRequest) {
self.approval = Some(ApprovalOverlay::new(request));
self.mode = InputMode::Approval;
}
/// Queue an approval request.
pub fn queue_approval(&mut self, request: ApprovalRequest) {
if self.approval.is_none() {
self.show_approval(request);
} else {
self.pending_approvals.push_back(request);
}
}
/// Handle approval response.
pub fn handle_approval_response(&mut self, approved: bool) -> Option<ApprovalRequest> {
let request = self.approval.take().map(|o| o.request);
// Show next pending approval if any
if let Some(next) = self.pending_approvals.pop_front() {
self.show_approval(next);
} else {
self.mode = InputMode::Editing;
}
if approved { request } else { None }
}
/// Clear all pending approvals.
pub fn clear_approvals(&mut self) {
self.approval = None;
self.pending_approvals.clear();
self.mode = InputMode::Editing;
}
/// Set the status message.
pub fn set_status(&mut self, message: impl Into<String>) {
self.status_message = Some(message.into());
}
/// Clear the status message.
pub fn clear_status(&mut self) {
self.status_message = None;
}
/// Scroll to the bottom of messages.
pub fn scroll_to_bottom(&mut self) {
// Will be calculated based on render area in render.rs
self.scroll_offset = 0;
}
/// Scroll up.
pub fn scroll_up(&mut self, amount: u16) {
self.scroll_offset = self.scroll_offset.saturating_add(amount);
}
/// Scroll down.
pub fn scroll_down(&mut self, amount: u16) {
self.scroll_offset = self.scroll_offset.saturating_sub(amount);
}
}
impl Default for AppState {
fn default() -> Self {
Self::new()
}
}
+318
View File
@@ -0,0 +1,318 @@
//! Input composer with history and completion.
use std::collections::VecDeque;
/// Maximum number of history entries to keep.
const MAX_HISTORY: usize = 100;
/// Available slash commands for completion.
const SLASH_COMMANDS: &[&str] = &[
"/help", "/job", "/status", "/cancel", "/list", "/tools", "/clear", "/quit",
];
/// Chat input composer with history navigation and slash command completion.
pub struct ChatComposer {
/// Current input buffer.
buffer: String,
/// Cursor position in the buffer.
cursor: usize,
/// Input history.
history: VecDeque<String>,
/// Current position in history (-1 = current input).
history_index: Option<usize>,
/// Saved current input when navigating history.
saved_input: String,
/// Completion candidates.
completions: Vec<String>,
/// Current completion index.
completion_index: Option<usize>,
}
impl ChatComposer {
/// Create a new composer.
pub fn new() -> Self {
Self {
buffer: String::new(),
cursor: 0,
history: VecDeque::with_capacity(MAX_HISTORY),
history_index: None,
saved_input: String::new(),
completions: Vec::new(),
completion_index: None,
}
}
/// Get the current input buffer.
pub fn buffer(&self) -> &str {
&self.buffer
}
/// Get the cursor position.
pub fn cursor(&self) -> usize {
self.cursor
}
/// Check if the buffer is empty.
pub fn is_empty(&self) -> bool {
self.buffer.is_empty()
}
/// Insert a character at the cursor.
pub fn insert(&mut self, c: char) {
self.clear_completion();
self.buffer.insert(self.cursor, c);
self.cursor += c.len_utf8();
}
/// Insert a string at the cursor.
pub fn insert_str(&mut self, s: &str) {
self.clear_completion();
self.buffer.insert_str(self.cursor, s);
self.cursor += s.len();
}
/// Delete the character before the cursor (backspace).
pub fn backspace(&mut self) {
self.clear_completion();
if self.cursor > 0 {
// Find the previous character boundary
let prev = self.buffer[..self.cursor]
.char_indices()
.next_back()
.map(|(i, _)| i)
.unwrap_or(0);
self.buffer.drain(prev..self.cursor);
self.cursor = prev;
}
}
/// Delete the character at the cursor (delete).
pub fn delete(&mut self) {
self.clear_completion();
if self.cursor < self.buffer.len() {
// Find the next character boundary
let next = self.buffer[self.cursor..]
.char_indices()
.nth(1)
.map(|(i, _)| self.cursor + i)
.unwrap_or(self.buffer.len());
self.buffer.drain(self.cursor..next);
}
}
/// Move cursor left.
pub fn move_left(&mut self) {
if self.cursor > 0 {
self.cursor = self.buffer[..self.cursor]
.char_indices()
.next_back()
.map(|(i, _)| i)
.unwrap_or(0);
}
}
/// Move cursor right.
pub fn move_right(&mut self) {
if self.cursor < self.buffer.len() {
self.cursor = self.buffer[self.cursor..]
.char_indices()
.nth(1)
.map(|(i, _)| self.cursor + i)
.unwrap_or(self.buffer.len());
}
}
/// Move cursor to start.
pub fn move_home(&mut self) {
self.cursor = 0;
}
/// Move cursor to end.
pub fn move_end(&mut self) {
self.cursor = self.buffer.len();
}
/// Delete from cursor to end of line.
pub fn kill_line(&mut self) {
self.clear_completion();
self.buffer.truncate(self.cursor);
}
/// Delete from start to cursor.
pub fn kill_to_start(&mut self) {
self.clear_completion();
self.buffer.drain(..self.cursor);
self.cursor = 0;
}
/// Clear the entire buffer.
pub fn clear(&mut self) {
self.buffer.clear();
self.cursor = 0;
self.clear_completion();
}
/// Submit the current input and return it.
pub fn submit(&mut self) -> String {
let input = std::mem::take(&mut self.buffer);
self.cursor = 0;
self.clear_completion();
// Add to history if non-empty and different from last entry
if !input.is_empty() && self.history.front() != Some(&input) {
self.history.push_front(input.clone());
if self.history.len() > MAX_HISTORY {
self.history.pop_back();
}
}
self.history_index = None;
self.saved_input.clear();
input
}
/// Navigate to previous history entry.
pub fn history_prev(&mut self) {
if self.history.is_empty() {
return;
}
match self.history_index {
None => {
// Save current input and go to first history entry
self.saved_input = std::mem::take(&mut self.buffer);
self.history_index = Some(0);
self.buffer = self.history[0].clone();
}
Some(i) if i + 1 < self.history.len() => {
self.history_index = Some(i + 1);
self.buffer = self.history[i + 1].clone();
}
_ => {}
}
self.cursor = self.buffer.len();
self.clear_completion();
}
/// Navigate to next history entry.
pub fn history_next(&mut self) {
match self.history_index {
Some(0) => {
// Go back to saved input
self.history_index = None;
self.buffer = std::mem::take(&mut self.saved_input);
}
Some(i) => {
self.history_index = Some(i - 1);
self.buffer = self.history[i - 1].clone();
}
None => {}
}
self.cursor = self.buffer.len();
self.clear_completion();
}
/// Attempt tab completion.
pub fn complete(&mut self) {
// Only complete slash commands for now
if !self.buffer.starts_with('/') {
return;
}
if self.completions.is_empty() {
// Generate completions
let prefix = &self.buffer;
self.completions = SLASH_COMMANDS
.iter()
.filter(|cmd| cmd.starts_with(prefix))
.map(|s| s.to_string())
.collect();
if !self.completions.is_empty() {
self.completion_index = Some(0);
}
} else if let Some(i) = self.completion_index {
// Cycle through completions
self.completion_index = Some((i + 1) % self.completions.len());
}
// Apply completion
if let Some(i) = self.completion_index {
if let Some(completion) = self.completions.get(i) {
self.buffer = completion.clone();
self.cursor = self.buffer.len();
}
}
}
/// Clear completion state.
fn clear_completion(&mut self) {
self.completions.clear();
self.completion_index = None;
}
/// Get current completion hint (for display).
pub fn completion_hint(&self) -> Option<&str> {
if let Some(i) = self.completion_index {
self.completions.get(i).map(|s| s.as_str())
} else {
None
}
}
/// Get the number of completions available.
pub fn completion_count(&self) -> usize {
self.completions.len()
}
}
impl Default for ChatComposer {
fn default() -> Self {
Self::new()
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_insert_and_backspace() {
let mut composer = ChatComposer::new();
composer.insert('h');
composer.insert('i');
assert_eq!(composer.buffer(), "hi");
composer.backspace();
assert_eq!(composer.buffer(), "h");
}
#[test]
fn test_history_navigation() {
let mut composer = ChatComposer::new();
composer.insert_str("first");
composer.submit();
composer.insert_str("second");
composer.submit();
composer.insert_str("current");
composer.history_prev();
assert_eq!(composer.buffer(), "second");
composer.history_prev();
assert_eq!(composer.buffer(), "first");
composer.history_next();
assert_eq!(composer.buffer(), "second");
composer.history_next();
assert_eq!(composer.buffer(), "current");
}
#[test]
fn test_completion() {
let mut composer = ChatComposer::new();
composer.insert_str("/hel");
composer.complete();
assert_eq!(composer.buffer(), "/help");
}
}
+333
View File
@@ -0,0 +1,333 @@
//! Event handling for the TUI.
use std::io;
use std::time::Duration;
use crossterm::event::{self, Event, KeyCode, KeyEvent, KeyModifiers};
use ratatui::Terminal;
use ratatui::backend::CrosstermBackend;
use tokio::sync::mpsc;
use crate::channels::IncomingMessage;
use crate::channels::cli::app::{AppEvent, AppState, InputMode};
use crate::channels::cli::render;
/// Tick rate for the event loop (50ms = 20fps).
const TICK_RATE: Duration = Duration::from_millis(50);
/// Run the main event loop.
pub fn run_event_loop(
terminal: &mut Terminal<CrosstermBackend<io::Stdout>>,
app: &mut AppState,
msg_tx: mpsc::Sender<IncomingMessage>,
mut event_rx: mpsc::Receiver<AppEvent>,
) -> io::Result<()> {
loop {
// Render
terminal.draw(|f| render::render(f, app))?;
// Check for quit - send shutdown signal and exit
if app.should_quit {
// Send a shutdown message so the agent loop knows to exit
let shutdown_msg = IncomingMessage::new("tui", "system", "/shutdown");
let _ = msg_tx.blocking_send(shutdown_msg);
// Explicitly drop to close the channel
drop(msg_tx);
return Ok(());
}
// Poll for terminal events
if event::poll(TICK_RATE)? {
let evt = event::read()?;
if let Err(e) = handle_event(app, evt, &msg_tx) {
tracing::error!("Event handling error: {}", e);
}
}
// Check for app events from agent (non-blocking)
while let Ok(app_event) = event_rx.try_recv() {
handle_app_event(app, app_event);
}
}
}
/// Handle a crossterm event.
fn handle_event(
app: &mut AppState,
event: Event,
msg_tx: &mpsc::Sender<IncomingMessage>,
) -> io::Result<()> {
match event {
Event::Key(key) => handle_key(app, key, msg_tx),
Event::Mouse(_) => Ok(()), // Could handle mouse scrolling here
Event::Resize(_, _) => Ok(()), // Terminal will handle resize
_ => Ok(()),
}
}
/// Handle a key event.
fn handle_key(
app: &mut AppState,
key: KeyEvent,
msg_tx: &mpsc::Sender<IncomingMessage>,
) -> io::Result<()> {
// Global keybindings
if key.modifiers.contains(KeyModifiers::CONTROL) {
match key.code {
KeyCode::Char('c') => {
if app.mode == InputMode::Approval {
// Cancel all pending approvals
app.clear_approvals();
} else {
// Quit
app.should_quit = true;
}
app.ctrl_d_pending = false;
return Ok(());
}
KeyCode::Char('d') => {
if app.ctrl_d_pending {
// Second Ctrl+D, quit now
app.should_quit = true;
} else {
// First Ctrl+D, show hint
app.ctrl_d_pending = true;
app.set_status("Press Ctrl+D again to quit");
}
return Ok(());
}
_ => {
// Any other Ctrl+ combo clears the Ctrl+D pending state
app.ctrl_d_pending = false;
}
}
} else {
// Any non-Ctrl key clears the Ctrl+D pending state
app.ctrl_d_pending = false;
}
match app.mode {
InputMode::Normal => handle_normal_mode(app, key),
InputMode::Editing => handle_editing_mode(app, key, msg_tx),
InputMode::Approval => handle_approval_mode(app, key),
InputMode::ModelSelector => handle_model_selector_mode(app, key),
}
}
/// Handle keys in normal mode.
fn handle_normal_mode(app: &mut AppState, key: KeyEvent) -> io::Result<()> {
match key.code {
KeyCode::Char('i') | KeyCode::Char('a') => {
app.mode = InputMode::Editing;
}
KeyCode::Char('q') => {
app.should_quit = true;
}
KeyCode::Up | KeyCode::Char('k') => {
app.scroll_up(1);
}
KeyCode::Down | KeyCode::Char('j') => {
app.scroll_down(1);
}
KeyCode::PageUp => {
app.scroll_up(10);
}
KeyCode::PageDown => {
app.scroll_down(10);
}
KeyCode::Char('G') => {
app.scroll_to_bottom();
}
_ => {}
}
Ok(())
}
/// Handle keys in editing mode.
fn handle_editing_mode(
app: &mut AppState,
key: KeyEvent,
msg_tx: &mpsc::Sender<IncomingMessage>,
) -> io::Result<()> {
match key.code {
KeyCode::Enter => {
if !app.composer.is_empty() {
let input = app.composer.submit();
// Handle /model command locally (TUI-specific)
if input.trim().eq_ignore_ascii_case("/model") {
app.show_model_selector();
return Ok(());
}
app.add_user_message(&input);
// Send message to agent
let msg = IncomingMessage::new("tui", "local-user", &input);
let _ = msg_tx.blocking_send(msg);
}
}
KeyCode::Esc => {
app.mode = InputMode::Normal;
}
KeyCode::Backspace => {
app.composer.backspace();
}
KeyCode::Delete => {
app.composer.delete();
}
KeyCode::Left => {
if key.modifiers.contains(KeyModifiers::CONTROL) {
// Move word left (simplified: just move to start)
app.composer.move_home();
} else {
app.composer.move_left();
}
}
KeyCode::Right => {
if key.modifiers.contains(KeyModifiers::CONTROL) {
// Move word right (simplified: just move to end)
app.composer.move_end();
} else {
app.composer.move_right();
}
}
KeyCode::Home => {
app.composer.move_home();
}
KeyCode::End => {
app.composer.move_end();
}
KeyCode::Up => {
app.composer.history_prev();
}
KeyCode::Down => {
app.composer.history_next();
}
KeyCode::Tab => {
app.composer.complete();
}
KeyCode::Char(c) => {
if key.modifiers.contains(KeyModifiers::CONTROL) {
match c {
'a' => app.composer.move_home(),
'e' => app.composer.move_end(),
'k' => app.composer.kill_line(),
'u' => app.composer.kill_to_start(),
'w' => {
// Delete word backwards (simplified: clear)
app.composer.clear();
}
_ => {}
}
} else {
app.composer.insert(c);
}
}
_ => {}
}
Ok(())
}
/// Handle keys in approval mode.
fn handle_approval_mode(app: &mut AppState, key: KeyEvent) -> io::Result<()> {
if let Some(ref mut overlay) = app.approval {
match key.code {
KeyCode::Left | KeyCode::Char('h') => {
overlay.select_prev();
}
KeyCode::Right | KeyCode::Char('l') => {
overlay.select_next();
}
KeyCode::Enter | KeyCode::Char(' ') => {
let (approved, _always) = overlay.confirm();
app.handle_approval_response(approved);
// TODO: If always, remember to auto-approve this tool
}
KeyCode::Char(c) => {
if let Some(approved) = overlay.handle_shortcut(c) {
app.handle_approval_response(approved);
}
}
KeyCode::Esc => {
// Deny this approval
app.handle_approval_response(false);
}
_ => {}
}
}
Ok(())
}
/// Handle keys in model selector mode.
fn handle_model_selector_mode(app: &mut AppState, key: KeyEvent) -> io::Result<()> {
if let Some(ref mut overlay) = app.model_selector {
match key.code {
KeyCode::Left | KeyCode::Char('h') => {
overlay.select_prev();
}
KeyCode::Right | KeyCode::Char('l') => {
overlay.select_next();
}
KeyCode::Enter | KeyCode::Char(' ') => {
let selected = overlay.selected_model().map(|s| s.to_string());
app.handle_model_selection(selected);
}
KeyCode::Esc => {
// Cancel without changing model
app.handle_model_selection(None);
}
_ => {}
}
}
Ok(())
}
/// Handle an application event.
fn handle_app_event(app: &mut AppState, event: AppEvent) {
match event {
AppEvent::Response(content) => {
app.add_agent_message(content);
}
AppEvent::ToolStarted { name } => {
app.set_thinking(format!("⚙️ Running tool: {}...", name));
}
AppEvent::ToolCompleted { name, success } => {
if success {
app.set_thinking(format!("✓ Tool {} completed", name));
} else {
app.set_thinking(format!("✗ Tool {} failed", name));
}
}
AppEvent::ApprovalRequested(request) => {
app.queue_approval(request);
}
AppEvent::StreamChunk(chunk) => {
if app.streaming_buffer.is_none() {
app.start_streaming();
}
app.append_stream(&chunk);
}
AppEvent::Redraw => {
// Just triggers a redraw on next loop iteration
}
AppEvent::Quit => {
app.should_quit = true;
}
AppEvent::Input(_) => {
// Already handled directly
}
AppEvent::LogMessage(msg) => {
app.set_status(msg);
}
AppEvent::ThinkingMessage(msg) => {
app.set_thinking(msg);
}
AppEvent::ErrorMessage(msg) => {
app.add_error_message(msg);
}
AppEvent::AvailableModels(models) => {
app.set_available_models(models);
}
}
}
+238
View File
@@ -0,0 +1,238 @@
//! Interactive TUI channel using Ratatui.
//!
//! Provides a rich terminal interface with:
//! - Input history navigation
//! - Slash command completion
//! - Approval overlays for tool execution
//! - Streaming response display
mod app;
mod composer;
mod events;
mod model_selector;
mod overlay;
mod render;
use std::io;
use std::sync::Arc;
use async_trait::async_trait;
use crossterm::{
execute,
terminal::{EnterAlternateScreen, LeaveAlternateScreen, disable_raw_mode, enable_raw_mode},
};
use ratatui::Terminal;
use ratatui::backend::CrosstermBackend;
use tokio::sync::{Mutex, mpsc};
use tokio_stream::wrappers::ReceiverStream;
use crate::channels::{Channel, IncomingMessage, MessageStream, OutgoingResponse, StatusUpdate};
use crate::error::ChannelError;
pub use app::{AppEvent, AppState, InputMode};
pub use composer::ChatComposer;
pub use model_selector::{ModelSelectorOverlay, ModelSelectorRequest};
pub use overlay::{ApprovalOverlay, ApprovalRequest};
/// TUI channel for interactive terminal input with Ratatui.
pub struct TuiChannel {
/// Channel for sending events to the TUI (created upfront for logging).
event_tx: mpsc::Sender<AppEvent>,
/// Receiver end, taken when start() is called.
event_rx: Arc<Mutex<Option<mpsc::Receiver<AppEvent>>>>,
}
impl TuiChannel {
/// Create a new TUI channel.
pub fn new() -> Self {
let (event_tx, event_rx) = mpsc::channel(64);
Self {
event_tx,
event_rx: Arc::new(Mutex::new(Some(event_rx))),
}
}
/// Get a log writer that sends messages to the TUI status line.
/// Use this to redirect tracing output to the TUI.
pub fn log_writer(&self) -> TuiLogWriter {
TuiLogWriter::new(self.event_tx.clone())
}
/// Get a sender for sending events to the TUI.
/// Use this to send available models or other events from outside the channel.
pub fn event_sender(&self) -> mpsc::Sender<AppEvent> {
self.event_tx.clone()
}
}
impl Default for TuiChannel {
fn default() -> Self {
Self::new()
}
}
#[async_trait]
impl Channel for TuiChannel {
fn name(&self) -> &str {
"tui"
}
async fn start(&self) -> Result<MessageStream, ChannelError> {
let (msg_tx, msg_rx) = mpsc::channel(32);
// Take the event receiver (can only start once)
let event_rx = {
let mut guard = self.event_rx.lock().await;
guard.take().ok_or_else(|| ChannelError::StartupFailed {
name: "tui".to_string(),
reason: "TUI channel already started".to_string(),
})?
};
tokio::task::spawn_blocking(move || {
if let Err(e) = run_tui(msg_tx, event_rx) {
// Try to restore terminal even on error
let _ = disable_raw_mode();
let _ = execute!(io::stdout(), LeaveAlternateScreen);
eprintln!("TUI error: {}", e);
}
});
Ok(Box::pin(ReceiverStream::new(msg_rx)))
}
async fn respond(
&self,
_msg: &IncomingMessage,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
self.event_tx
.send(AppEvent::Response(response.content))
.await
.map_err(|e| ChannelError::SendFailed {
name: "tui".to_string(),
reason: e.to_string(),
})?;
Ok(())
}
async fn send_status(
&self,
status: StatusUpdate,
_metadata: &serde_json::Value,
) -> Result<(), ChannelError> {
let event = match status {
StatusUpdate::Thinking(msg) => AppEvent::ThinkingMessage(format!("🤔 {}", msg)),
StatusUpdate::ToolStarted { name } => AppEvent::ToolStarted { name },
StatusUpdate::ToolCompleted { name, success } => {
AppEvent::ToolCompleted { name, success }
}
StatusUpdate::StreamChunk(chunk) => AppEvent::StreamChunk(chunk),
StatusUpdate::Status(msg) => AppEvent::ThinkingMessage(msg),
};
self.event_tx
.send(event)
.await
.map_err(|e| ChannelError::SendFailed {
name: "tui".to_string(),
reason: e.to_string(),
})?;
Ok(())
}
async fn broadcast(
&self,
_user_id: &str,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
// For TUI, broadcasts appear as regular agent responses with a notification indicator
self.event_tx
.send(AppEvent::Response(response.content))
.await
.map_err(|e| ChannelError::SendFailed {
name: "tui".to_string(),
reason: e.to_string(),
})?;
Ok(())
}
async fn health_check(&self) -> Result<(), ChannelError> {
// Channel is healthy if we haven't been closed
if self.event_tx.is_closed() {
Err(ChannelError::HealthCheckFailed {
name: "tui".to_string(),
})
} else {
Ok(())
}
}
async fn shutdown(&self) -> Result<(), ChannelError> {
let _ = self.event_tx.send(AppEvent::Quit).await;
Ok(())
}
}
/// Run the TUI event loop (blocking).
fn run_tui(
msg_tx: mpsc::Sender<IncomingMessage>,
event_rx: mpsc::Receiver<AppEvent>,
) -> io::Result<()> {
// Setup terminal
// Note: We don't enable mouse capture so users can select text normally
enable_raw_mode()?;
let mut stdout = io::stdout();
execute!(stdout, EnterAlternateScreen)?;
let backend = CrosstermBackend::new(stdout);
let mut terminal = Terminal::new(backend)?;
// Create app state
let mut app = AppState::new();
// Run event loop
let result = events::run_event_loop(&mut terminal, &mut app, msg_tx, event_rx);
// Restore terminal
disable_raw_mode()?;
execute!(terminal.backend_mut(), LeaveAlternateScreen)?;
terminal.show_cursor()?;
result
}
/// TUI-compatible tracing writer that sends log messages to the TUI status line.
#[derive(Clone)]
pub struct TuiLogWriter {
tx: mpsc::Sender<AppEvent>,
}
impl TuiLogWriter {
pub fn new(tx: mpsc::Sender<AppEvent>) -> Self {
Self { tx }
}
}
impl std::io::Write for TuiLogWriter {
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
if let Ok(s) = std::str::from_utf8(buf) {
let s = s.trim();
if !s.is_empty() {
// Fire and forget - don't block on logging
let _ = self.tx.try_send(AppEvent::LogMessage(s.to_string()));
}
}
Ok(buf.len())
}
fn flush(&mut self) -> io::Result<()> {
Ok(())
}
}
impl<'a> tracing_subscriber::fmt::MakeWriter<'a> for TuiLogWriter {
type Writer = Self;
fn make_writer(&'a self) -> Self::Writer {
self.clone()
}
}
+156
View File
@@ -0,0 +1,156 @@
//! Model selector overlay for switching LLM models.
/// Request to show the model selector.
#[derive(Debug, Clone)]
pub struct ModelSelectorRequest {
/// Currently selected model.
pub current_model: String,
/// Available models to choose from.
pub available_models: Vec<String>,
}
/// Model selector overlay state.
#[derive(Debug, Clone)]
pub struct ModelSelectorOverlay {
/// The request that triggered this overlay.
pub request: ModelSelectorRequest,
/// Currently highlighted index.
pub selection_index: usize,
}
impl ModelSelectorOverlay {
/// Create a new model selector overlay.
pub fn new(request: ModelSelectorRequest) -> Self {
// Find the current model in the list, default to 0
let selection_index = request
.available_models
.iter()
.position(|m| m == &request.current_model)
.unwrap_or(0);
Self {
request,
selection_index,
}
}
/// Get the list of available models.
pub fn models(&self) -> &[String] {
&self.request.available_models
}
/// Move selection up.
pub fn select_prev(&mut self) {
let len = self.request.available_models.len();
if len == 0 {
return;
}
if self.selection_index > 0 {
self.selection_index -= 1;
} else {
// Wrap to bottom
self.selection_index = len - 1;
}
}
/// Move selection down.
pub fn select_next(&mut self) {
let len = self.request.available_models.len();
if len == 0 {
return;
}
if self.selection_index < len - 1 {
self.selection_index += 1;
} else {
// Wrap to top
self.selection_index = 0;
}
}
/// Get the currently selected model name.
pub fn selected_model(&self) -> Option<&str> {
self.request
.available_models
.get(self.selection_index)
.map(|s| s.as_str())
}
/// Check if the selection is the current model.
pub fn is_current(&self) -> bool {
self.selected_model() == Some(&self.request.current_model)
}
/// Format a model name for display (shorten long names).
pub fn format_model_name(model: &str) -> String {
// Shorten fireworks model names
if let Some(rest) = model.strip_prefix("fireworks::accounts/fireworks/models/") {
return format!("fireworks/{}", rest);
}
// Shorten other long prefixes
if let Some(rest) = model.strip_prefix("accounts/") {
return rest.to_string();
}
model.to_string()
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_model_selector_navigation() {
let request = ModelSelectorRequest {
current_model: "gpt-4o".to_string(),
available_models: vec![
"claude-3-5-sonnet".to_string(),
"gpt-4o".to_string(),
"gpt-4o-mini".to_string(),
],
};
let mut overlay = ModelSelectorOverlay::new(request);
// Should start at gpt-4o index (1)
assert_eq!(overlay.selected_model(), Some("gpt-4o"));
// Navigate down
overlay.select_next();
assert_eq!(overlay.selected_model(), Some("gpt-4o-mini"));
// Navigate down (wrap)
overlay.select_next();
assert_eq!(overlay.selected_model(), Some("claude-3-5-sonnet"));
// Navigate up
overlay.select_prev();
assert_eq!(overlay.selected_model(), Some("gpt-4o-mini"));
}
#[test]
fn test_format_model_name() {
assert_eq!(
ModelSelectorOverlay::format_model_name("claude-3-5-sonnet-20241022"),
"claude-3-5-sonnet-20241022"
);
assert_eq!(
ModelSelectorOverlay::format_model_name(
"fireworks::accounts/fireworks/models/llama-v3p1-405b-instruct"
),
"fireworks/llama-v3p1-405b-instruct"
);
}
#[test]
fn test_empty_models() {
let request = ModelSelectorRequest {
current_model: "unknown".to_string(),
available_models: vec![],
};
let mut overlay = ModelSelectorOverlay::new(request);
assert_eq!(overlay.selected_model(), None);
// Should not panic
overlay.select_next();
overlay.select_prev();
}
}
+145
View File
@@ -0,0 +1,145 @@
//! Approval overlay modal.
use uuid::Uuid;
/// A request for user approval before executing a tool.
#[derive(Debug, Clone)]
pub struct ApprovalRequest {
/// Unique ID for this request.
pub id: Uuid,
/// Name of the tool requesting approval.
pub tool_name: String,
/// Description of what the tool will do.
pub description: String,
/// Parameters being passed to the tool.
pub parameters: serde_json::Value,
/// Whether this is a destructive operation.
pub destructive: bool,
}
impl ApprovalRequest {
/// Create a new approval request.
pub fn new(
tool_name: impl Into<String>,
description: impl Into<String>,
parameters: serde_json::Value,
) -> Self {
Self {
id: Uuid::new_v4(),
tool_name: tool_name.into(),
description: description.into(),
parameters,
destructive: false,
}
}
/// Mark as destructive operation.
pub fn destructive(mut self) -> Self {
self.destructive = true;
self
}
}
/// Current selection in the approval overlay.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ApprovalSelection {
/// Yes, approve this action.
Yes,
/// No, deny this action.
No,
/// Always approve this tool (for this session).
Always,
}
impl ApprovalSelection {
/// Get the next selection (cycling).
pub fn next(self) -> Self {
match self {
Self::Yes => Self::No,
Self::No => Self::Always,
Self::Always => Self::Yes,
}
}
/// Get the previous selection (cycling).
pub fn prev(self) -> Self {
match self {
Self::Yes => Self::Always,
Self::No => Self::Yes,
Self::Always => Self::No,
}
}
}
/// Approval overlay state.
pub struct ApprovalOverlay {
/// The request being shown.
pub request: ApprovalRequest,
/// Current selection.
pub selection: ApprovalSelection,
}
impl ApprovalOverlay {
/// Create a new approval overlay.
pub fn new(request: ApprovalRequest) -> Self {
Self {
request,
selection: ApprovalSelection::Yes,
}
}
/// Move selection left.
pub fn select_prev(&mut self) {
self.selection = self.selection.prev();
}
/// Move selection right.
pub fn select_next(&mut self) {
self.selection = self.selection.next();
}
/// Handle keyboard shortcut.
pub fn handle_shortcut(&mut self, c: char) -> Option<bool> {
match c.to_ascii_lowercase() {
'y' => Some(true),
'n' => Some(false),
'a' => {
self.selection = ApprovalSelection::Always;
Some(true)
}
_ => None,
}
}
/// Confirm the current selection.
pub fn confirm(&self) -> (bool, bool) {
match self.selection {
ApprovalSelection::Yes => (true, false),
ApprovalSelection::No => (false, false),
ApprovalSelection::Always => (true, true),
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_approval_selection_cycle() {
let sel = ApprovalSelection::Yes;
assert_eq!(sel.next(), ApprovalSelection::No);
assert_eq!(sel.next().next(), ApprovalSelection::Always);
assert_eq!(sel.next().next().next(), ApprovalSelection::Yes);
}
#[test]
fn test_approval_shortcuts() {
let request = ApprovalRequest::new("test", "Test operation", serde_json::json!({}));
let mut overlay = ApprovalOverlay::new(request);
assert_eq!(overlay.handle_shortcut('y'), Some(true));
assert_eq!(overlay.handle_shortcut('n'), Some(false));
assert_eq!(overlay.handle_shortcut('x'), None);
}
}
+341
View File
@@ -0,0 +1,341 @@
//! TUI rendering with Ratatui.
use ratatui::{
Frame,
layout::{Constraint, Direction, Layout, Rect},
style::{Color, Modifier, Style},
text::{Line, Span, Text},
widgets::{Block, Borders, Clear, Paragraph, Wrap},
};
use crate::channels::cli::app::{AppState, InputMode, MessageRole, MessageStatus};
use crate::channels::cli::model_selector::ModelSelectorOverlay;
use crate::channels::cli::overlay::ApprovalSelection;
/// Render the entire UI.
pub fn render(frame: &mut Frame, app: &AppState) {
let chunks = Layout::default()
.direction(Direction::Vertical)
.constraints([
Constraint::Min(3), // Messages
Constraint::Length(3), // Input
Constraint::Length(1), // Status
])
.split(frame.area());
render_messages(frame, app, chunks[0]);
render_input(frame, app, chunks[1]);
render_status(frame, app, chunks[2]);
// Render approval overlay if active
if app.mode == InputMode::Approval {
render_approval_overlay(frame, app);
}
}
/// Render the message history.
fn render_messages(frame: &mut Frame, app: &AppState, area: Rect) {
// Build all lines from all messages
let mut lines: Vec<Line> = Vec::new();
for msg in &app.messages {
let (prefix, style) = match msg.role {
MessageRole::User => ("You: ", Style::default().fg(Color::Cyan)),
MessageRole::Agent => ("Agent: ", Style::default().fg(Color::Green)),
MessageRole::System => (
"",
Style::default()
.fg(Color::DarkGray)
.add_modifier(Modifier::ITALIC),
),
};
let status_indicator = match msg.status {
Some(MessageStatus::Pending) => "",
Some(MessageStatus::InProgress) => " ⚙️",
Some(MessageStatus::Complete) => "",
Some(MessageStatus::Error) => "",
None => "",
};
// Split content by newlines and create a line for each
let content_lines: Vec<&str> = msg.content.lines().collect();
for (i, line_text) in content_lines.iter().enumerate() {
if i == 0 {
// First line gets the prefix
let line_content = if status_indicator.is_empty() {
format!("{}{}", prefix, line_text)
} else if content_lines.len() == 1 {
format!("{}{}{}", prefix, line_text, status_indicator)
} else {
format!("{}{}", prefix, line_text)
};
lines.push(Line::styled(line_content, style));
} else if i == content_lines.len() - 1 && !status_indicator.is_empty() {
// Last line gets status indicator
lines.push(Line::styled(
format!("{}{}", line_text, status_indicator),
style,
));
} else {
// Middle lines just get the content
lines.push(Line::styled(line_text.to_string(), style));
}
}
// Add empty line between messages for readability
lines.push(Line::from(""));
}
// Calculate scroll - show most recent messages
let visible_height = area.height.saturating_sub(2) as usize; // Account for borders
let total_lines = lines.len();
let scroll_offset = total_lines.saturating_sub(visible_height);
let text = Text::from(lines);
let messages = Paragraph::new(text)
.block(Block::default().borders(Borders::ALL).title("Chat"))
.wrap(Wrap { trim: false })
.scroll((scroll_offset as u16, 0));
frame.render_widget(messages, area);
}
/// Render the input area (or model selector when in ModelSelector mode).
fn render_input(frame: &mut Frame, app: &AppState, area: Rect) {
// In ModelSelector mode, render inline selector instead of input
if app.mode == InputMode::ModelSelector {
render_model_selector_inline(frame, app, area);
return;
}
let input_style = match app.mode {
InputMode::Editing => Style::default().fg(Color::Yellow),
InputMode::Normal => Style::default(),
InputMode::Approval | InputMode::ModelSelector => Style::default().fg(Color::DarkGray),
};
let buffer = app.composer.buffer();
let cursor = app.composer.cursor();
// Build the input text with cursor
let (before, after) = buffer.split_at(cursor.min(buffer.len()));
let cursor_char = after.chars().next().unwrap_or(' ');
let after_cursor = if after.is_empty() {
""
} else {
&after[cursor_char.len_utf8()..]
};
let input = Paragraph::new(Line::from(vec![
Span::raw(before),
Span::styled(
cursor_char.to_string(),
Style::default().bg(Color::White).fg(Color::Black),
),
Span::raw(after_cursor),
]))
.style(input_style)
.block(Block::default().borders(Borders::ALL).title("Input"));
frame.render_widget(input, area);
// Show cursor in editing mode
if app.mode == InputMode::Editing {
// Calculate cursor position accounting for the block border
let cursor_x = area.x + 1 + cursor as u16;
let cursor_y = area.y + 1;
frame.set_cursor_position((cursor_x, cursor_y));
}
}
/// Render inline model selector in the input area.
fn render_model_selector_inline(frame: &mut Frame, app: &AppState, area: Rect) {
let Some(ref overlay) = app.model_selector else {
return;
};
let models = overlay.models();
// Build horizontal list of models
let mut spans: Vec<Span> = Vec::new();
if models.is_empty() {
spans.push(Span::styled(
"Loading models...",
Style::default()
.fg(Color::DarkGray)
.add_modifier(Modifier::ITALIC),
));
} else {
for (i, model) in models.iter().enumerate() {
if i > 0 {
spans.push(Span::raw(" "));
}
let display_name = ModelSelectorOverlay::format_model_name(model);
let is_selected = i == overlay.selection_index;
let is_current = model == &overlay.request.current_model;
let style = if is_selected {
Style::default().bg(Color::Blue).fg(Color::White)
} else if is_current {
Style::default().fg(Color::Green)
} else {
Style::default().fg(Color::White)
};
let prefix = if is_current { "" } else { " " };
spans.push(Span::styled(format!("{}{}", prefix, display_name), style));
}
}
let content = Paragraph::new(Line::from(spans))
.block(Block::default().borders(Borders::ALL).title(Span::styled(
"Select Model",
Style::default().fg(Color::Cyan),
)))
.scroll((
0,
calculate_model_scroll(overlay, area.width.saturating_sub(2)),
));
frame.render_widget(content, area);
}
/// Calculate horizontal scroll offset to keep selected model visible.
fn calculate_model_scroll(overlay: &ModelSelectorOverlay, visible_width: u16) -> u16 {
let models = overlay.models();
if models.is_empty() {
return 0;
}
// Estimate position of selected model (rough calculation)
let mut pos: u16 = 0;
for (i, model) in models.iter().enumerate() {
let name_len = ModelSelectorOverlay::format_model_name(model).len() as u16 + 3; // +3 for prefix and spacing
if i == overlay.selection_index {
// Check if selection is beyond visible area
if pos > visible_width {
return pos.saturating_sub(visible_width / 2);
}
return 0;
}
pos += name_len;
}
0
}
/// Render the status line.
fn render_status(frame: &mut Frame, app: &AppState, area: Rect) {
let status_text = if let Some(ref msg) = app.status_message {
msg.clone()
} else {
match app.mode {
InputMode::Normal | InputMode::Editing => {
let model = ModelSelectorOverlay::format_model_name(&app.current_model);
format!("{} | /model to switch", model)
}
InputMode::Approval => "y=Yes, n=No, a=Always, Ctrl+C=Cancel".to_string(),
InputMode::ModelSelector => "←/→ navigate, Enter=select, Esc=cancel".to_string(),
}
};
let status = Paragraph::new(status_text).style(Style::default().fg(Color::DarkGray));
frame.render_widget(status, area);
}
/// Render the approval overlay.
fn render_approval_overlay(frame: &mut Frame, app: &AppState) {
let Some(ref overlay) = app.approval else {
return;
};
let area = frame.area();
// Calculate overlay size and position
let overlay_width = (area.width * 60 / 100).min(60);
let overlay_height = 12;
let overlay_x = (area.width - overlay_width) / 2;
let overlay_y = (area.height - overlay_height) / 2;
let overlay_area = Rect::new(overlay_x, overlay_y, overlay_width, overlay_height);
// Clear the area behind the overlay
frame.render_widget(Clear, overlay_area);
// Build overlay content
let title = if overlay.request.destructive {
"⚠️ Approval Required (Destructive)"
} else {
"Approval Required"
};
let title_style = if overlay.request.destructive {
Style::default().fg(Color::Red).add_modifier(Modifier::BOLD)
} else {
Style::default()
.fg(Color::Yellow)
.add_modifier(Modifier::BOLD)
};
// Build the text content
let mut lines = vec![
Line::from(vec![
Span::styled("Tool: ", Style::default().add_modifier(Modifier::BOLD)),
Span::raw(&overlay.request.tool_name),
]),
Line::from(""),
Line::from(overlay.request.description.as_str()),
Line::from(""),
];
// Add parameters preview (truncated)
let params_str = serde_json::to_string_pretty(&overlay.request.parameters)
.unwrap_or_else(|_| "{}".to_string());
let params_preview: String = params_str.chars().take(100).collect();
lines.push(Line::from(vec![
Span::styled("Params: ", Style::default().add_modifier(Modifier::BOLD)),
Span::styled(params_preview, Style::default().fg(Color::DarkGray)),
]));
lines.push(Line::from(""));
// Add selection buttons
let yes_style = if overlay.selection == ApprovalSelection::Yes {
Style::default().bg(Color::Green).fg(Color::Black)
} else {
Style::default().fg(Color::Green)
};
let no_style = if overlay.selection == ApprovalSelection::No {
Style::default().bg(Color::Red).fg(Color::Black)
} else {
Style::default().fg(Color::Red)
};
let always_style = if overlay.selection == ApprovalSelection::Always {
Style::default().bg(Color::Blue).fg(Color::Black)
} else {
Style::default().fg(Color::Blue)
};
lines.push(Line::from(vec![
Span::raw(" "),
Span::styled(" [Y]es ", yes_style),
Span::raw(" "),
Span::styled(" [N]o ", no_style),
Span::raw(" "),
Span::styled(" [A]lways ", always_style),
]));
let content = Paragraph::new(lines)
.block(
Block::default()
.borders(Borders::ALL)
.title(Span::styled(title, title_style)),
)
.wrap(Wrap { trim: true });
frame.render_widget(content, overlay_area);
}
+59 -23
View File
@@ -1,5 +1,6 @@
//! HTTP webhook channel for receiving messages via HTTP POST.
use std::net::SocketAddr;
use std::sync::Arc;
use async_trait::async_trait;
@@ -31,6 +32,8 @@ struct HttpChannelState {
tx: RwLock<Option<mpsc::Sender<IncomingMessage>>>,
/// Pending responses keyed by message ID.
pending_responses: RwLock<std::collections::HashMap<Uuid, oneshot::Sender<String>>>,
/// Server shutdown signal.
shutdown_tx: RwLock<Option<oneshot::Sender<()>>>,
/// Expected webhook secret for authentication (if configured).
webhook_secret: Option<String>,
/// Fixed user ID for this HTTP channel.
@@ -71,6 +74,7 @@ impl HttpChannel {
state: Arc::new(HttpChannelState {
tx: RwLock::new(None),
pending_responses: RwLock::new(std::collections::HashMap::new()),
shutdown_tx: RwLock::new(None),
webhook_secret,
user_id,
rate_limit: tokio::sync::Mutex::new(RateLimitState {
@@ -80,24 +84,6 @@ impl HttpChannel {
}),
}
}
/// Return the channel's axum routes with state applied.
///
/// The returned `Router` shares the same `Arc<HttpChannelState>` that
/// `start()` later populates. Before `start()` is called the webhook
/// handler returns 503 ("Channel not started").
pub fn routes(&self) -> Router {
Router::new()
.route("/health", get(health_handler))
.route("/webhook", post(webhook_handler))
.layer(DefaultBodyLimit::max(MAX_BODY_BYTES))
.with_state(self.state.clone())
}
/// Return the configured host and port for this channel.
pub fn addr(&self) -> (&str, u16) {
(&self.config.host, self.config.port)
}
}
#[derive(Debug, Deserialize)]
@@ -317,11 +303,53 @@ impl Channel for HttpChannel {
let (tx, rx) = mpsc::channel(256);
*self.state.tx.write().await = Some(tx);
tracing::info!(
"HTTP channel ready ({}:{})",
self.config.host,
self.config.port
);
let state = self.state.clone();
let host = self.config.host.clone();
let port = self.config.port;
// Parse address before spawning so we can return errors
let addr: SocketAddr =
format!("{}:{}", host, port)
.parse()
.map_err(|e| ChannelError::StartupFailed {
name: "http".to_string(),
reason: format!("Invalid address '{}:{}': {}", host, port, e),
})?;
// Bind listener before spawning so we can return errors
let listener =
tokio::net::TcpListener::bind(addr)
.await
.map_err(|e| ChannelError::StartupFailed {
name: "http".to_string(),
reason: format!("Failed to bind to {}: {}", addr, e),
})?;
tracing::info!("HTTP channel listening on {}", addr);
// Create router
let app = Router::new()
.route("/health", get(health_handler))
.route("/webhook", post(webhook_handler))
.layer(DefaultBodyLimit::max(MAX_BODY_BYTES))
.with_state(state.clone());
// Create shutdown channel
let (shutdown_tx, shutdown_rx) = oneshot::channel();
*self.state.shutdown_tx.write().await = Some(shutdown_tx);
// Spawn server (listener is already bound, serve errors are logged)
tokio::spawn(async move {
if let Err(e) = axum::serve(listener, app)
.with_graceful_shutdown(async {
let _ = shutdown_rx.await;
tracing::info!("HTTP channel shutting down");
})
.await
{
tracing::error!("HTTP server error: {}", e);
}
});
Ok(Box::pin(ReceiverStream::new(rx)))
}
@@ -335,10 +363,13 @@ impl Channel for HttpChannel {
if let Some(tx) = self.state.pending_responses.write().await.remove(&msg.id) {
let _ = tx.send(response.content);
}
// For async webhooks, we'd need to make an HTTP callback here
// but that requires the caller to provide a callback URL
Ok(())
}
async fn health_check(&self) -> Result<(), ChannelError> {
// Check if we have an active sender
if self.state.tx.read().await.is_some() {
Ok(())
} else {
@@ -349,6 +380,11 @@ impl Channel for HttpChannel {
}
async fn shutdown(&self) -> Result<(), ChannelError> {
// Send shutdown signal
if let Some(tx) = self.state.shutdown_tx.write().await.take() {
let _ = tx.send(());
}
// Clear the message sender
*self.state.tx.write().await = None;
Ok(())
}
+5 -7
View File
@@ -9,9 +9,9 @@
//! ┌─────────────────────────────────────────────────────────────────────┐
//! │ ChannelManager │
//! │ │
//! │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
//! │ │ ReplChannel │ │ HttpChannel │ │ WasmChannel │ ... │
//! │ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ │
//! │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐
//! │ │ TuiChannel │ │ HttpChannel │ │ WasmChannel │ ...
//! │ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘
//! │ │ │ │ │
//! │ └─────────────────┴─────────────────┘ │
//! │ │ │
@@ -28,16 +28,14 @@
//! See the [`wasm`] module for details.
mod channel;
pub mod cli;
mod http;
mod manager;
mod repl;
pub mod wasm;
pub mod web;
mod webhook_server;
pub use channel::{Channel, IncomingMessage, MessageStream, OutgoingResponse, StatusUpdate};
pub use cli::{AppEvent, TuiChannel};
pub use http::HttpChannel;
pub use manager::ChannelManager;
pub use repl::ReplChannel;
pub use web::GatewayChannel;
pub use webhook_server::{WebhookServer, WebhookServerConfig};
+81 -405
View File
@@ -1,8 +1,6 @@
//! Interactive REPL channel with line editing and markdown rendering.
//! Interactive REPL channel for debugging and testing.
//!
//! Provides the primary CLI interface for interacting with the agent.
//! Uses rustyline for line editing, history, and tab-completion.
//! Uses termimad for rendering markdown responses inline.
//! Provides a command-line interface for interacting with the agent.
//!
//! ## Commands
//!
@@ -16,176 +14,23 @@
//! - `/new` - Start a new thread
//! - `yes`/`no`/`always` - Respond to tool approval prompts
use std::borrow::Cow;
use std::io::{self, Write};
use std::io::{self, BufRead, Write};
use std::sync::Arc;
use std::sync::atomic::{AtomicBool, Ordering};
use async_trait::async_trait;
use rustyline::completion::Completer;
use rustyline::config::Config;
use rustyline::error::ReadlineError;
use rustyline::highlight::Highlighter;
use rustyline::hint::Hinter;
use rustyline::validate::Validator;
use rustyline::{CompletionType, Editor, Helper};
use termimad::MadSkin;
use tokio::sync::mpsc;
use tokio_stream::wrappers::ReceiverStream;
use crate::agent::truncate_for_preview;
use crate::channels::{Channel, IncomingMessage, MessageStream, OutgoingResponse, StatusUpdate};
use crate::error::ChannelError;
/// Max characters for tool result previews in the terminal.
const CLI_TOOL_RESULT_MAX: usize = 200;
/// Max characters for thinking/status messages in the terminal.
const CLI_STATUS_MAX: usize = 200;
/// Slash commands available in the REPL.
const SLASH_COMMANDS: &[&str] = &[
"/help",
"/quit",
"/exit",
"/debug",
"/model",
"/undo",
"/redo",
"/clear",
"/compact",
"/new",
"/interrupt",
"/version",
"/tools",
"/ping",
"/job",
"/status",
"/cancel",
"/list",
"/heartbeat",
"/summarize",
"/suggest",
"/thread",
"/resume",
];
/// Rustyline helper for slash-command tab completion.
struct ReplHelper;
impl Completer for ReplHelper {
type Candidate = String;
fn complete(
&self,
line: &str,
pos: usize,
_ctx: &rustyline::Context<'_>,
) -> rustyline::Result<(usize, Vec<String>)> {
if !line.starts_with('/') {
return Ok((0, vec![]));
}
let prefix = &line[..pos];
let matches: Vec<String> = SLASH_COMMANDS
.iter()
.filter(|cmd| cmd.starts_with(prefix))
.map(|cmd| cmd.to_string())
.collect();
Ok((0, matches))
}
}
impl Hinter for ReplHelper {
type Hint = String;
fn hint(&self, line: &str, pos: usize, _ctx: &rustyline::Context<'_>) -> Option<String> {
if !line.starts_with('/') || pos < line.len() {
return None;
}
SLASH_COMMANDS
.iter()
.find(|cmd| cmd.starts_with(line) && **cmd != line)
.map(|cmd| cmd[line.len()..].to_string())
}
}
impl Highlighter for ReplHelper {
fn highlight_hint<'h>(&self, hint: &'h str) -> Cow<'h, str> {
Cow::Owned(format!("\x1b[90m{hint}\x1b[0m"))
}
}
impl Validator for ReplHelper {}
impl Helper for ReplHelper {}
/// Build a termimad skin with our color scheme.
fn make_skin() -> MadSkin {
let mut skin = MadSkin::default();
skin.set_headers_fg(termimad::crossterm::style::Color::Yellow);
skin.bold.set_fg(termimad::crossterm::style::Color::White);
skin.italic
.set_fg(termimad::crossterm::style::Color::Magenta);
skin.inline_code
.set_fg(termimad::crossterm::style::Color::Green);
skin.code_block
.set_fg(termimad::crossterm::style::Color::Green);
skin.code_block.left_margin = 2;
skin
}
/// Format JSON params as `key: value` lines for the approval card.
fn format_json_params(params: &serde_json::Value, indent: &str) -> String {
match params {
serde_json::Value::Object(map) => {
let mut lines = Vec::new();
for (key, value) in map {
let val_str = match value {
serde_json::Value::String(s) => {
let display = if s.len() > 120 { &s[..120] } else { s };
format!("\x1b[32m\"{display}\"\x1b[0m")
}
other => {
let rendered = other.to_string();
if rendered.len() > 120 {
format!("{}...", &rendered[..120])
} else {
rendered
}
}
};
lines.push(format!("{indent}\x1b[36m{key}\x1b[0m: {val_str}"));
}
lines.join("\n")
}
other => {
let pretty = serde_json::to_string_pretty(other).unwrap_or_else(|_| other.to_string());
let truncated = if pretty.len() > 300 {
format!("{}...", &pretty[..300])
} else {
pretty
};
truncated
.lines()
.map(|l| format!("{indent}\x1b[90m{l}\x1b[0m"))
.collect::<Vec<_>>()
.join("\n")
}
}
}
/// REPL channel with line editing and markdown rendering.
/// REPL channel for interactive agent debugging.
pub struct ReplChannel {
/// Optional single message to send (for -m flag).
single_message: Option<String>,
/// Debug mode flag (shared with input thread).
debug_mode: Arc<AtomicBool>,
/// Whether we're currently streaming (chunks have been printed without a trailing newline).
is_streaming: Arc<AtomicBool>,
/// When true, the one-liner startup banner is suppressed (boot screen shown instead).
suppress_banner: Arc<AtomicBool>,
}
impl ReplChannel {
@@ -194,8 +39,6 @@ impl ReplChannel {
Self {
single_message: None,
debug_mode: Arc::new(AtomicBool::new(false)),
is_streaming: Arc::new(AtomicBool::new(false)),
suppress_banner: Arc::new(AtomicBool::new(false)),
}
}
@@ -204,16 +47,9 @@ impl ReplChannel {
Self {
single_message: Some(message),
debug_mode: Arc::new(AtomicBool::new(false)),
is_streaming: Arc::new(AtomicBool::new(false)),
suppress_banner: Arc::new(AtomicBool::new(false)),
}
}
/// Suppress the one-liner startup banner (boot screen will be shown instead).
pub fn suppress_banner(&self) {
self.suppress_banner.store(true, Ordering::Relaxed);
}
fn is_debug(&self) -> bool {
self.debug_mode.load(Ordering::Relaxed)
}
@@ -226,41 +62,32 @@ impl Default for ReplChannel {
}
fn print_help() {
// Bold white for section headers, bold cyan for commands, dim gray for descriptions
let h = "\x1b[1m"; // bold (section headers)
let c = "\x1b[1;36m"; // bold cyan (commands)
let d = "\x1b[90m"; // dim gray (descriptions)
let r = "\x1b[0m"; // reset
println!(
r#"
IronClaw REPL - Interactive debugging mode
println!();
println!(" {h}IronClaw REPL{r}");
println!();
println!(" {h}Commands{r}");
println!(" {c}/help{r} {d}show this help{r}");
println!(" {c}/debug{r} {d}toggle verbose output{r}");
println!(" {c}/quit{r} {c}/exit{r} {d}exit the repl{r}");
println!();
println!(" {h}Conversation{r}");
println!(" {c}/undo{r} {d}undo the last turn{r}");
println!(" {c}/redo{r} {d}redo an undone turn{r}");
println!(" {c}/clear{r} {d}clear conversation{r}");
println!(" {c}/compact{r} {d}compact context window{r}");
println!(" {c}/new{r} {d}new conversation thread{r}");
println!(" {c}/interrupt{r} {d}stop current operation{r}");
println!();
println!(" {h}Approval responses{r}");
println!(" {c}yes{r} ({c}y{r}) {d}approve tool execution{r}");
println!(" {c}no{r} ({c}n{r}) {d}deny tool execution{r}");
println!(" {c}always{r} ({c}a{r}) {d}approve for this session{r}");
println!();
}
Commands:
/help Show this help message
/quit, /exit Exit the REPL
/debug Toggle debug mode (verbose output)
/undo Undo the last turn
/redo Redo an undone turn
/clear Clear the conversation
/compact Compact the context window
/new Start a new conversation thread
/interrupt Stop the current operation
/// Get the history file path (~/.ironclaw/history).
fn history_path() -> std::path::PathBuf {
dirs::home_dir()
.unwrap_or_else(|| std::path::PathBuf::from("."))
.join(".ironclaw")
.join("history")
Approval responses (when prompted):
yes, y Approve the tool execution
no, n Deny the tool execution
always Approve and auto-approve this tool for the session
Tips:
- Tool calls requiring approval will pause and wait for your response
- Use /debug to see detailed tool inputs and outputs
- Press Ctrl+C to interrupt a long-running operation
"#
);
}
#[async_trait]
@@ -273,65 +100,49 @@ impl Channel for ReplChannel {
let (tx, rx) = mpsc::channel(32);
let single_message = self.single_message.clone();
let debug_mode = Arc::clone(&self.debug_mode);
let suppress_banner = Arc::clone(&self.suppress_banner);
std::thread::spawn(move || {
// Single message mode: send it and return
// If single message mode, send it and exit
if let Some(msg) = single_message {
let incoming = IncomingMessage::new("repl", "default", &msg);
let _ = tx.blocking_send(incoming);
let incoming = IncomingMessage::new("repl", "user", &msg);
if tx.blocking_send(incoming).is_err() {
return;
}
// Wait a bit for response, then the channel will close
return;
}
// Set up rustyline
let config = Config::builder()
.history_ignore_dups(true)
.expect("valid config")
.auto_add_history(true)
.completion_type(CompletionType::List)
.build();
// Interactive REPL mode
let stdin = io::stdin();
let mut stdout = io::stdout();
let mut rl = match Editor::with_config(config) {
Ok(editor) => editor,
Err(e) => {
eprintln!("Failed to initialize line editor: {e}");
return;
}
};
rl.set_helper(Some(ReplHelper));
// Load history
let hist_path = history_path();
if let Some(parent) = hist_path.parent() {
let _ = std::fs::create_dir_all(parent);
}
let _ = rl.load_history(&hist_path);
if !suppress_banner.load(Ordering::Relaxed) {
println!("\x1b[1mIronClaw\x1b[0m /help for commands, /quit to exit");
println!();
}
println!("IronClaw REPL - Type /help for commands, /quit to exit");
println!();
loop {
// Print prompt
let prompt = if debug_mode.load(Ordering::Relaxed) {
"\x1b[33m[debug]\x1b[0m \x1b[1;36m\u{203A}\x1b[0m "
"[debug] > "
} else {
"\x1b[1;36m\u{203A}\x1b[0m "
"> "
};
print!("{}", prompt);
let _ = stdout.flush();
match rl.readline(prompt) {
Ok(line) => {
// Read line
let mut line = String::new();
match stdin.lock().read_line(&mut line) {
Ok(0) => break, // EOF
Ok(_) => {
let line = line.trim();
if line.is_empty() {
continue;
}
// Handle local REPL commands (only commands that need
// immediate local handling stay here)
// Handle local REPL commands
match line.to_lowercase().as_str() {
"/quit" | "/exit" => break,
"/help" => {
"/help" | "/?" => {
print_help();
continue;
}
@@ -339,42 +150,23 @@ impl Channel for ReplChannel {
let current = debug_mode.load(Ordering::Relaxed);
debug_mode.store(!current, Ordering::Relaxed);
if !current {
println!("\x1b[90mdebug mode on\x1b[0m");
println!("Debug mode ON - showing verbose tool output");
} else {
println!("\x1b[90mdebug mode off\x1b[0m");
println!("Debug mode OFF");
}
continue;
}
_ => {}
}
let msg = IncomingMessage::new("repl", "default", line);
let msg = IncomingMessage::new("repl", "user", line);
if tx.blocking_send(msg).is_err() {
break;
}
}
Err(ReadlineError::Interrupted) => {
// Ctrl+C: send /interrupt
let msg = IncomingMessage::new("repl", "default", "/interrupt");
if tx.blocking_send(msg).is_err() {
break;
}
}
Err(ReadlineError::Eof) => {
// Ctrl+D: send /quit so the agent loop runs graceful shutdown
let msg = IncomingMessage::new("repl", "default", "/quit");
let _ = tx.blocking_send(msg);
break;
}
Err(e) => {
eprintln!("Input error: {e}");
break;
}
Err(_) => break,
}
}
// Save history on exit
let _ = rl.save_history(&history_path());
});
Ok(Box::pin(ReceiverStream::new(rx)))
@@ -385,27 +177,8 @@ impl Channel for ReplChannel {
_msg: &IncomingMessage,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
let width = crossterm::terminal::size()
.map(|(w, _)| w as usize)
.unwrap_or(80);
// If we were streaming, the content was already printed via StreamChunk.
// Just finish the line and reset.
if self.is_streaming.swap(false, Ordering::Relaxed) {
println!();
println!();
return Ok(());
}
// Dim separator line before the response
let sep_width = width.min(80);
eprintln!("\x1b[90m{}\x1b[0m", "\u{2500}".repeat(sep_width));
// Render markdown
let skin = make_skin();
let text = termimad::FmtText::from(&skin, &response.content, Some(width));
print!("{text}");
println!();
println!("{}", response.content);
println!();
Ok(())
}
@@ -419,129 +192,38 @@ impl Channel for ReplChannel {
match status {
StatusUpdate::Thinking(msg) => {
let display = truncate_for_preview(&msg, CLI_STATUS_MAX);
eprintln!(" \x1b[90m\u{25CB} {display}\x1b[0m");
if debug {
eprintln!("\x1b[90m[thinking] {}\x1b[0m", msg);
} else {
eprint!(".");
let _ = io::stderr().flush();
}
}
StatusUpdate::ToolStarted { name } => {
eprintln!(" \x1b[33m\u{25CB} {name}\x1b[0m");
if debug {
eprintln!("\x1b[33m[tool:start] {}\x1b[0m", name);
} else {
eprintln!("\x1b[33m⚡ {}\x1b[0m", name);
}
}
StatusUpdate::ToolCompleted { name, success } => {
if success {
eprintln!(" \x1b[32m\u{25CF} {name}\x1b[0m");
} else {
eprintln!(" \x1b[31m\u{2717} {name} (failed)\x1b[0m");
if debug {
if success {
eprintln!("\x1b[32m[tool:done] {}\x1b[0m", name);
} else {
eprintln!("\x1b[31m[tool:fail] {}\x1b[0m", name);
}
} else if !success {
eprintln!("\x1b[31m✗ {} failed\x1b[0m", name);
}
}
StatusUpdate::ToolResult { name: _, preview } => {
let display = truncate_for_preview(&preview, CLI_TOOL_RESULT_MAX);
eprintln!(" \x1b[90m{display}\x1b[0m");
}
StatusUpdate::StreamChunk(chunk) => {
// Print separator on the false-to-true transition
if !self.is_streaming.swap(true, Ordering::Relaxed) {
let width = crossterm::terminal::size()
.map(|(w, _)| w as usize)
.unwrap_or(80);
let sep_width = width.min(80);
eprintln!("\x1b[90m{}\x1b[0m", "\u{2500}".repeat(sep_width));
}
print!("{chunk}");
print!("{}", chunk);
let _ = io::stdout().flush();
}
StatusUpdate::JobStarted {
job_id,
title,
browse_url,
} => {
eprintln!(
" \x1b[36m[job]\x1b[0m {title} \x1b[90m({job_id})\x1b[0m \x1b[4m{browse_url}\x1b[0m"
);
}
StatusUpdate::Status(msg) => {
if debug || msg.contains("approval") || msg.contains("Approval") {
let display = truncate_for_preview(&msg, CLI_STATUS_MAX);
eprintln!(" \x1b[90m{display}\x1b[0m");
}
}
StatusUpdate::ApprovalNeeded {
request_id,
tool_name,
description,
parameters,
} => {
let term_width = crossterm::terminal::size()
.map(|(w, _)| w as usize)
.unwrap_or(80);
let box_width = (term_width.saturating_sub(4)).clamp(40, 60);
// Short request ID for the bottom border
let short_id = if request_id.len() > 8 {
&request_id[..8]
} else {
&request_id
};
// Top border: ┌ tool_name requires approval ───
let top_label = format!(" {tool_name} requires approval ");
let top_fill = box_width.saturating_sub(top_label.len() + 1);
let top_border = format!(
"\u{250C}\x1b[33m{top_label}\x1b[0m{}",
"\u{2500}".repeat(top_fill)
);
// Bottom border: └─ short_id ─────
let bot_label = format!(" {short_id} ");
let bot_fill = box_width.saturating_sub(bot_label.len() + 2);
let bot_border = format!(
"\u{2514}\u{2500}\x1b[90m{bot_label}\x1b[0m{}",
"\u{2500}".repeat(bot_fill)
);
eprintln!();
eprintln!(" {top_border}");
eprintln!(" \u{2502} \x1b[90m{description}\x1b[0m");
eprintln!(" \u{2502}");
// Params
let param_lines = format_json_params(&parameters, " \u{2502} ");
// The format_json_params already includes the indent prefix
// but we need to handle the case where each line already starts with it
for line in param_lines.lines() {
eprintln!("{line}");
}
eprintln!(" \u{2502}");
eprintln!(
" \u{2502} \x1b[32myes\x1b[0m (y) / \x1b[34malways\x1b[0m (a) / \x1b[31mno\x1b[0m (n)"
);
eprintln!(" {bot_border}");
eprintln!();
}
StatusUpdate::AuthRequired {
extension_name,
instructions,
setup_url,
..
} => {
eprintln!();
eprintln!("\x1b[33m Authentication required for {extension_name}\x1b[0m");
if let Some(ref instr) = instructions {
eprintln!(" {instr}");
}
if let Some(ref url) = setup_url {
eprintln!(" \x1b[4m{url}\x1b[0m");
}
eprintln!();
}
StatusUpdate::AuthCompleted {
extension_name,
success,
message,
} => {
if success {
eprintln!("\x1b[32m {extension_name}: {message}\x1b[0m");
} else {
eprintln!("\x1b[31m {extension_name}: {message}\x1b[0m");
eprintln!("\x1b[90m[status] {}\x1b[0m", msg);
}
}
}
@@ -553,15 +235,9 @@ impl Channel for ReplChannel {
_user_id: &str,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
let skin = make_skin();
let width = crossterm::terminal::size()
.map(|(w, _)| w as usize)
.unwrap_or(80);
eprintln!("\x1b[34m\u{25CF}\x1b[0m notification");
let text = termimad::FmtText::from(&skin, &response.content, Some(width));
eprint!("{text}");
eprintln!();
println!();
println!("\x1b[36m[notification]\x1b[0m {}", response.content);
println!();
Ok(())
}
-165
View File
@@ -1,165 +0,0 @@
//! Known WASM channels that can be installed from build artifacts.
//!
//! Instead of embedding WASM binaries in the host binary via include_bytes!,
//! channels are compiled separately and installed from their build output
//! directories during onboarding.
//!
//! Channel source layout:
//! channels-src/<name>/
//! target/wasm32-wasip2/release/<name>_channel.wasm
//! <name>.capabilities.json
use std::path::{Path, PathBuf};
use tokio::fs;
/// Compile-time project root, used to locate channels-src/ in dev builds.
const CARGO_MANIFEST_DIR: &str = env!("CARGO_MANIFEST_DIR");
/// Known channel names and their crate names (for locating build artifacts).
const KNOWN_CHANNELS: &[(&str, &str)] = &[
("telegram", "telegram_channel"),
("slack", "slack_channel"),
("whatsapp", "whatsapp_channel"),
];
/// Names of known channels that can be installed.
pub fn bundled_channel_names() -> Vec<&'static str> {
KNOWN_CHANNELS.iter().map(|(name, _)| *name).collect()
}
/// Resolve the channels source directory.
///
/// Checks (in order):
/// 1. `IRONCLAW_CHANNELS_SRC` env var
/// 2. `<CARGO_MANIFEST_DIR>/channels-src/` (dev builds)
fn channels_src_dir() -> PathBuf {
if let Ok(dir) = std::env::var("IRONCLAW_CHANNELS_SRC") {
return PathBuf::from(dir);
}
PathBuf::from(CARGO_MANIFEST_DIR).join("channels-src")
}
/// Locate the build artifacts for a channel.
///
/// Returns (wasm_path, capabilities_path) or an error if files are missing.
fn locate_channel_artifacts(name: &str) -> Result<(PathBuf, PathBuf), String> {
let (_, crate_name) = KNOWN_CHANNELS
.iter()
.find(|(n, _)| *n == name)
.ok_or_else(|| format!("Unknown channel '{}'", name))?;
let src_dir = channels_src_dir();
let channel_dir = src_dir.join(name);
let wasm_path = channel_dir
.join("target/wasm32-wasip2/release")
.join(format!("{}.wasm", crate_name));
let caps_path = channel_dir.join(format!("{}.capabilities.json", name));
if !wasm_path.exists() {
return Err(format!(
"Channel '{}' WASM not found at {}. Build it first:\n \
cd {} && cargo build --target wasm32-wasip2 --release",
name,
wasm_path.display(),
channel_dir.display()
));
}
if !caps_path.exists() {
return Err(format!(
"Channel '{}' capabilities not found at {}",
name,
caps_path.display()
));
}
Ok((wasm_path, caps_path))
}
/// Install a channel from build artifacts into the channels directory.
pub async fn install_bundled_channel(
name: &str,
target_dir: &Path,
force: bool,
) -> Result<(), String> {
let (wasm_src, caps_src) = locate_channel_artifacts(name)?;
fs::create_dir_all(target_dir)
.await
.map_err(|e| format!("Failed to create channels directory: {}", e))?;
let wasm_dst = target_dir.join(format!("{}.wasm", name));
let caps_dst = target_dir.join(format!("{}.capabilities.json", name));
let has_existing = wasm_dst.exists() || caps_dst.exists();
if has_existing && !force {
return Err(format!(
"Channel '{}' already exists at {}",
name,
target_dir.display()
));
}
fs::copy(&wasm_src, &wasm_dst)
.await
.map_err(|e| format!("Failed to copy {}: {}", wasm_src.display(), e))?;
fs::copy(&caps_src, &caps_dst)
.await
.map_err(|e| format!("Failed to copy {}: {}", caps_src.display(), e))?;
Ok(())
}
/// Check which known channels have build artifacts available.
pub fn available_channel_names() -> Vec<&'static str> {
KNOWN_CHANNELS
.iter()
.filter(|(name, _)| locate_channel_artifacts(name).is_ok())
.map(|(name, _)| *name)
.collect()
}
#[cfg(test)]
mod tests {
use tempfile::tempdir;
use tokio::fs;
use super::*;
#[test]
fn test_known_channels_includes_all_three() {
let names = bundled_channel_names();
assert!(names.contains(&"telegram"));
assert!(names.contains(&"slack"));
assert!(names.contains(&"whatsapp"));
}
#[test]
fn test_channels_src_dir_default() {
let dir = channels_src_dir();
assert!(dir.ends_with("channels-src"));
}
#[test]
fn test_locate_unknown_channel_errors() {
assert!(locate_channel_artifacts("nonexistent").is_err());
}
#[tokio::test]
async fn test_install_refuses_overwrite_without_force() {
let dir = tempdir().unwrap();
let wasm_path = dir.path().join("telegram.wasm");
fs::write(&wasm_path, b"custom").await.unwrap();
let result = install_bundled_channel("telegram", dir.path(), false).await;
// Either fails because artifacts missing OR because file exists
assert!(result.is_err());
// Original file should be untouched
let existing = fs::read(&wasm_path).await.unwrap();
assert_eq!(existing, b"custom");
}
}
+14 -32
View File
@@ -16,21 +16,16 @@ use crate::channels::wasm::error::WasmChannelError;
use crate::channels::wasm::runtime::WasmChannelRuntime;
use crate::channels::wasm::schema::ChannelCapabilitiesFile;
use crate::channels::wasm::wrapper::WasmChannel;
use crate::pairing::PairingStore;
/// Loads WASM channels from the filesystem.
pub struct WasmChannelLoader {
runtime: Arc<WasmChannelRuntime>,
pairing_store: Arc<PairingStore>,
}
impl WasmChannelLoader {
/// Create a new loader with the given runtime and pairing store.
pub fn new(runtime: Arc<WasmChannelRuntime>, pairing_store: Arc<PairingStore>) -> Self {
Self {
runtime,
pairing_store,
}
/// Create a new loader with the given runtime.
pub fn new(runtime: Arc<WasmChannelRuntime>) -> Self {
Self { runtime }
}
/// Load a single WASM channel from a file pair.
@@ -119,13 +114,7 @@ impl WasmChannelLoader {
.await?;
// Create the channel
let channel = WasmChannel::new(
self.runtime.clone(),
prepared,
capabilities,
config_json,
self.pairing_store.clone(),
);
let channel = WasmChannel::new(self.runtime.clone(), prepared, capabilities, config_json);
tracing::info!(
name = name,
@@ -162,18 +151,17 @@ impl WasmChannelLoader {
}
let mut results = LoadResults::default();
// Collect all .wasm entries first, then load in parallel
let mut channel_entries = Vec::new();
let mut entries = fs::read_dir(dir).await?;
while let Some(entry) = entries.next_entry().await? {
let path = entry.path();
// Only process .wasm files
if path.extension().and_then(|e| e.to_str()) != Some("wasm") {
continue;
}
// Extract channel name from filename
let name = match path.file_stem().and_then(|s| s.to_str()) {
Some(n) => n.to_string(),
None => {
@@ -185,20 +173,15 @@ impl WasmChannelLoader {
}
};
// Look for sidecar capabilities file
let cap_path = path.with_extension("capabilities.json");
let has_cap = cap_path.exists();
channel_entries.push((name, path, if has_cap { Some(cap_path) } else { None }));
}
let cap_path_option = if cap_path.exists() {
Some(cap_path.as_path())
} else {
None
};
// Load all channels in parallel (file I/O + WASM compilation)
let load_futures = channel_entries
.iter()
.map(|(name, path, cap_path)| self.load_from_files(name, path, cap_path.as_deref()));
let load_results = futures::future::join_all(load_futures).await;
for ((name, path, _), result) in channel_entries.into_iter().zip(load_results) {
match result {
match self.load_from_files(&name, &path, cap_path_option).await {
Ok(loaded) => {
results.loaded.push(loaded);
}
@@ -363,7 +346,6 @@ mod tests {
use crate::channels::wasm::loader::{WasmChannelLoader, discover_channels};
use crate::channels::wasm::runtime::{WasmChannelRuntime, WasmChannelRuntimeConfig};
use crate::pairing::PairingStore;
use std::sync::Arc;
#[tokio::test]
@@ -420,7 +402,7 @@ mod tests {
async fn test_loader_invalid_name() {
let config = WasmChannelRuntimeConfig::for_testing();
let runtime = Arc::new(WasmChannelRuntime::new(config).unwrap());
let loader = WasmChannelLoader::new(runtime, Arc::new(PairingStore::new()));
let loader = WasmChannelLoader::new(runtime);
let dir = TempDir::new().unwrap();
let wasm_path = dir.path().join("test.wasm");
+3 -3
View File
@@ -78,7 +78,6 @@
//! }
//! ```
mod bundled;
mod capabilities;
mod error;
mod host;
@@ -89,7 +88,6 @@ mod schema;
mod wrapper;
// Core types
pub use bundled::{available_channel_names, bundled_channel_names, install_bundled_channel};
pub use capabilities::{ChannelCapabilities, EmitRateLimitConfig, HttpEndpointConfig, PollConfig};
pub use error::WasmChannelError;
pub use host::{ChannelEmitRateLimiter, ChannelHostState, EmittedMessage};
@@ -97,7 +95,9 @@ pub use loader::{
DiscoveredChannel, LoadResults, LoadedChannel, WasmChannelLoader, default_channels_dir,
discover_channels,
};
pub use router::{RegisteredEndpoint, WasmChannelRouter, create_wasm_channel_router};
pub use router::{
RegisteredEndpoint, WasmChannelRouter, WasmChannelServer, create_wasm_channel_router,
};
pub use runtime::{PreparedChannelModule, WasmChannelRuntime, WasmChannelRuntimeConfig};
pub use schema::{
ChannelCapabilitiesFile, ChannelConfig, SecretSetupSchema, SetupSchema, WebhookSchema,
+51 -2
View File
@@ -4,6 +4,7 @@
//! registered paths. Handles secret validation at the host level.
use std::collections::HashMap;
use std::net::SocketAddr;
use std::sync::Arc;
use axum::{
@@ -468,6 +469,56 @@ pub fn create_wasm_channel_router(
.with_state(state)
}
/// HTTP server for WASM channel webhooks.
pub struct WasmChannelServer {
router: Arc<WasmChannelRouter>,
extension_manager: Option<Arc<crate::extensions::ExtensionManager>>,
}
impl WasmChannelServer {
/// Create a new server.
pub fn new(router: Arc<WasmChannelRouter>) -> Self {
Self {
router,
extension_manager: None,
}
}
/// Set the extension manager for OAuth callback handling.
pub fn with_extension_manager(
mut self,
manager: Arc<crate::extensions::ExtensionManager>,
) -> Self {
self.extension_manager = Some(manager);
self
}
/// Start the HTTP server.
///
/// Returns a handle that can be used to shut down the server.
pub async fn start(
&self,
addr: SocketAddr,
) -> Result<tokio::task::JoinHandle<()>, std::io::Error> {
let app = create_wasm_channel_router(self.router.clone(), self.extension_manager.clone());
let listener = tokio::net::TcpListener::bind(addr).await?;
tracing::info!(
addr = %addr,
"WASM channel HTTP server started"
);
let handle = tokio::spawn(async move {
if let Err(e) = axum::serve(listener, app).await {
tracing::error!("WASM channel HTTP server error: {}", e);
}
});
Ok(handle)
}
}
#[cfg(test)]
mod tests {
use std::sync::Arc;
@@ -478,7 +529,6 @@ mod tests {
PreparedChannelModule, WasmChannelRuntime, WasmChannelRuntimeConfig,
};
use crate::channels::wasm::wrapper::WasmChannel;
use crate::pairing::PairingStore;
use crate::tools::wasm::ResourceLimits;
fn create_test_channel(name: &str) -> Arc<WasmChannel> {
@@ -500,7 +550,6 @@ mod tests {
prepared,
capabilities,
"{}".to_string(),
Arc::new(PairingStore::new()),
))
}
+53 -413
View File
@@ -48,7 +48,6 @@ use crate::channels::wasm::runtime::{PreparedChannelModule, WasmChannelRuntime};
use crate::channels::wasm::schema::ChannelConfig;
use crate::channels::{Channel, IncomingMessage, MessageStream, OutgoingResponse, StatusUpdate};
use crate::error::ChannelError;
use crate::pairing::PairingStore;
use crate::safety::LeakDetector;
use crate::tools::wasm::LogLevel;
use crate::tools::wasm::WasmResourceLimiter;
@@ -74,11 +73,6 @@ struct ChannelStoreData {
/// Injected credentials for URL substitution (e.g., bot tokens).
/// Keys are placeholder names like "TELEGRAM_BOT_TOKEN".
credentials: HashMap<String, String>,
/// Pairing store for DM pairing (guest access control).
pairing_store: Arc<PairingStore>,
/// Dedicated tokio runtime for HTTP requests, lazily initialized.
/// Reused across multiple `http_request` calls within one execution.
http_runtime: Option<tokio::runtime::Runtime>,
}
impl ChannelStoreData {
@@ -87,7 +81,6 @@ impl ChannelStoreData {
channel_name: &str,
capabilities: ChannelCapabilities,
credentials: HashMap<String, String>,
pairing_store: Arc<PairingStore>,
) -> Self {
// Create a minimal WASI context (no filesystem, no env vars for security)
let wasi = WasiCtxBuilder::new().build();
@@ -98,8 +91,6 @@ impl ChannelStoreData {
wasi,
table: ResourceTable::new(),
credentials,
pairing_store,
http_runtime: None,
}
}
@@ -138,34 +129,18 @@ impl ChannelStoreData {
if result.contains('{') && result.contains('}') {
// Only warn if it looks like an unresolved placeholder (not JSON braces)
let brace_pattern = regex::Regex::new(r"\{[A-Z_]+\}").ok();
if let Some(re) = brace_pattern
&& re.is_match(&result)
{
tracing::warn!(
context = %context,
"String may contain unresolved credential placeholders"
);
if let Some(re) = brace_pattern {
if re.is_match(&result) {
tracing::warn!(
context = %context,
"String may contain unresolved credential placeholders"
);
}
}
}
result
}
/// Replace injected credential values with `[REDACTED]` in text.
///
/// Prevents credentials from leaking through error messages, logs, or
/// return values to WASM. reqwest::Error includes the full URL in its
/// Display output, so any error from an injected-URL request will
/// contain the raw credential unless we scrub it.
fn redact_credentials(&self, text: &str) -> String {
let mut result = text.to_string();
for (name, value) in &self.credentials {
if !value.is_empty() {
result = result.replace(value, &format!("[REDACTED:{}]", name));
}
}
result
}
}
// Implement WasiView to provide WASI context and resource table
@@ -212,7 +187,6 @@ impl near::agent::channel_host::Host for ChannelStoreData {
url: String,
headers_json: String,
body: Option<Vec<u8>>,
timeout_ms: Option<u32>,
) -> Result<near::agent::channel_host::HttpResponse, String> {
tracing::info!(
method = %method,
@@ -277,35 +251,10 @@ impl near::agent::channel_host::Host for ChannelStoreData {
.scan_http_request(&url, &header_vec, body.as_deref())
.map_err(|e| format!("Potential secret leak blocked: {}", e))?;
// Get the max response size from capabilities (default 10MB).
let max_response_bytes = self
.host_state
.capabilities()
.tool_capabilities
.http
.as_ref()
.map(|h| h.max_response_bytes)
.unwrap_or(10 * 1024 * 1024);
// Make the HTTP request using a dedicated single-threaded runtime.
// We're inside spawn_blocking, so we can't rely on the main runtime's
// I/O driver (it may be busy with WASM compilation or other startup work).
// A dedicated runtime gives us our own I/O driver and avoids contention.
// The runtime is lazily created and reused across calls within one execution.
if self.http_runtime.is_none() {
self.http_runtime = Some(
tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.map_err(|e| format!("Failed to create HTTP runtime: {e}"))?,
);
}
let rt = self.http_runtime.as_ref().expect("just initialized");
let result = rt.block_on(async {
let client = reqwest::Client::builder()
.connect_timeout(std::time::Duration::from_secs(10))
.build()
.map_err(|e| format!("Failed to build HTTP client: {e}"))?;
// Make the HTTP request using blocking I/O
// We're already in a spawn_blocking context, so we can use block_on
let result = tokio::runtime::Handle::current().block_on(async {
let client = reqwest::Client::new();
let mut request = match method.to_uppercase().as_str() {
"GET" => client.get(&url),
@@ -327,21 +276,12 @@ impl near::agent::channel_host::Host for ChannelStoreData {
request = request.body(body_bytes);
}
// Send request with caller-specified timeout (default 30s, max 5min).
let timeout_ms = timeout_ms.unwrap_or(30_000).min(300_000) as u64;
let timeout = std::time::Duration::from_millis(timeout_ms);
let response = request.timeout(timeout).send().await.map_err(|e| {
// Walk the full error chain so we get the actual root cause
// (DNS, TLS, connection refused, etc.) instead of just
// "error sending request for url (...)".
let mut chain = format!("HTTP request failed: {}", e);
let mut source = std::error::Error::source(&e);
while let Some(cause) = source {
chain.push_str(&format!(" -> {}", cause));
source = cause.source();
}
chain
})?;
// Send request with timeout
let response = request
.timeout(std::time::Duration::from_secs(30))
.send()
.await
.map_err(|e| format!("HTTP request failed: {}", e))?;
let status = response.status().as_u16();
let response_headers: std::collections::HashMap<String, String> = response
@@ -354,29 +294,11 @@ impl near::agent::channel_host::Host for ChannelStoreData {
})
.collect();
let headers_json = serde_json::to_string(&response_headers).unwrap_or_default();
// Enforce max response body size to prevent memory exhaustion.
let max_response = max_response_bytes;
if let Some(cl) = response.content_length()
&& cl as usize > max_response
{
return Err(format!(
"Response body too large: {} bytes exceeds limit of {} bytes",
cl, max_response
));
}
let body = response
.bytes()
.await
.map_err(|e| format!("Failed to read response body: {}", e))?;
if body.len() > max_response {
return Err(format!(
"Response body too large: {} bytes exceeds limit of {} bytes",
body.len(),
max_response
));
}
let body = body.to_vec();
.map_err(|e| format!("Failed to read response body: {}", e))?
.to_vec();
tracing::info!(
status = status,
@@ -408,11 +330,6 @@ impl near::agent::channel_host::Host for ChannelStoreData {
})
});
// Scrub credential values from error messages before logging or returning
// to WASM. reqwest::Error includes the full URL (with injected credentials)
// in its Display output.
let result = result.map_err(|e| self.redact_credentials(&e));
match &result {
Ok(resp) => {
tracing::info!(status = resp.status, "http_request completed successfully");
@@ -455,43 +372,6 @@ impl near::agent::channel_host::Host for ChannelStoreData {
}
}
}
fn pairing_upsert_request(
&mut self,
channel: String,
id: String,
meta_json: String,
) -> Result<near::agent::channel_host::PairingUpsertResult, String> {
let meta = if meta_json.is_empty() {
None
} else {
serde_json::from_str(&meta_json).ok()
};
match self.pairing_store.upsert_request(&channel, &id, meta) {
Ok(r) => Ok(near::agent::channel_host::PairingUpsertResult {
code: r.code,
created: r.created,
}),
Err(e) => Err(e.to_string()),
}
}
fn pairing_is_allowed(
&mut self,
channel: String,
id: String,
username: Option<String>,
) -> Result<bool, String> {
self.pairing_store
.is_sender_allowed(&channel, &id, username.as_deref())
.map_err(|e| e.to_string())
}
fn pairing_read_allow_from(&mut self, channel: String) -> Result<Vec<String>, String> {
self.pairing_store
.read_allow_from(&channel)
.map_err(|e| e.to_string())
}
}
/// A WASM-based channel implementing the Channel trait.
@@ -544,9 +424,6 @@ pub struct WasmChannel {
/// Background task that repeats typing indicators every 4 seconds.
/// Telegram's "typing..." indicator expires after ~5s, so we refresh it.
typing_task: RwLock<Option<tokio::task::JoinHandle<()>>>,
/// Pairing store for DM pairing (guest access control).
pairing_store: Arc<PairingStore>,
}
impl WasmChannel {
@@ -556,7 +433,6 @@ impl WasmChannel {
prepared: Arc<PreparedChannelModule>,
capabilities: ChannelCapabilities,
config_json: String,
pairing_store: Arc<PairingStore>,
) -> Self {
let name = prepared.name.clone();
let rate_limiter = ChannelEmitRateLimiter::new(capabilities.emit_rate_limit.clone());
@@ -576,7 +452,6 @@ impl WasmChannel {
endpoints: RwLock::new(Vec::new()),
credentials: Arc::new(RwLock::new(HashMap::new())),
typing_task: RwLock::new(None),
pairing_store,
}
}
@@ -658,7 +533,6 @@ impl WasmChannel {
prepared: &PreparedChannelModule,
capabilities: &ChannelCapabilities,
credentials: HashMap<String, String>,
pairing_store: Arc<PairingStore>,
) -> Result<Store<ChannelStoreData>, WasmChannelError> {
let engine = runtime.engine();
let limits = &prepared.limits;
@@ -669,7 +543,6 @@ impl WasmChannel {
&prepared.name,
capabilities.clone(),
credentials,
pairing_store,
);
let mut store = Store::new(engine, store_data);
@@ -770,18 +643,12 @@ impl WasmChannel {
let timeout = self.runtime.config().callback_timeout;
let channel_name = self.name.clone();
let credentials = self.get_credentials().await;
let pairing_store = self.pairing_store.clone();
// Execute in blocking task with timeout
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
// Call on_start using the generated typed interface
@@ -814,21 +681,7 @@ impl WasmChannel {
.await;
match result {
Ok(Ok((config, mut host_state))) => {
// Surface WASM guest logs (errors/warnings from webhook setup, etc.)
for entry in host_state.take_logs() {
match entry.level {
crate::tools::wasm::LogLevel::Error => {
tracing::error!(channel = %self.name, "{}", entry.message);
}
crate::tools::wasm::LogLevel::Warn => {
tracing::warn!(channel = %self.name, "{}", entry.message);
}
_ => {
tracing::debug!(channel = %self.name, "{}", entry.message);
}
}
}
Ok(Ok((config, _host_state))) => {
tracing::info!(
channel = %self.name,
display_name = %config.display_name,
@@ -900,7 +753,6 @@ impl WasmChannel {
let capabilities = self.capabilities.clone();
let timeout = self.runtime.config().callback_timeout;
let credentials = self.get_credentials().await;
let pairing_store = self.pairing_store.clone();
// Prepare request data
let method = method.to_string();
@@ -914,13 +766,8 @@ impl WasmChannel {
// Execute in blocking task with timeout
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
// Build the WIT request type
@@ -993,18 +840,12 @@ impl WasmChannel {
let timeout = self.runtime.config().callback_timeout;
let channel_name = self.name.clone();
let credentials = self.get_credentials().await;
let pairing_store = self.pairing_store.clone();
// Execute in blocking task with timeout
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
// Call on_poll using the generated typed interface
@@ -1088,7 +929,6 @@ impl WasmChannel {
let timeout = self.runtime.config().callback_timeout;
let channel_name = self.name.clone();
let credentials = self.get_credentials().await;
let pairing_store = self.pairing_store.clone();
// Prepare response data
let message_id_str = message_id.to_string();
@@ -1102,13 +942,8 @@ impl WasmChannel {
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
tracing::info!("Creating WASM store for on_respond");
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials)?;
tracing::info!("Instantiating WASM component for on_respond");
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
@@ -1201,19 +1036,13 @@ impl WasmChannel {
let timeout = self.runtime.config().callback_timeout;
let channel_name = self.name.clone();
let credentials = self.get_credentials().await;
let pairing_store = self.pairing_store.clone();
let wit_update = status_to_wit(status, metadata);
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
let channel_iface = instance.near_agent_channel();
@@ -1251,14 +1080,12 @@ impl WasmChannel {
///
/// Static method for use by the background typing repeat task (which
/// doesn't have access to `&self`).
#[allow(clippy::too_many_arguments)]
async fn execute_status(
channel_name: &str,
runtime: &Arc<WasmChannelRuntime>,
prepared: &Arc<PreparedChannelModule>,
capabilities: &ChannelCapabilities,
credentials: &RwLock<HashMap<String, String>>,
pairing_store: Arc<PairingStore>,
timeout: Duration,
wit_update: wit_channel::StatusUpdate,
) -> Result<(), WasmChannelError> {
@@ -1274,13 +1101,8 @@ impl WasmChannel {
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials_snapshot,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials_snapshot)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
let channel_iface = instance.near_agent_channel();
@@ -1348,7 +1170,6 @@ impl WasmChannel {
let prepared = Arc::clone(&self.prepared);
let capabilities = self.capabilities.clone();
let credentials = self.credentials.clone();
let pairing_store = self.pairing_store.clone();
let callback_timeout = self.runtime.config().callback_timeout;
let wit_update = status_to_wit(&status, metadata);
@@ -1368,7 +1189,6 @@ impl WasmChannel {
&prepared,
&capabilities,
&credentials,
pairing_store.clone(),
callback_timeout,
wit_update_clone,
)
@@ -1499,7 +1319,6 @@ impl WasmChannel {
let message_tx = self.message_tx.clone();
let rate_limiter = self.rate_limiter.clone();
let credentials = self.credentials.clone();
let pairing_store = self.pairing_store.clone();
let callback_timeout = self.runtime.config().callback_timeout;
tokio::spawn(async move {
@@ -1521,15 +1340,14 @@ impl WasmChannel {
&prepared,
&capabilities,
&credentials,
pairing_store.clone(),
callback_timeout,
).await;
match result {
Ok(emitted_messages) => {
// Process any emitted messages
if !emitted_messages.is_empty()
&& let Err(e) = Self::dispatch_emitted_messages(
if !emitted_messages.is_empty() {
if let Err(e) = Self::dispatch_emitted_messages(
&channel_name,
emitted_messages,
&message_tx,
@@ -1541,6 +1359,7 @@ impl WasmChannel {
"Failed to dispatch emitted messages from poll"
);
}
}
}
Err(e) => {
tracing::warn!(
@@ -1572,7 +1391,6 @@ impl WasmChannel {
prepared: &Arc<PreparedChannelModule>,
capabilities: &ChannelCapabilities,
credentials: &RwLock<HashMap<String, String>>,
pairing_store: Arc<PairingStore>,
timeout: Duration,
) -> Result<Vec<EmittedMessage>, WasmChannelError> {
// Skip if no WASM bytes (testing mode)
@@ -1593,13 +1411,8 @@ impl WasmChannel {
// Execute in blocking task with timeout
let result = tokio::time::timeout(timeout, async move {
tokio::task::spawn_blocking(move || {
let mut store = Self::create_store(
&runtime,
&prepared,
&capabilities,
credentials_snapshot,
pairing_store,
)?;
let mut store =
Self::create_store(&runtime, &prepared, &capabilities, credentials_snapshot)?;
let instance = Self::instantiate_component(&runtime, &prepared, &mut store)?;
// Call on_poll using the generated typed interface
@@ -1770,22 +1583,22 @@ impl Channel for WasmChannel {
*self.endpoints.write().await = endpoints;
// Start polling if configured
if let Some(poll_config) = &config.poll
&& poll_config.enabled
{
let interval = self
.capabilities
.validate_poll_interval(poll_config.interval_ms)
.map_err(|e| ChannelError::StartupFailed {
name: self.name.clone(),
reason: e,
})?;
if let Some(poll_config) = &config.poll {
if poll_config.enabled {
let interval = self
.capabilities
.validate_poll_interval(poll_config.interval_ms)
.map_err(|e| ChannelError::StartupFailed {
name: self.name.clone(),
reason: e,
})?;
// Create shutdown channel for polling and store the sender to keep it alive
let (poll_shutdown_tx, poll_shutdown_rx) = oneshot::channel();
*self.poll_shutdown_tx.write().await = Some(poll_shutdown_tx);
// Create shutdown channel for polling and store the sender to keep it alive
let (poll_shutdown_tx, poll_shutdown_rx) = oneshot::channel();
*self.poll_shutdown_tx.write().await = Some(poll_shutdown_tx);
self.start_polling(Duration::from_millis(interval as u64), poll_shutdown_rx);
self.start_polling(Duration::from_millis(interval as u64), poll_shutdown_rx);
}
}
tracing::info!(
@@ -2013,11 +1826,6 @@ fn status_to_wit(status: &StatusUpdate, metadata: &serde_json::Value) -> wit_cha
message: format!("{}: {}", name, if *success { "ok" } else { "failed" }),
metadata_json,
},
StatusUpdate::ToolResult { name, preview } => wit_channel::StatusUpdate {
status: wit_channel::StatusType::ToolCompleted,
message: format!("{}: {}", name, preview),
metadata_json,
},
StatusUpdate::StreamChunk(chunk) => wit_channel::StatusUpdate {
status: wit_channel::StatusType::Thinking,
message: chunk.clone(),
@@ -2036,38 +1844,6 @@ fn status_to_wit(status: &StatusUpdate, metadata: &serde_json::Value) -> wit_cha
metadata_json,
}
}
StatusUpdate::ApprovalNeeded {
tool_name,
description,
..
} => wit_channel::StatusUpdate {
status: wit_channel::StatusType::Thinking,
message: format!("Approval needed: {} - {}", tool_name, description),
metadata_json,
},
StatusUpdate::JobStarted { job_id, title, .. } => wit_channel::StatusUpdate {
status: wit_channel::StatusType::Thinking,
message: format!("Job started: {} ({})", title, job_id),
metadata_json,
},
StatusUpdate::AuthRequired { extension_name, .. } => wit_channel::StatusUpdate {
status: wit_channel::StatusType::Thinking,
message: format!("Auth required: {}", extension_name),
metadata_json,
},
StatusUpdate::AuthCompleted {
extension_name,
success,
..
} => wit_channel::StatusUpdate {
status: wit_channel::StatusType::Thinking,
message: format!(
"Auth {}: {}",
if *success { "completed" } else { "failed" },
extension_name
),
metadata_json,
},
}
}
@@ -2139,7 +1915,6 @@ mod tests {
PreparedChannelModule, WasmChannelRuntime, WasmChannelRuntimeConfig,
};
use crate::channels::wasm::wrapper::{HttpResponse, WasmChannel};
use crate::pairing::PairingStore;
use crate::tools::wasm::ResourceLimits;
fn create_test_channel() -> WasmChannel {
@@ -2155,13 +1930,7 @@ mod tests {
let capabilities = ChannelCapabilities::for_channel("test").with_path("/webhook/test");
WasmChannel::new(
runtime,
prepared,
capabilities,
"{}".to_string(),
Arc::new(PairingStore::new()),
)
WasmChannel::new(runtime, prepared, capabilities, "{}".to_string())
}
#[test]
@@ -2236,7 +2005,6 @@ mod tests {
&prepared,
&capabilities,
&credentials,
Arc::new(PairingStore::new()),
timeout,
)
.await;
@@ -2330,13 +2098,7 @@ mod tests {
.with_path("/webhook/poll")
.with_polling(1000);
let channel = WasmChannel::new(
runtime,
prepared,
capabilities,
"{}".to_string(),
Arc::new(PairingStore::new()),
);
let channel = WasmChannel::new(runtime, prepared, capabilities, "{}".to_string());
// Start the channel
let _stream = channel.start().await.expect("Channel should start");
@@ -2574,126 +2336,4 @@ mod tests {
assert_eq!(cloned.message, "hello");
assert_eq!(cloned.metadata_json, "{\"a\":1}");
}
#[test]
fn test_redact_credentials_replaces_values() {
use super::ChannelStoreData;
let mut creds = std::collections::HashMap::new();
creds.insert(
"TELEGRAM_BOT_TOKEN".to_string(),
"8218490433:AAEZeUxwqZ5OO3mOCXv7fKvpdhDgsmBBNis".to_string(),
);
creds.insert("OTHER_SECRET".to_string(), "s3cret".to_string());
let store = ChannelStoreData::new(
1024 * 1024,
"test",
ChannelCapabilities::default(),
creds,
Arc::new(PairingStore::new()),
);
let error = "HTTP request failed: error sending request for url \
(https://api.telegram.org/bot8218490433:AAEZeUxwqZ5OO3mOCXv7fKvpdhDgsmBBNis/getUpdates)";
let redacted = store.redact_credentials(error);
assert!(
!redacted.contains("8218490433:AAEZeUxwqZ5OO3mOCXv7fKvpdhDgsmBBNis"),
"credential value should be redacted"
);
assert!(
redacted.contains("[REDACTED:TELEGRAM_BOT_TOKEN]"),
"redacted text should contain placeholder name"
);
assert!(
!redacted.contains("s3cret"),
"other credentials should also be redacted"
);
}
#[test]
fn test_redact_credentials_no_op_without_credentials() {
use super::ChannelStoreData;
let store = ChannelStoreData::new(
1024 * 1024,
"test",
ChannelCapabilities::default(),
std::collections::HashMap::new(),
Arc::new(PairingStore::new()),
);
let input = "some error message";
assert_eq!(store.redact_credentials(input), input);
}
#[test]
fn test_redact_credentials_skips_empty_values() {
use super::ChannelStoreData;
let mut creds = std::collections::HashMap::new();
creds.insert("EMPTY_TOKEN".to_string(), String::new());
let store = ChannelStoreData::new(
1024 * 1024,
"test",
ChannelCapabilities::default(),
creds,
Arc::new(PairingStore::new()),
);
let input = "should not match anything";
assert_eq!(store.redact_credentials(input), input);
}
/// Verify that WASM HTTP host functions work using a dedicated
/// current-thread runtime inside spawn_blocking.
#[tokio::test]
async fn test_dedicated_runtime_inside_spawn_blocking() {
let result = tokio::task::spawn_blocking(|| {
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.expect("failed to build runtime");
rt.block_on(async { 42 })
})
.await
.expect("spawn_blocking panicked");
assert_eq!(result, 42);
}
/// Verify a real HTTP request works using the dedicated-runtime pattern.
/// This catches DNS, TLS, and I/O driver issues that trivial tests miss.
#[tokio::test]
#[ignore] // requires network
async fn test_dedicated_runtime_real_http() {
let result = tokio::task::spawn_blocking(|| {
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.expect("failed to build runtime");
rt.block_on(async {
let client = reqwest::Client::builder()
.connect_timeout(std::time::Duration::from_secs(10))
.build()
.expect("failed to build client");
let resp = client
.get("https://api.telegram.org/bot000/getMe")
.timeout(std::time::Duration::from_secs(10))
.send()
.await;
match resp {
Ok(r) => r.status().as_u16(),
Err(e) if e.is_timeout() => panic!("request timed out: {e}"),
Err(e) => panic!("unexpected error: {e}"),
}
})
})
.await
.expect("spawn_blocking panicked");
// 404 because "000" is not a valid bot token
assert_eq!(result, 404);
}
}
-62
View File
@@ -1,62 +0,0 @@
//! Bearer token authentication middleware for the web gateway.
use axum::{
extract::{Request, State},
http::{HeaderMap, StatusCode},
middleware::Next,
response::{IntoResponse, Response},
};
use subtle::ConstantTimeEq;
/// Shared auth state injected via axum middleware state.
#[derive(Clone)]
pub struct AuthState {
pub token: String,
}
/// Auth middleware that validates bearer token from header or query param.
///
/// SSE connections can't set headers from `EventSource`, so we also accept
/// `?token=xxx` as a query parameter.
pub async fn auth_middleware(
State(auth): State<AuthState>,
headers: HeaderMap,
request: Request,
next: Next,
) -> Response {
// Try Authorization header first (constant-time comparison)
if let Some(auth_header) = headers.get("authorization")
&& let Ok(value) = auth_header.to_str()
&& let Some(token) = value.strip_prefix("Bearer ")
&& bool::from(token.as_bytes().ct_eq(auth.token.as_bytes()))
{
return next.run(request).await;
}
// Fall back to query parameter for SSE EventSource (constant-time comparison)
if let Some(query) = request.uri().query() {
for pair in query.split('&') {
if let Some(token) = pair.strip_prefix("token=")
&& bool::from(token.as_bytes().ct_eq(auth.token.as_bytes()))
{
return next.run(request).await;
}
}
}
(StatusCode::UNAUTHORIZED, "Invalid or missing auth token").into_response()
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_auth_state_clone() {
let state = AuthState {
token: "test-token".to_string(),
};
let cloned = state.clone();
assert_eq!(cloned.token, "test-token");
}
}
-358
View File
@@ -1,358 +0,0 @@
//! Tracing layer that broadcasts log events to the web gateway via SSE.
//!
//! ```text
//! tracing::info!("...")
//! │
//! ▼
//! WebLogLayer::on_event()
//! │
//! ▼
//! LogBroadcaster::send()
//! │
//! ├──► broadcast::Sender<LogEntry> (live subscribers)
//! └──► ring buffer (recent history for late joiners)
//! │
//! ▼
//! SSE /api/logs/events
//! ```
use std::collections::VecDeque;
use std::sync::{Arc, Mutex};
use serde::Serialize;
use tokio::sync::broadcast;
use tracing::field::{Field, Visit};
use tracing_subscriber::Layer;
use crate::safety::LeakDetector;
/// Maximum number of recent log entries kept for late-joining SSE subscribers.
const HISTORY_CAP: usize = 500;
/// A single log entry broadcast to connected clients.
#[derive(Debug, Clone, Serialize)]
pub struct LogEntry {
pub level: String,
pub target: String,
pub message: String,
pub timestamp: String,
}
/// Broadcasts log entries to SSE subscribers.
///
/// Created early in main.rs (before tracing init), shared with both
/// the tracing layer and the gateway's SSE endpoint.
///
/// Keeps a ring buffer of recent entries so browsers that connect
/// after startup still see the boot log.
pub struct LogBroadcaster {
tx: broadcast::Sender<LogEntry>,
recent: Mutex<VecDeque<LogEntry>>,
/// Scrubs secrets from log messages before broadcasting to SSE clients.
leak_detector: LeakDetector,
}
impl LogBroadcaster {
pub fn new() -> Self {
let (tx, _) = broadcast::channel(512);
Self {
tx,
recent: Mutex::new(VecDeque::with_capacity(HISTORY_CAP)),
leak_detector: LeakDetector::new(),
}
}
pub fn send(&self, mut entry: LogEntry) {
// Scrub secrets from the message before it reaches any subscriber.
// This is defense-in-depth: even if code elsewhere accidentally logs
// a secret, it won't be broadcast to SSE clients.
entry.message = self
.leak_detector
.scan_and_clean(&entry.message)
.unwrap_or_else(|_| "[log message redacted: contained blocked secret]".to_string());
// Stash in ring buffer (for late joiners)
if let Ok(mut buf) = self.recent.lock() {
if buf.len() >= HISTORY_CAP {
buf.pop_front();
}
buf.push_back(entry.clone());
}
// Broadcast to live subscribers (ok to drop if nobody listening)
let _ = self.tx.send(entry);
}
/// Subscribe to the live event stream.
pub fn subscribe(&self) -> broadcast::Receiver<LogEntry> {
self.tx.subscribe()
}
/// Snapshot of recent entries for replaying to a new subscriber.
pub fn recent_entries(&self) -> Vec<LogEntry> {
self.recent
.lock()
.map(|buf| buf.iter().cloned().collect())
.unwrap_or_default()
}
}
impl Default for LogBroadcaster {
fn default() -> Self {
Self::new()
}
}
/// Visitor that extracts the `message` field and all extra key-value
/// fields from a tracing event.
///
/// The terminal formatter shows something like:
/// INFO ironclaw::agent: Request completed url="http://..." status=200
///
/// We replicate that by capturing both the message and the extra fields.
struct MessageVisitor {
message: String,
fields: Vec<String>,
}
impl MessageVisitor {
fn new() -> Self {
Self {
message: String::new(),
fields: Vec::new(),
}
}
/// Build the final message string: "message key=val key=val ..."
fn finish(self) -> String {
if self.fields.is_empty() {
self.message
} else {
format!("{} {}", self.message, self.fields.join(" "))
}
}
}
impl Visit for MessageVisitor {
fn record_debug(&mut self, field: &Field, value: &dyn std::fmt::Debug) {
if field.name() == "message" {
self.message = format!("{:?}", value);
// Strip surrounding quotes from Debug output
if self.message.starts_with('"') && self.message.ends_with('"') {
self.message = self.message[1..self.message.len() - 1].to_string();
}
} else {
self.fields.push(format!("{}={:?}", field.name(), value));
}
}
fn record_str(&mut self, field: &Field, value: &str) {
if field.name() == "message" {
self.message = value.to_string();
} else {
self.fields.push(format!("{}={}", field.name(), value));
}
}
}
/// Tracing layer that forwards events to a [`LogBroadcaster`].
///
/// Only forwards DEBUG and above. Attach to the tracing subscriber
/// alongside the existing fmt layer.
///
/// Log messages are scrubbed through `LeakDetector` in `LogBroadcaster::send()`
/// (the single funnel point for all log output, including late-joiner history).
pub struct WebLogLayer {
broadcaster: Arc<LogBroadcaster>,
}
impl WebLogLayer {
pub fn new(broadcaster: Arc<LogBroadcaster>) -> Self {
Self { broadcaster }
}
}
impl<S: tracing::Subscriber> Layer<S> for WebLogLayer {
fn on_event(
&self,
event: &tracing::Event<'_>,
_ctx: tracing_subscriber::layer::Context<'_, S>,
) {
let metadata = event.metadata();
// Only forward DEBUG+
if *metadata.level() > tracing::Level::DEBUG {
return;
}
let mut visitor = MessageVisitor::new();
event.record(&mut visitor);
let entry = LogEntry {
level: metadata.level().to_string().to_uppercase(),
target: metadata.target().to_string(),
message: visitor.finish(),
timestamp: chrono::Utc::now().to_rfc3339_opts(chrono::SecondsFormat::Millis, true),
};
// LeakDetector scrubbing happens inside broadcaster.send()
self.broadcaster.send(entry);
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_log_broadcaster_creation() {
let broadcaster = LogBroadcaster::new();
// Should not panic with no receivers
broadcaster.send(LogEntry {
level: "INFO".to_string(),
target: "test".to_string(),
message: "hello".to_string(),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
});
}
#[test]
fn test_log_broadcaster_subscribe() {
let broadcaster = LogBroadcaster::new();
let mut rx = broadcaster.subscribe();
broadcaster.send(LogEntry {
level: "WARN".to_string(),
target: "ironclaw::test".to_string(),
message: "test warning".to_string(),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
});
let entry = rx.try_recv().expect("should receive entry");
assert_eq!(entry.level, "WARN");
assert_eq!(entry.message, "test warning");
}
#[test]
fn test_log_entry_serialization() {
let entry = LogEntry {
level: "ERROR".to_string(),
target: "ironclaw::agent".to_string(),
message: "something broke".to_string(),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
};
let json = serde_json::to_string(&entry).expect("should serialize");
assert!(json.contains("\"level\":\"ERROR\""));
assert!(json.contains("something broke"));
}
#[test]
fn test_recent_entries_buffer() {
let broadcaster = LogBroadcaster::new();
for i in 0..5 {
broadcaster.send(LogEntry {
level: "INFO".to_string(),
target: "test".to_string(),
message: format!("msg {}", i),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
});
}
let recent = broadcaster.recent_entries();
assert_eq!(recent.len(), 5);
assert_eq!(recent[0].message, "msg 0");
assert_eq!(recent[4].message, "msg 4");
}
#[test]
fn test_recent_entries_cap() {
let broadcaster = LogBroadcaster::new();
// Overflow the buffer
for i in 0..(HISTORY_CAP + 50) {
broadcaster.send(LogEntry {
level: "INFO".to_string(),
target: "test".to_string(),
message: format!("msg {}", i),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
});
}
let recent = broadcaster.recent_entries();
assert_eq!(recent.len(), HISTORY_CAP);
// Oldest should be msg 50 (first 50 evicted)
assert_eq!(recent[0].message, "msg 50");
}
#[test]
fn test_recent_entries_available_without_subscribers() {
let broadcaster = LogBroadcaster::new();
// No subscribe() call, just send
broadcaster.send(LogEntry {
level: "INFO".to_string(),
target: "test".to_string(),
message: "before anyone listened".to_string(),
timestamp: "2024-01-01T00:00:00.000Z".to_string(),
});
let recent = broadcaster.recent_entries();
assert_eq!(recent.len(), 1);
assert_eq!(recent[0].message, "before anyone listened");
}
#[test]
fn test_message_visitor_finish_message_only() {
let v = MessageVisitor {
message: "hello world".to_string(),
fields: vec![],
};
assert_eq!(v.finish(), "hello world");
}
#[test]
fn test_message_visitor_finish_with_fields() {
let v = MessageVisitor {
message: "Request completed".to_string(),
fields: vec![
"url=http://localhost:8080".to_string(),
"status=200".to_string(),
],
};
let result = v.finish();
assert_eq!(
result,
"Request completed url=http://localhost:8080 status=200"
);
}
#[test]
fn test_message_visitor_finish_empty() {
let v = MessageVisitor::new();
assert_eq!(v.finish(), "");
}
#[test]
fn test_broadcaster_has_leak_detector() {
let broadcaster = LogBroadcaster::new();
// Verify the leak detector is initialized with default patterns
assert!(broadcaster.leak_detector.pattern_count() > 0);
}
#[test]
fn test_leak_detector_scrubs_api_key_in_log() {
let detector = crate::safety::LeakDetector::new();
let msg = "Connecting with token sk-proj-test1234567890abcdefghij";
let result = detector.scan_and_clean(msg);
// Should be blocked (OpenAI key pattern)
assert!(result.is_err());
}
#[test]
fn test_leak_detector_passes_clean_log() {
let detector = crate::safety::LeakDetector::new();
let msg = "Request completed status=200 url=https://api.example.com/data";
let result = detector.scan_and_clean(msg);
assert!(result.is_ok());
assert_eq!(result.unwrap(), msg);
}
}
-346
View File
@@ -1,346 +0,0 @@
//! Web gateway channel for browser-based access to IronClaw.
//!
//! Provides a single-page web UI with:
//! - Chat with the agent (via REST + SSE)
//! - Workspace/memory browsing
//! - Job management
//!
//! ```text
//! Browser ─── POST /api/chat/send ──► Agent Loop
//! ◄── GET /api/chat/events ── SSE stream
//! ─── GET /api/chat/ws ─────► WebSocket (bidirectional)
//! ─── GET /api/memory/* ────► Workspace
//! ─── GET /api/jobs/* ──────► Database
//! ◄── GET / ───────────────── Static HTML/CSS/JS
//! ```
pub mod auth;
pub mod log_layer;
pub mod openai_compat;
pub mod server;
pub mod sse;
pub mod types;
pub mod ws;
use std::net::SocketAddr;
use std::sync::Arc;
use async_trait::async_trait;
use tokio::sync::mpsc;
use tokio_stream::wrappers::ReceiverStream;
use crate::agent::SessionManager;
use crate::channels::{Channel, IncomingMessage, MessageStream, OutgoingResponse, StatusUpdate};
use crate::config::GatewayConfig;
use crate::db::Database;
use crate::error::ChannelError;
use crate::extensions::ExtensionManager;
use crate::orchestrator::job_manager::ContainerJobManager;
use crate::tools::ToolRegistry;
use crate::workspace::Workspace;
use self::log_layer::LogBroadcaster;
use self::server::GatewayState;
use self::sse::SseManager;
use self::types::SseEvent;
/// Web gateway channel implementing the Channel trait.
pub struct GatewayChannel {
config: GatewayConfig,
state: Arc<GatewayState>,
/// The actual auth token in use (generated or from config).
auth_token: String,
}
impl GatewayChannel {
/// Create a new gateway channel.
///
/// If no auth token is configured, generates a random one and prints it.
pub fn new(config: GatewayConfig) -> Self {
let auth_token = config.auth_token.clone().unwrap_or_else(|| {
use rand::Rng;
let token: String = rand::thread_rng()
.sample_iter(&rand::distributions::Alphanumeric)
.take(32)
.map(char::from)
.collect();
token
});
let state = Arc::new(GatewayState {
msg_tx: tokio::sync::RwLock::new(None),
sse: SseManager::new(),
workspace: None,
session_manager: None,
log_broadcaster: None,
extension_manager: None,
tool_registry: None,
store: None,
job_manager: None,
prompt_queue: None,
user_id: config.user_id.clone(),
shutdown_tx: tokio::sync::RwLock::new(None),
ws_tracker: Some(Arc::new(ws::WsConnectionTracker::new())),
llm_provider: None,
chat_rate_limiter: server::RateLimiter::new(30, 60),
});
Self {
config,
state,
auth_token,
}
}
/// Helper to rebuild state, copying existing fields and applying a mutation.
fn rebuild_state(&mut self, mutate: impl FnOnce(&mut GatewayState)) {
let mut new_state = GatewayState {
msg_tx: tokio::sync::RwLock::new(None),
sse: SseManager::new(),
workspace: self.state.workspace.clone(),
session_manager: self.state.session_manager.clone(),
log_broadcaster: self.state.log_broadcaster.clone(),
extension_manager: self.state.extension_manager.clone(),
tool_registry: self.state.tool_registry.clone(),
store: self.state.store.clone(),
job_manager: self.state.job_manager.clone(),
prompt_queue: self.state.prompt_queue.clone(),
user_id: self.state.user_id.clone(),
shutdown_tx: tokio::sync::RwLock::new(None),
ws_tracker: self.state.ws_tracker.clone(),
llm_provider: self.state.llm_provider.clone(),
chat_rate_limiter: server::RateLimiter::new(30, 60),
};
mutate(&mut new_state);
self.state = Arc::new(new_state);
}
/// Inject the workspace reference for the memory API.
pub fn with_workspace(mut self, workspace: Arc<Workspace>) -> Self {
self.rebuild_state(|s| s.workspace = Some(workspace));
self
}
/// Inject the session manager for thread/session info.
pub fn with_session_manager(mut self, sm: Arc<SessionManager>) -> Self {
self.rebuild_state(|s| s.session_manager = Some(sm));
self
}
/// Inject the log broadcaster for the logs SSE endpoint.
pub fn with_log_broadcaster(mut self, lb: Arc<LogBroadcaster>) -> Self {
self.rebuild_state(|s| s.log_broadcaster = Some(lb));
self
}
/// Inject the extension manager for the extensions API.
pub fn with_extension_manager(mut self, em: Arc<ExtensionManager>) -> Self {
self.rebuild_state(|s| s.extension_manager = Some(em));
self
}
/// Inject the tool registry for the extensions API.
pub fn with_tool_registry(mut self, tr: Arc<ToolRegistry>) -> Self {
self.rebuild_state(|s| s.tool_registry = Some(tr));
self
}
/// Inject the database store for sandbox job persistence.
pub fn with_store(mut self, store: Arc<dyn Database>) -> Self {
self.rebuild_state(|s| s.store = Some(store));
self
}
/// Inject the container job manager for sandbox operations.
pub fn with_job_manager(mut self, jm: Arc<ContainerJobManager>) -> Self {
self.rebuild_state(|s| s.job_manager = Some(jm));
self
}
/// Inject the prompt queue for Claude Code follow-up prompts.
pub fn with_prompt_queue(
mut self,
pq: Arc<
tokio::sync::Mutex<
std::collections::HashMap<
uuid::Uuid,
std::collections::VecDeque<crate::orchestrator::api::PendingPrompt>,
>,
>,
>,
) -> Self {
self.rebuild_state(|s| s.prompt_queue = Some(pq));
self
}
/// Inject the LLM provider for OpenAI-compatible API proxy.
pub fn with_llm_provider(mut self, llm: Arc<dyn crate::llm::LlmProvider>) -> Self {
self.rebuild_state(|s| s.llm_provider = Some(llm));
self
}
/// Get the auth token (for printing to console on startup).
pub fn auth_token(&self) -> &str {
&self.auth_token
}
/// Get a reference to the shared gateway state (for the agent to push SSE events).
pub fn state(&self) -> &Arc<GatewayState> {
&self.state
}
}
#[async_trait]
impl Channel for GatewayChannel {
fn name(&self) -> &str {
"gateway"
}
async fn start(&self) -> Result<MessageStream, ChannelError> {
let (tx, rx) = mpsc::channel(256);
*self.state.msg_tx.write().await = Some(tx);
let addr: SocketAddr = format!("{}:{}", self.config.host, self.config.port)
.parse()
.map_err(|e| ChannelError::StartupFailed {
name: "gateway".to_string(),
reason: format!(
"Invalid address '{}:{}': {}",
self.config.host, self.config.port, e
),
})?;
server::start_server(addr, self.state.clone(), self.auth_token.clone()).await?;
Ok(Box::pin(ReceiverStream::new(rx)))
}
async fn respond(
&self,
msg: &IncomingMessage,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
let thread_id = msg.thread_id.clone().unwrap_or_default();
self.state.sse.broadcast(SseEvent::Response {
content: response.content,
thread_id,
});
Ok(())
}
async fn send_status(
&self,
status: StatusUpdate,
metadata: &serde_json::Value,
) -> Result<(), ChannelError> {
let thread_id = metadata
.get("thread_id")
.and_then(|v| v.as_str())
.map(String::from);
let event = match status {
StatusUpdate::Thinking(msg) => SseEvent::Thinking {
message: msg,
thread_id: thread_id.clone(),
},
StatusUpdate::ToolStarted { name } => SseEvent::ToolStarted {
name,
thread_id: thread_id.clone(),
},
StatusUpdate::ToolCompleted { name, success } => SseEvent::ToolCompleted {
name,
success,
thread_id: thread_id.clone(),
},
StatusUpdate::ToolResult { name, preview } => SseEvent::ToolResult {
name,
preview,
thread_id: thread_id.clone(),
},
StatusUpdate::StreamChunk(content) => SseEvent::StreamChunk {
content,
thread_id: thread_id.clone(),
},
StatusUpdate::Status(msg) => SseEvent::Status {
message: msg,
thread_id: thread_id.clone(),
},
StatusUpdate::JobStarted {
job_id,
title,
browse_url,
} => SseEvent::JobStarted {
job_id,
title,
browse_url,
},
StatusUpdate::ApprovalNeeded {
request_id,
tool_name,
description,
parameters,
} => SseEvent::ApprovalNeeded {
request_id,
tool_name,
description,
parameters: serde_json::to_string_pretty(&parameters)
.unwrap_or_else(|_| parameters.to_string()),
},
StatusUpdate::AuthRequired {
extension_name,
instructions,
auth_url,
setup_url,
} => SseEvent::AuthRequired {
extension_name,
instructions,
auth_url,
setup_url,
},
StatusUpdate::AuthCompleted {
extension_name,
success,
message,
} => SseEvent::AuthCompleted {
extension_name,
success,
message,
},
};
self.state.sse.broadcast(event);
Ok(())
}
async fn broadcast(
&self,
_user_id: &str,
response: OutgoingResponse,
) -> Result<(), ChannelError> {
self.state.sse.broadcast(SseEvent::Response {
content: response.content,
thread_id: String::new(),
});
Ok(())
}
async fn health_check(&self) -> Result<(), ChannelError> {
if self.state.msg_tx.read().await.is_some() {
Ok(())
} else {
Err(ChannelError::HealthCheckFailed {
name: "gateway".to_string(),
})
}
}
async fn shutdown(&self) -> Result<(), ChannelError> {
if let Some(tx) = self.state.shutdown_tx.write().await.take() {
let _ = tx.send(());
}
*self.state.msg_tx.write().await = None;
Ok(())
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More