Compare commits

..
Author SHA1 Message Date
Illia PolosukhinandClaude Opus 4.6 274175184e feat: unified event bus, sealed state machines, and startup verification
Introduce a unified EventBus as the single broadcast channel for all
system events, replacing the 6 disconnected event mechanisms. Seal
Thread/Turn/ContainerState fields behind private accessors with validated
transitions to prevent invalid state mutations. Fix TOCTOU races in
thread_ops and session_manager.

Event bus (src/event_bus/):
- SystemEvent envelope with EventPayload (Domain, StateChange, Telemetry,
  StateTransition, ToolExecution, AuthEvent, ConfigChange)
- Four sinks: SSE (→SseManager), audit (→DB with JSONL fallback),
  state (→StateBus), metrics (→Observer)
- AuditStore trait + implementations for PostgreSQL and libSQL
- V13 audit_log migration for both backends
- Wired into AppComponents and AgentDeps (Option<EventBus> for compat)
- Worker dual-emit through bus alongside legacy SSE+DB paths

Sealed state machines:
- Thread.state private with state() accessor, can_transition_to(),
  set_processing(), reset_to_idle()
- Turn.state private with state() accessor
- ContainerHandle.state private with new() constructor,
  mark_running/stopped/failed(), can_transition_to()
- TOCTOU fix: thread_ops moves safety validation before lock, then
  checks state + starts turn atomically under single lock
- SessionManager TOCTOU fix: atomic check-and-insert with write lock
  held for entire UUID adoption sequence

Startup verification:
- AppComponents::verify_readiness() checks component presence vs config
- ToolRegistry::verify_expected_tools() validates builtin registration
- Config::validate() checks cross-field invariants (Docker, WASM dir)

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-03-16 00:54:21 -07:00
Illia Polosukhin 6fc652a24d Merge remote-tracking branch 'origin/staging' into refactor/architectural-hardening
# Conflicts:
#	src/agent/routine.rs
2026-03-15 22:07:55 -07:00
Illia PolosukhinandClaude Opus 4.6 b04d14b114 refactor: decouple modules, add resilience middleware and state bus [skip-regression-check]
Break circular dependencies between agent, db, channels, and context
modules by extracting shared domain types to neutral locations:

- Extract routine types to src/models/routine.rs
- Extract ToolFailureRecord to src/models/tool_failure.rs
- Move SseEvent to src/events.rs as DomainEvent
- Move HttpInterceptor to src/observability/
- Move truncate_preview to src/util.rs

Add generic resilience middleware (src/resilience/):
- ErrorClassifier, RetryLayer, CircuitBreakerLayer, HealthTracker

Add state invalidation bus (src/state_bus.rs)
Add boundary chaos tests (tests/boundary_chaos.rs)

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-03-14 21:17:25 -07:00
157 changed files with 7010 additions and 11955 deletions
-5
View File
@@ -18,11 +18,6 @@ DATABASE_POOL_SIZE=10
# === OpenAI Direct ===
# OPENAI_API_KEY=sk-...
# Reuse Codex CLI auth.json instead of setting OPENAI_API_KEY manually.
# Works with both OpenAI API-key mode and Codex ChatGPT OAuth mode.
# In ChatGPT mode this uses the private `chatgpt.com/backend-api/codex` endpoint.
# LLM_USE_CODEX_AUTH=true
# CODEX_AUTH_PATH=~/.codex/auth.json
# === NEAR AI (Chat Completions API) ===
# Two auth modes:
+2 -6
View File
@@ -5,8 +5,6 @@ on:
- cron: "0 6 * * 1" # Weekly Monday 6 AM UTC
workflow_dispatch:
pull_request:
branches:
- main
paths:
- "src/channels/web/**"
- "tests/e2e/**"
@@ -52,11 +50,9 @@ jobs:
- group: core
files: "tests/e2e/scenarios/test_connection.py tests/e2e/scenarios/test_chat.py tests/e2e/scenarios/test_sse_reconnect.py tests/e2e/scenarios/test_html_injection.py tests/e2e/scenarios/test_csp.py"
- group: features
files: "tests/e2e/scenarios/test_skills.py tests/e2e/scenarios/test_tool_approval.py tests/e2e/scenarios/test_webhook.py"
files: "tests/e2e/scenarios/test_skills.py tests/e2e/scenarios/test_tool_approval.py"
- group: extensions
files: "tests/e2e/scenarios/test_extensions.py tests/e2e/scenarios/test_extension_oauth.py tests/e2e/scenarios/test_telegram_token_validation.py tests/e2e/scenarios/test_telegram_hot_activation.py tests/e2e/scenarios/test_wasm_lifecycle.py tests/e2e/scenarios/test_tool_execution.py tests/e2e/scenarios/test_pairing.py tests/e2e/scenarios/test_mcp_auth_flow.py tests/e2e/scenarios/test_oauth_credential_fallback.py tests/e2e/scenarios/test_routine_oauth_credential_injection.py"
- group: routines
files: "tests/e2e/scenarios/test_owner_scope.py tests/e2e/scenarios/test_routine_event_batch.py"
files: "tests/e2e/scenarios/test_extensions.py tests/e2e/scenarios/test_extension_oauth.py tests/e2e/scenarios/test_wasm_lifecycle.py tests/e2e/scenarios/test_tool_execution.py tests/e2e/scenarios/test_pairing.py tests/e2e/scenarios/test_oauth_credential_fallback.py tests/e2e/scenarios/test_routine_oauth_credential_injection.py"
steps:
- uses: actions/checkout@v6
+3 -30
View File
@@ -17,10 +17,7 @@ jobs:
matrix:
include:
- name: all-features
# Keep product feature coverage broad without pulling in the
# test-only `integration` feature, which is exercised separately
# in the heavy integration job below.
flags: "--no-default-features --features postgres,libsql,html-to-markdown,bedrock,import"
flags: "--features postgres,libsql,html-to-markdown"
- name: default
flags: ""
- name: libsql-only
@@ -42,26 +39,6 @@ jobs:
- name: Run Tests
run: cargo test ${{ matrix.flags }} -- --nocapture
heavy-integration-tests:
name: Heavy Integration Tests
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v6
- name: Install Rust
uses: dtolnay/rust-toolchain@stable
with:
targets: wasm32-wasip2
- uses: Swatinem/rust-cache@v2
with:
key: heavy-integration
- name: Build Telegram WASM channel
run: cargo build --manifest-path channels-src/telegram/Cargo.toml --target wasm32-wasip2 --release
- name: Run thread scheduling integration tests
run: cargo test --no-default-features --features libsql,integration --test e2e_thread_scheduling -- --nocapture
- name: Run Telegram thread-scope regression test
run: cargo test --features integration --test telegram_auth_integration test_private_messages_use_chat_id_as_thread_scope -- --exact
telegram-tests:
name: Telegram Channel Tests
if: >
@@ -88,7 +65,7 @@ jobs:
matrix:
include:
- name: all-features
flags: "--no-default-features --features postgres,libsql,html-to-markdown,bedrock,import"
flags: "--all-features"
- name: default
flags: ""
- name: libsql-only
@@ -172,7 +149,7 @@ jobs:
name: Run Tests
runs-on: ubuntu-latest
if: always()
needs: [tests, heavy-integration-tests, telegram-tests, wasm-wit-compat, docker-build, windows-build, version-check, bench-compile]
needs: [tests, telegram-tests, wasm-wit-compat, docker-build, windows-build, version-check, bench-compile]
steps:
- run: |
# Unit tests must always pass
@@ -180,10 +157,6 @@ jobs:
echo "Unit tests failed"
exit 1
fi
if [[ "${{ needs.heavy-integration-tests.result }}" != "success" ]]; then
echo "Heavy integration tests failed"
exit 1
fi
# Gated jobs: must pass on promotion PRs / push, skipped on developer PRs
for job in telegram-tests wasm-wit-compat docker-build windows-build version-check bench-compile; do
case "$job" in
-6
View File
@@ -33,9 +33,3 @@ trace_*.json
# Local Claude Code settings (machine-specific, should not be committed)
.claude/settings.local.json
.worktrees/
# Python cache
__pycache__/
*.pyc
*.pyo
*.pyd
Generated
+4 -5
View File
@@ -3461,7 +3461,6 @@ dependencies = [
"dirs 6.0.0",
"dotenvy",
"ed25519-dalek",
"eventsource-stream",
"flate2",
"fs4",
"futures",
@@ -4365,9 +4364,9 @@ dependencies = [
[[package]]
name = "openssl"
version = "0.10.76"
version = "0.10.75"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "951c002c75e16ea2c65b8c7e4d3d51d5530d8dfa7d060b4776828c88cfb18ecf"
checksum = "08838db121398ad17ab8531ce9de97b244589089e290a384c900cb9ff7434328"
dependencies = [
"bitflags 2.11.0",
"cfg-if",
@@ -4403,9 +4402,9 @@ checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
[[package]]
name = "openssl-sys"
version = "0.9.112"
version = "0.9.111"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "57d55af3b3e226502be1526dfdba67ab0e9c96fc293004e79576b2b9edb0dbdb"
checksum = "82cab2d520aa75e3c58898289429321eb788c3106963d0dc886ec7a5f4adc321"
dependencies = [
"cc",
"libc",
-7
View File
@@ -40,7 +40,6 @@ eula = false
tokio = { version = "1", features = ["full"] }
tokio-stream = { version = "0.1", features = ["sync"] }
futures = "0.3"
eventsource-stream = "0.2"
# HTTP client
reqwest = { version = "0.12", default-features = false, features = ["json", "multipart", "rustls-tls-native-roots", "stream"] }
@@ -222,17 +221,11 @@ postgres = [
"rust_decimal/db-tokio-postgres",
]
libsql = ["dep:libsql"]
# Opt-in feature for especially heavy integration-test targets that run in a
# dedicated CI job instead of the default Rust test matrix.
integration = []
html-to-markdown = ["dep:html-to-markdown-rs", "dep:readabilityrs"]
bedrock = ["dep:aws-config", "dep:aws-sdk-bedrockruntime", "dep:aws-smithy-types"]
import = ["dep:json5", "libsql"]
[[test]]
name = "e2e_thread_scheduling"
required-features = ["libsql", "integration"]
[[test]]
name = "html_to_markdown"
required-features = ["html-to-markdown"]
+4 -4
View File
@@ -20,9 +20,9 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
|---------|----------|----------|-------|
| Hub-and-spoke architecture | ✅ | ✅ | Web gateway as central hub |
| WebSocket control plane | ✅ | ✅ | Gateway with WebSocket + SSE |
| Single-user system | ✅ | ✅ | Explicit instance owner scope for persistent routines, secrets, jobs, settings, extensions, and workspace memory |
| Single-user system | ✅ | ✅ | |
| Multi-agent routing | ✅ | ❌ | Workspace isolation per-agent |
| Session-based messaging | ✅ | ✅ | Owner scope is separate from sender identity and conversation scope |
| Session-based messaging | ✅ | ✅ | Per-sender sessions |
| Loopback-first networking | ✅ | ✅ | HTTP binds to 0.0.0.0 but can be configured |
### Owner: _Unassigned_
@@ -66,9 +66,9 @@ This document tracks feature parity between IronClaw (Rust implementation) and O
| CLI/TUI | ✅ | ✅ | - | Ratatui-based TUI |
| HTTP webhook | ✅ | ✅ | - | axum with secret validation |
| REPL (simple) | ✅ | ✅ | - | For testing |
| WASM channels | ❌ | ✅ | - | IronClaw innovation; host resolves owner scope vs sender identity |
| WASM channels | ❌ | ✅ | - | IronClaw innovation |
| WhatsApp | ✅ | ❌ | P1 | Baileys (Web), same-phone mode with echo detection |
| Telegram | ✅ | ✅ | - | WASM channel(MTProto), DM pairing, caption, /start, bot_username, DM topics, setup-time owner auto-verification, owner-scoped persistence |
| Telegram | ✅ | ✅ | - | WASM channel(MTProto), DM pairing, caption, /start, bot_username, DM topics |
| Discord | ✅ | ❌ | P2 | discord.js, thread parent binding inheritance |
| Signal | ✅ | ✅ | P2 | signal-cli daemonPC, SSE listener HTTP/JSON-R, user/group allowlists, DM pairing |
| Slack | ✅ | ✅ | - | WASM tool |
+3 -3
View File
@@ -61,7 +61,7 @@ fn bench_validate_tool_params(c: &mut Criterion) {
let validator = Validator::new();
let simple_params: serde_json::Value =
serde_json::from_str(r#"{"command": "echo hello"}"#).unwrap();
serde_json::from_str(r#"{"command": "echo hello"}"#).unwrap(); // safety: bench-only constant JSON
let complex_params: serde_json::Value = serde_json::from_str(
r#"{
@@ -73,7 +73,7 @@ fn bench_validate_tool_params(c: &mut Criterion) {
"capture_output": true
}"#,
)
.unwrap();
.unwrap(); // safety: bench-only constant JSON
// Deeply nested JSON to stress the recursive validation walk
let nested_params: serde_json::Value = serde_json::from_str(
@@ -84,7 +84,7 @@ fn bench_validate_tool_params(c: &mut Criterion) {
"env": {"KEY1": "val1", "KEY2": "val2", "KEY3": "val3", "KEY4": "val4"}
}"#,
)
.unwrap();
.unwrap(); // safety: bench-only constant JSON
group.bench_function("simple", |b| {
b.iter(|| validator.validate_tool_params(black_box(&simple_params)))
+69 -178
View File
@@ -100,14 +100,6 @@ struct TelegramMessage {
/// Sticker.
sticker: Option<TelegramSticker>,
/// Forum topic ID. Present when the message is sent inside a forum topic.
#[serde(default)]
message_thread_id: Option<i64>,
/// True when this message is sent inside a forum topic.
#[serde(default)]
is_topic_message: Option<bool>,
}
/// Telegram PhotoSize object.
@@ -298,10 +290,6 @@ struct TelegramMessageMetadata {
/// Whether this is a private (DM) chat.
is_private: bool,
/// Forum topic thread ID (for routing replies back to the correct topic).
#[serde(default, skip_serializing_if = "Option::is_none")]
message_thread_id: Option<i64>,
}
/// Channel configuration injected by host.
@@ -503,7 +491,8 @@ impl Guest for TelegramChannel {
// Delete any existing webhook before polling. Telegram returns success
// when no webhook exists, so any error here (e.g. 401) means a bad token.
delete_webhook().map_err(|e| format!("Bot token validation failed: {}", e))?;
delete_webhook()
.map_err(|e| format!("Bot token validation failed: {}", e))?;
}
// Configure polling only if not in webhook mode
@@ -691,12 +680,7 @@ impl Guest for TelegramChannel {
let metadata: TelegramMessageMetadata = serde_json::from_str(&response.metadata_json)
.map_err(|e| format!("Failed to parse metadata: {}", e))?;
send_response(
metadata.chat_id,
&response,
Some(metadata.message_id),
metadata.message_thread_id,
)
send_response(metadata.chat_id, &response, Some(metadata.message_id))
}
fn on_broadcast(user_id: String, response: AgentResponse) -> Result<(), String> {
@@ -704,7 +688,7 @@ impl Guest for TelegramChannel {
.parse()
.map_err(|e| format!("Invalid chat_id '{}': {}", user_id, e))?;
send_response(chat_id, &response, None, None)
send_response(chat_id, &response, None)
}
fn on_status(update: StatusUpdate) {
@@ -728,15 +712,11 @@ impl Guest for TelegramChannel {
match action {
TelegramStatusAction::Typing => {
// POST /sendChatAction with action "typing"
let mut payload = serde_json::json!({
let payload = serde_json::json!({
"chat_id": metadata.chat_id,
"action": "typing"
});
if let Some(thread_id) = metadata.message_thread_id {
payload["message_thread_id"] = serde_json::Value::Number(thread_id.into());
}
let payload_bytes = match serde_json::to_vec(&payload) {
Ok(b) => b,
Err(_) => return,
@@ -763,13 +743,9 @@ impl Guest for TelegramChannel {
}
TelegramStatusAction::Notify(prompt) => {
// Send user-visible status updates for actionable events.
if let Err(first_err) = send_message(
metadata.chat_id,
&prompt,
Some(metadata.message_id),
None,
metadata.message_thread_id,
) {
if let Err(first_err) =
send_message(metadata.chat_id, &prompt, Some(metadata.message_id), None)
{
channel_host::log(
channel_host::LogLevel::Warn,
&format!(
@@ -778,13 +754,7 @@ impl Guest for TelegramChannel {
),
);
if let Err(retry_err) = send_message(
metadata.chat_id,
&prompt,
None,
None,
metadata.message_thread_id,
) {
if let Err(retry_err) = send_message(metadata.chat_id, &prompt, None, None) {
channel_host::log(
channel_host::LogLevel::Debug,
&format!(
@@ -827,14 +797,6 @@ impl std::fmt::Display for SendError {
}
}
/// Normalize `message_thread_id` for outbound API calls.
///
/// Telegram rejects `sendMessage` and file-send methods when
/// `message_thread_id = 1` (the "General" topic), so omit it in that case.
fn normalize_thread_id(thread_id: Option<i64>) -> Option<i64> {
thread_id.filter(|&id| id != 1)
}
/// Send a message via the Telegram Bot API.
///
/// Returns the sent message_id on success. When `parse_mode` is set and
@@ -845,10 +807,7 @@ fn send_message(
text: &str,
reply_to_message_id: Option<i64>,
parse_mode: Option<&str>,
message_thread_id: Option<i64>,
) -> Result<i64, SendError> {
let message_thread_id = normalize_thread_id(message_thread_id);
let mut payload = serde_json::json!({
"chat_id": chat_id,
"text": text,
@@ -862,10 +821,6 @@ fn send_message(
payload["parse_mode"] = serde_json::Value::String(mode.to_string());
}
if let Some(thread_id) = message_thread_id {
payload["message_thread_id"] = serde_json::Value::Number(thread_id.into());
}
let payload_bytes = serde_json::to_vec(&payload)
.map_err(|e| SendError::Other(format!("Failed to serialize payload: {}", e)))?;
@@ -956,20 +911,19 @@ fn download_telegram_file(file_id: &str) -> Result<Vec<u8>, String> {
);
let headers = serde_json::json!({});
let result = channel_host::http_request("GET", &get_file_url, &headers.to_string(), None, None);
let result =
channel_host::http_request("GET", &get_file_url, &headers.to_string(), None, None);
let response = result.map_err(|e| format!("getFile request failed: {}", e))?;
if response.status != 200 {
let body_str = String::from_utf8_lossy(&response.body);
return Err(format!(
"getFile returned {}: {}",
response.status, body_str
));
return Err(format!("getFile returned {}: {}", response.status, body_str));
}
let api_response: TelegramApiResponse<TelegramFile> = serde_json::from_slice(&response.body)
.map_err(|e| format!("Failed to parse getFile response: {}", e))?;
let api_response: TelegramApiResponse<TelegramFile> =
serde_json::from_slice(&response.body)
.map_err(|e| format!("Failed to parse getFile response: {}", e))?;
if !api_response.ok {
return Err(format!(
@@ -999,12 +953,16 @@ fn download_telegram_file(file_id: &str) -> Result<Vec<u8>, String> {
file_path
);
let result = channel_host::http_request("GET", &download_url, &headers.to_string(), None, None);
let result =
channel_host::http_request("GET", &download_url, &headers.to_string(), None, None);
let response = result.map_err(|e| format!("File download failed: {}", e))?;
if response.status != 200 {
return Err(format!("File download returned status {}", response.status));
return Err(format!(
"File download returned status {}",
response.status
));
}
// Post-download size guard: Telegram metadata file_size is optional,
@@ -1078,10 +1036,7 @@ fn send_photo(
mime_type: &str,
data: &[u8],
reply_to_message_id: Option<i64>,
message_thread_id: Option<i64>,
) -> Result<(), String> {
let message_thread_id = normalize_thread_id(message_thread_id);
if data.len() > MAX_PHOTO_SIZE {
channel_host::log(
channel_host::LogLevel::Info,
@@ -1091,14 +1046,7 @@ fn send_photo(
data.len()
),
);
return send_document(
chat_id,
filename,
mime_type,
data,
reply_to_message_id,
message_thread_id,
);
return send_document(chat_id, filename, mime_type, data, reply_to_message_id);
}
let boundary = format!("ironclaw-{}", channel_host::now_millis());
@@ -1106,20 +1054,7 @@ fn send_photo(
write_multipart_field(&mut body, &boundary, "chat_id", &chat_id.to_string());
if let Some(msg_id) = reply_to_message_id {
write_multipart_field(
&mut body,
&boundary,
"reply_to_message_id",
&msg_id.to_string(),
);
}
if let Some(thread_id) = message_thread_id {
write_multipart_field(
&mut body,
&boundary,
"message_thread_id",
&thread_id.to_string(),
);
write_multipart_field(&mut body, &boundary, "reply_to_message_id", &msg_id.to_string());
}
write_multipart_file(&mut body, &boundary, "photo", filename, mime_type, data);
body.extend_from_slice(format!("--{}--\r\n", boundary).as_bytes());
@@ -1162,29 +1097,13 @@ fn send_document(
mime_type: &str,
data: &[u8],
reply_to_message_id: Option<i64>,
message_thread_id: Option<i64>,
) -> Result<(), String> {
let message_thread_id = normalize_thread_id(message_thread_id);
let boundary = format!("ironclaw-{}", channel_host::now_millis());
let mut body = Vec::new();
write_multipart_field(&mut body, &boundary, "chat_id", &chat_id.to_string());
if let Some(msg_id) = reply_to_message_id {
write_multipart_field(
&mut body,
&boundary,
"reply_to_message_id",
&msg_id.to_string(),
);
}
if let Some(thread_id) = message_thread_id {
write_multipart_field(
&mut body,
&boundary,
"message_thread_id",
&thread_id.to_string(),
);
write_multipart_field(&mut body, &boundary, "reply_to_message_id", &msg_id.to_string());
}
write_multipart_file(&mut body, &boundary, "document", filename, mime_type, data);
body.extend_from_slice(format!("--{}--\r\n", boundary).as_bytes());
@@ -1221,7 +1140,12 @@ fn send_document(
}
/// Image MIME types that Telegram's sendPhoto API supports.
const PHOTO_MIME_TYPES: &[&str] = &["image/jpeg", "image/png", "image/gif", "image/webp"];
const PHOTO_MIME_TYPES: &[&str] = &[
"image/jpeg",
"image/png",
"image/gif",
"image/webp",
];
/// Send a full agent response (attachments + text) to a chat.
///
@@ -1230,11 +1154,10 @@ fn send_response(
chat_id: i64,
response: &AgentResponse,
reply_to_message_id: Option<i64>,
message_thread_id: Option<i64>,
) -> Result<(), String> {
// Send attachments first (photos/documents)
for attachment in &response.attachments {
send_attachment(chat_id, attachment, reply_to_message_id, message_thread_id)?;
send_attachment(chat_id, attachment, reply_to_message_id)?;
}
// Skip text if empty and we already sent attachments
@@ -1243,23 +1166,13 @@ fn send_response(
}
// Try Markdown, fall back to plain text on parse errors
match send_message(
chat_id,
&response.content,
reply_to_message_id,
Some("Markdown"),
message_thread_id,
) {
match send_message(chat_id, &response.content, reply_to_message_id, Some("Markdown")) {
Ok(_) => Ok(()),
Err(SendError::ParseEntities(_)) => send_message(
chat_id,
&response.content,
reply_to_message_id,
None,
message_thread_id,
)
.map(|_| ())
.map_err(|e| format!("Plain-text retry also failed: {}", e)),
Err(SendError::ParseEntities(_)) => {
send_message(chat_id, &response.content, reply_to_message_id, None)
.map(|_| ())
.map_err(|e| format!("Plain-text retry also failed: {}", e))
}
Err(e) => Err(e.to_string()),
}
}
@@ -1269,7 +1182,6 @@ fn send_attachment(
chat_id: i64,
attachment: &Attachment,
reply_to_message_id: Option<i64>,
message_thread_id: Option<i64>,
) -> Result<(), String> {
if PHOTO_MIME_TYPES.contains(&attachment.mime_type.as_str()) {
send_photo(
@@ -1278,7 +1190,6 @@ fn send_attachment(
&attachment.mime_type,
&attachment.data,
reply_to_message_id,
message_thread_id,
)
} else {
send_document(
@@ -1287,7 +1198,6 @@ fn send_attachment(
&attachment.mime_type,
&attachment.data,
reply_to_message_id,
message_thread_id,
)
}
}
@@ -1427,10 +1337,7 @@ fn register_webhook(tunnel_url: &str, webhook_secret: Option<&str>) -> Result<()
let context = if retried { " (after retry)" } else { "" };
channel_host::log(
channel_host::LogLevel::Info,
&format!(
"Webhook registered successfully{}: {}",
context, webhook_url
),
&format!("Webhook registered successfully{}: {}", context, webhook_url),
);
Ok(())
@@ -1450,7 +1357,6 @@ fn send_pairing_reply(chat_id: i64, code: &str) -> Result<(), String> {
),
None,
Some("Markdown"),
None,
)
.map(|_| ())
.map_err(|e| e.to_string())
@@ -1532,9 +1438,7 @@ fn extract_attachments(message: &TelegramMessage) -> Vec<InboundAttachment> {
if let Some(ref doc) = message.document {
attachments.push(make_inbound_attachment(
doc.file_id.clone(),
doc.mime_type
.clone()
.unwrap_or_else(|| "application/octet-stream".to_string()),
doc.mime_type.clone().unwrap_or_else(|| "application/octet-stream".to_string()),
doc.file_name.clone(),
doc.file_size.map(|s| s as u64),
Some(get_file_url(&doc.file_id)),
@@ -1547,10 +1451,7 @@ fn extract_attachments(message: &TelegramMessage) -> Vec<InboundAttachment> {
if let Some(ref audio) = message.audio {
attachments.push(make_inbound_attachment(
audio.file_id.clone(),
audio
.mime_type
.clone()
.unwrap_or_else(|| "audio/mpeg".to_string()),
audio.mime_type.clone().unwrap_or_else(|| "audio/mpeg".to_string()),
audio.file_name.clone(),
audio.file_size.map(|s| s as u64),
Some(get_file_url(&audio.file_id)),
@@ -1563,10 +1464,7 @@ fn extract_attachments(message: &TelegramMessage) -> Vec<InboundAttachment> {
if let Some(ref video) = message.video {
attachments.push(make_inbound_attachment(
video.file_id.clone(),
video
.mime_type
.clone()
.unwrap_or_else(|| "video/mp4".to_string()),
video.mime_type.clone().unwrap_or_else(|| "video/mp4".to_string()),
video.file_name.clone(),
video.file_size.map(|s| s as u64),
Some(get_file_url(&video.file_id)),
@@ -1791,14 +1689,25 @@ fn handle_message(message: TelegramMessage) {
let is_private = message.chat.chat_type == "private";
let owner_id = channel_host::workspace_read(OWNER_ID_PATH)
.filter(|s| !s.is_empty())
.and_then(|s| s.parse::<i64>().ok());
let is_owner = owner_id == Some(from.id);
// 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 !is_owner {
// Non-owner senders remain guests. Apply authorization based on
// dm_policy / allow_from before letting them chat in their own scope.
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 {
// No owner_id: apply authorization based on dm_policy and allow_from
// This applies to both private and group chats when owner_id is null
let dm_policy =
channel_host::workspace_read(DM_POLICY_PATH).unwrap_or_else(|| "pairing".to_string());
@@ -1905,7 +1814,6 @@ fn handle_message(message: TelegramMessage) {
message_id: message.message_id,
user_id: from.id,
is_private,
message_thread_id: message.message_thread_id,
};
let metadata_json = serde_json::to_string(&metadata).unwrap_or_else(|_| "{}".to_string());
@@ -1930,7 +1838,7 @@ fn handle_message(message: TelegramMessage) {
user_id: from.id.to_string(),
user_name: Some(user_name),
content: content_to_emit,
thread_id: Some(message.chat.id.to_string()),
thread_id: None, // Telegram doesn't have threads in the same way
metadata_json,
attachments,
});
@@ -2530,11 +2438,7 @@ mod tests {
assert_eq!(attachments[0].id, "large_id"); // Largest photo
assert_eq!(attachments[0].mime_type, "image/jpeg");
assert_eq!(attachments[0].size_bytes, Some(54321));
assert!(attachments[0]
.source_url
.as_ref()
.unwrap()
.contains("large_id"));
assert!(attachments[0].source_url.as_ref().unwrap().contains("large_id"));
}
#[test]
@@ -2586,7 +2490,9 @@ mod tests {
attachments[0].filename.as_deref(),
Some("voice_voice_xyz.ogg")
);
assert!(attachments[0].extras_json.contains("\"duration_secs\":5"));
assert!(attachments[0]
.extras_json
.contains("\"duration_secs\":5"));
}
#[test]
@@ -2732,33 +2638,18 @@ mod tests {
};
// PDFs and Office docs should be downloaded
assert!(is_downloadable_document(&make(
"application/pdf",
Some("report.pdf")
)));
assert!(is_downloadable_document(&make("application/pdf", Some("report.pdf"))));
assert!(is_downloadable_document(&make(
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
Some("doc.docx"),
)));
assert!(is_downloadable_document(&make(
"text/plain",
Some("notes.txt")
)));
assert!(is_downloadable_document(&make("text/plain", Some("notes.txt"))));
// Voice, image, audio, video should NOT be downloaded
assert!(!is_downloadable_document(&make(
"audio/ogg",
Some("voice_123.ogg")
)));
assert!(!is_downloadable_document(&make("audio/ogg", Some("voice_123.ogg"))));
assert!(!is_downloadable_document(&make("image/jpeg", None)));
assert!(!is_downloadable_document(&make(
"audio/mpeg",
Some("song.mp3")
)));
assert!(!is_downloadable_document(&make(
"video/mp4",
Some("clip.mp4")
)));
assert!(!is_downloadable_document(&make("audio/mpeg", Some("song.mp3"))));
assert!(!is_downloadable_document(&make("video/mp4", Some("clip.mp4"))));
}
#[test]
+1 -1
View File
@@ -269,7 +269,7 @@ dependencies = [
[[package]]
name = "whatsapp-channel"
version = "0.2.0"
version = "0.1.0"
dependencies = [
"serde",
"serde_json",
+7 -7
View File
@@ -324,7 +324,7 @@ mod tests {
let violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"excessive_urls pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -349,7 +349,7 @@ mod tests {
let violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"obfuscated_string pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -370,7 +370,7 @@ mod tests {
let _violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"shell_injection pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -387,7 +387,7 @@ mod tests {
let _violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"sql_pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -405,7 +405,7 @@ mod tests {
let _violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"crypto_private_key pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -423,7 +423,7 @@ mod tests {
let _violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"system_file_access pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
@@ -441,7 +441,7 @@ mod tests {
let _violations = policy.check(&payload);
let elapsed = start.elapsed();
assert!(
elapsed.as_millis() < 500,
elapsed.as_millis() < 100,
"encoded_exploit pattern took {}ms on 100KB near-miss",
elapsed.as_millis()
);
+1 -1
View File
@@ -623,7 +623,7 @@ mod tests {
let combining_marks: Vec<char> =
(0x0300u32..=0x0331).filter_map(char::from_u32).collect();
assert!(combining_marks.len() >= 50);
let marks: String = combining_marks[..50].iter().collect();
let marks: String = combining_marks[..50].iter().collect(); // safety: Vec<char> slice, not byte slice
let input = format!("prefix a{marks}suffix padding to reach minimum length for check");
assert!(
!has_excessive_repetition(&input),
+24
View File
@@ -0,0 +1,24 @@
-- Append-only audit log for security-relevant system events.
-- No UPDATE or DELETE should ever be issued on this table.
CREATE TABLE IF NOT EXISTS audit_log (
id BIGSERIAL PRIMARY KEY,
event_id BIGINT NOT NULL,
event_type VARCHAR(64) NOT NULL,
source_module VARCHAR(64) NOT NULL,
source_component VARCHAR(64) NOT NULL,
category VARCHAR(32) NOT NULL,
session_id UUID,
thread_id UUID,
job_id UUID,
user_id VARCHAR(255),
payload JSONB NOT NULL DEFAULT '{}',
created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);
-- Indexes for common query patterns
CREATE INDEX IF NOT EXISTS idx_audit_log_created_at ON audit_log (created_at DESC);
CREATE INDEX IF NOT EXISTS idx_audit_log_job_id ON audit_log (job_id) WHERE job_id IS NOT NULL;
CREATE INDEX IF NOT EXISTS idx_audit_log_session_id ON audit_log (session_id) WHERE session_id IS NOT NULL;
CREATE INDEX IF NOT EXISTS idx_audit_log_user_id ON audit_log (user_id) WHERE user_id IS NOT NULL;
CREATE INDEX IF NOT EXISTS idx_audit_log_event_type ON audit_log (event_type);
@@ -1,11 +0,0 @@
-- Remove the legacy 'default' sentinel from routine notifications.
-- A NULL notify_user now means "resolve the configured owner's last-seen
-- channel target at send time."
ALTER TABLE routines
ALTER COLUMN notify_user DROP NOT NULL,
ALTER COLUMN notify_user DROP DEFAULT;
UPDATE routines
SET notify_user = NULL
WHERE notify_user = 'default';
+1 -1
View File
@@ -26,7 +26,7 @@ CREATE TABLE routines (
-- Notification preferences
notify_channel TEXT, -- NULL = use default
notify_user TEXT,
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,
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "discord",
"display_name": "Discord Channel",
"kind": "channel",
"version": "0.2.1",
"version": "0.2.0",
"wit_version": "0.3.0",
"description": "Talk to your agent in Discord",
"keywords": [
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "feishu",
"display_name": "Feishu / Lark Channel",
"kind": "channel",
"version": "0.1.1",
"version": "0.1.0",
"wit_version": "0.3.0",
"description": "Talk to your agent through a Feishu or Lark bot",
"keywords": [
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "telegram",
"display_name": "Telegram Channel",
"kind": "channel",
"version": "0.2.4",
"version": "0.2.3",
"wit_version": "0.3.0",
"description": "Talk to your agent through a Telegram bot",
"keywords": [
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "github",
"display_name": "GitHub",
"kind": "tool",
"version": "0.2.1",
"version": "0.2.0",
"wit_version": "0.3.0",
"description": "GitHub integration for issues, PRs, repos, and code search",
"keywords": [
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "web-search",
"display_name": "Web Search",
"kind": "tool",
"version": "0.2.1",
"version": "0.2.0",
"wit_version": "0.3.0",
"description": "Search the web using Brave Search API",
"keywords": [
+5 -2
View File
@@ -134,8 +134,11 @@ fi
# Excludes test files, test modules, and debug_assert (compiled out in release).
# Suppress with "// safety: <reason>".
PROD_DIFF="$DIFF_OUTPUT"
# Strip hunks from test-only files (tests/ directory, *_test.rs, test_*.rs)
PROD_DIFF=$(echo "$PROD_DIFF" | grep -v '^+++ b/tests/' || true)
# Strip all hunks from test-only files (tests/ directory, *_test.rs, test_*.rs, benches/)
PROD_DIFF=$(echo "$PROD_DIFF" | awk '
/^diff --git/ { in_test_file = ($0 ~ /tests\/|_test\.rs|test_.*\.rs|benches\//) }
!in_test_file { print }
' || true)
# Strip hunks whose @@ context line indicates a test module.
# git diff includes the enclosing function/module name after @@.
# Only match `mod tests` (the conventional #[cfg(test)] module) — do NOT
+39 -225
View File
@@ -22,7 +22,7 @@ use crate::channels::{ChannelManager, IncomingMessage, OutgoingResponse};
use crate::config::{AgentConfig, HeartbeatConfig, RoutineConfig, SkillsConfig};
use crate::context::ContextManager;
use crate::db::Database;
use crate::error::{ChannelError, Error};
use crate::error::Error;
use crate::extensions::ExtensionManager;
use crate::hooks::HookRegistry;
use crate::llm::LlmProvider;
@@ -54,75 +54,10 @@ pub(crate) fn truncate_for_preview(output: &str, max_chars: usize) -> String {
}
}
#[cfg(test)]
fn resolve_routine_notification_user(metadata: &serde_json::Value) -> Option<String> {
resolve_owner_scope_notification_user(
metadata.get("notify_user").and_then(|value| value.as_str()),
metadata.get("owner_id").and_then(|value| value.as_str()),
)
}
fn trimmed_option(value: Option<&str>) -> Option<String> {
value
.map(str::trim)
.filter(|value| !value.is_empty())
.map(ToOwned::to_owned)
}
fn resolve_owner_scope_notification_user(
explicit_user: Option<&str>,
owner_fallback: Option<&str>,
) -> Option<String> {
trimmed_option(explicit_user).or_else(|| trimmed_option(owner_fallback))
}
async fn resolve_channel_notification_user(
extension_manager: Option<&Arc<ExtensionManager>>,
channel: Option<&str>,
explicit_user: Option<&str>,
owner_fallback: Option<&str>,
) -> Option<String> {
if let Some(user) = trimmed_option(explicit_user) {
return Some(user);
}
if let Some(channel_name) = trimmed_option(channel)
&& let Some(extension_manager) = extension_manager
&& let Some(target) = extension_manager
.notification_target_for_channel(&channel_name)
.await
{
return Some(target);
}
resolve_owner_scope_notification_user(explicit_user, owner_fallback)
}
async fn resolve_routine_notification_target(
extension_manager: Option<&Arc<ExtensionManager>>,
metadata: &serde_json::Value,
) -> Option<String> {
resolve_channel_notification_user(
extension_manager,
metadata
.get("notify_channel")
.and_then(|value| value.as_str()),
metadata.get("notify_user").and_then(|value| value.as_str()),
metadata.get("owner_id").and_then(|value| value.as_str()),
)
.await
}
fn should_fallback_routine_notification(error: &ChannelError) -> bool {
!matches!(error, ChannelError::MissingRoutingTarget { .. })
}
/// Core dependencies for the agent.
///
/// Bundles the shared components to reduce argument count.
pub struct AgentDeps {
/// Resolved durable owner scope for the instance.
pub owner_id: String,
pub store: Option<Arc<dyn Database>>,
pub llm: Arc<dyn LlmProvider>,
/// Cheap/fast LLM for lightweight tasks (heartbeat, routing, evaluation).
@@ -139,7 +74,9 @@ pub struct AgentDeps {
/// Cost enforcement guardrails (daily budget, hourly rate limits).
pub cost_guard: Arc<crate::agent::cost_guard::CostGuard>,
/// SSE broadcast sender for live job event streaming to the web gateway.
pub sse_tx: Option<tokio::sync::broadcast::Sender<crate::channels::web::types::SseEvent>>,
pub sse_tx: Option<tokio::sync::broadcast::Sender<crate::events::DomainEvent>>,
/// Unified event bus. Optional for backward compatibility with tests.
pub event_bus: Option<crate::event_bus::EventBus>,
/// HTTP interceptor for trace recording/replay.
pub http_interceptor: Option<Arc<dyn crate::llm::recording::HttpInterceptor>>,
/// Audio transcription middleware for voice messages.
@@ -167,18 +104,6 @@ pub struct Agent {
}
impl Agent {
pub(super) fn owner_id(&self) -> &str {
if let Some(workspace) = self.deps.workspace.as_ref() {
debug_assert_eq!(
workspace.user_id(),
self.deps.owner_id,
"workspace.user_id() must stay aligned with deps.owner_id"
);
}
&self.deps.owner_id
}
/// Create a new agent.
///
/// Optionally accepts pre-created `ContextManager` and `SessionManager` for sharing
@@ -341,7 +266,6 @@ impl Agent {
));
let repair_interval = self.config.repair_check_interval;
let repair_channels = self.channels.clone();
let repair_owner_id = self.owner_id().to_string();
let repair_handle = tokio::spawn(async move {
loop {
tokio::time::sleep(repair_interval).await;
@@ -389,9 +313,7 @@ impl Agent {
if let Some(msg) = notification {
let response = OutgoingResponse::text(format!("Self-Repair: {}", msg));
let _ = repair_channels
.broadcast_all(&repair_owner_id, response)
.await;
let _ = repair_channels.broadcast_all("default", response).await;
}
}
@@ -405,9 +327,7 @@ impl Agent {
"Self-Repair: Tool '{}' repaired: {}",
tool.name, message
));
let _ = repair_channels
.broadcast_all(&repair_owner_id, response)
.await;
let _ = repair_channels.broadcast_all("default", response).await;
}
Ok(result) => {
tracing::info!("Tool repair result: {:?}", result);
@@ -444,12 +364,8 @@ impl Agent {
.timezone
.clone()
.or_else(|| Some(self.config.default_timezone.clone()));
let heartbeat_notify_user = resolve_owner_scope_notification_user(
hb_config.notify_user.as_deref(),
Some(self.owner_id()),
);
if let Some(channel) = &hb_config.notify_channel
&& let Some(user) = heartbeat_notify_user.as_deref()
if let (Some(user), Some(channel)) =
(&hb_config.notify_user, &hb_config.notify_channel)
{
config = config.with_notify(user, channel);
}
@@ -460,22 +376,15 @@ impl Agent {
// Spawn notification forwarder that routes through channel manager
let notify_channel = hb_config.notify_channel.clone();
let notify_target = resolve_channel_notification_user(
self.deps.extension_manager.as_ref(),
hb_config.notify_channel.as_deref(),
hb_config.notify_user.as_deref(),
Some(self.owner_id()),
)
.await;
let notify_user = heartbeat_notify_user;
let notify_user = hb_config.notify_user.clone();
let channels = self.channels.clone();
tokio::spawn(async move {
while let Some(response) = notify_rx.recv().await {
let user = notify_user.as_deref().unwrap_or("default");
// Try the configured channel first, fall back to
// broadcasting on all channels.
let targeted_ok = if let Some(ref channel) = notify_channel
&& let Some(ref user) = notify_target
{
let targeted_ok = if let Some(ref channel) = notify_channel {
channels
.broadcast(channel, user, response.clone())
.await
@@ -484,7 +393,7 @@ impl Agent {
false
};
if !targeted_ok && let Some(ref user) = notify_user {
if !targeted_ok {
let results = channels.broadcast_all(user, response).await;
for (ch, result) in results {
if let Err(e) = result {
@@ -553,60 +462,32 @@ impl Agent {
// Spawn notification forwarder (mirrors heartbeat pattern)
let channels = self.channels.clone();
let extension_manager = self.deps.extension_manager.clone();
tokio::spawn(async move {
while let Some(response) = notify_rx.recv().await {
let user = response
.metadata
.get("notify_user")
.and_then(|v| v.as_str())
.unwrap_or("default")
.to_string();
let notify_channel = response
.metadata
.get("notify_channel")
.and_then(|v| v.as_str())
.map(|s| s.to_string());
let fallback_user = resolve_owner_scope_notification_user(
response
.metadata
.get("notify_user")
.and_then(|v| v.as_str()),
response.metadata.get("owner_id").and_then(|v| v.as_str()),
);
let Some(user) = resolve_routine_notification_target(
extension_manager.as_ref(),
&response.metadata,
)
.await
else {
tracing::warn!(
notify_channel = ?notify_channel,
"Skipping routine notification with no explicit target or owner scope"
);
continue;
};
// Try the configured channel first, fall back to
// broadcasting on all channels.
let targeted_ok = if let Some(ref channel) = notify_channel {
match channels.broadcast(channel, &user, response.clone()).await {
Ok(()) => true,
Err(e) => {
let should_fallback =
should_fallback_routine_notification(&e);
tracing::warn!(
channel = %channel,
user = %user,
error = %e,
should_fallback,
"Failed to send routine notification to configured channel"
);
if !should_fallback {
continue;
}
false
}
}
channels
.broadcast(channel, &user, response.clone())
.await
.is_ok()
} else {
false
};
if !targeted_ok && let Some(user) = fallback_user {
if !targeted_ok {
let results = channels.broadcast_all(&user, response).await;
for (ch, result) in results {
if let Err(e) = result {
@@ -693,29 +574,6 @@ impl Agent {
// Store successfully extracted document text in workspace for indexing
self.store_extracted_documents(&message).await;
// Event-triggered routines consume plain user input before it enters
// the normal chat/tool pipeline. This avoids a duplicate turn where
// the main agent responds and the routine also fires on the same
// inbound message.
if !message.is_internal
&& matches!(
SubmissionParser::parse(&message.content),
Submission::UserInput { .. }
)
&& let Some(ref engine) = routine_engine_for_loop
{
let fired = engine.check_event_triggers(&message).await;
if fired > 0 {
tracing::debug!(
channel = %message.channel,
user = %message.user_id,
fired,
"Consumed inbound user message with matching event-triggered routine(s)"
);
continue;
}
}
match self.handle_message(&message).await {
Ok(Some(response)) if !response.is_empty() => {
// Hook: BeforeOutbound — allow hooks to modify or suppress outbound
@@ -788,6 +646,14 @@ impl Agent {
}
}
}
// Check event triggers (cheap in-memory regex, fires async if matched)
if let Some(ref engine) = routine_engine_for_loop {
let fired = engine.check_event_triggers(&message).await;
if fired > 0 {
tracing::debug!("Fired {} event-triggered routines", fired);
}
}
}
// Cleanup
@@ -904,7 +770,10 @@ impl Agent {
// For Signal, use signal_target from metadata (group:ID or phone number),
// otherwise fall back to user_id
let target = message
.routing_target()
.metadata
.get("signal_target")
.and_then(|v| v.as_str())
.map(|s| s.to_string())
.unwrap_or_else(|| message.user_id.clone());
self.tools()
.set_message_tool_context(Some(message.channel.clone()), Some(target))
@@ -944,7 +813,7 @@ impl Agent {
}
// Hydrate thread from DB if it's a historical thread not in memory
if let Some(external_thread_id) = message.conversation_scope() {
if let Some(ref external_thread_id) = message.thread_id {
tracing::trace!(
message_id = %message.id,
thread_id = %external_thread_id,
@@ -965,7 +834,7 @@ impl Agent {
.resolve_thread(
&message.user_id,
&message.channel,
message.conversation_scope(),
message.thread_id.as_deref(),
)
.await;
tracing::debug!(
@@ -1118,11 +987,7 @@ impl Agent {
#[cfg(test)]
mod tests {
use super::{
resolve_routine_notification_user, should_fallback_routine_notification,
truncate_for_preview,
};
use crate::error::ChannelError;
use super::truncate_for_preview;
#[test]
fn test_truncate_short_input() {
@@ -1185,55 +1050,4 @@ mod tests {
// 'h','e','l','l','o',' ','世','界' = 8 chars
assert_eq!(result, "hello 世界...");
}
#[test]
fn resolve_routine_notification_user_prefers_explicit_target() {
let metadata = serde_json::json!({
"notify_user": "12345",
"owner_id": "owner-scope",
});
let resolved = resolve_routine_notification_user(&metadata);
assert_eq!(resolved.as_deref(), Some("12345")); // safety: test-only assertion
}
#[test]
fn resolve_routine_notification_user_falls_back_to_owner_scope() {
let metadata = serde_json::json!({
"notify_user": null,
"owner_id": "owner-scope",
});
let resolved = resolve_routine_notification_user(&metadata);
assert_eq!(resolved.as_deref(), Some("owner-scope")); // safety: test-only assertion
}
#[test]
fn resolve_routine_notification_user_rejects_missing_values() {
let metadata = serde_json::json!({
"notify_user": " ",
});
assert_eq!(resolve_routine_notification_user(&metadata), None); // safety: test-only assertion
}
#[test]
fn targeted_routine_notifications_do_not_fallback_without_owner_route() {
let error = ChannelError::MissingRoutingTarget {
name: "telegram".to_string(),
reason: "No stored owner routing target for channel 'telegram'.".to_string(),
};
assert!(!should_fallback_routine_notification(&error)); // safety: test-only assertion
}
#[test]
fn targeted_routine_notifications_may_fallback_for_other_errors() {
let error = ChannelError::SendFailed {
name: "telegram".to_string(),
reason: "timeout talking to channel".to_string(),
};
assert!(should_fallback_routine_notification(&error)); // safety: test-only assertion
}
}
+1 -4
View File
@@ -836,10 +836,7 @@ impl Agent {
// 1. Persist to DB if available.
if let Some(store) = self.store() {
let value = serde_json::Value::String(model.to_string());
if let Err(e) = store
.set_setting(self.owner_id(), "selected_model", &value)
.await
{
if let Err(e) = store.set_setting("default", "selected_model", &value).await {
tracing::warn!("Failed to persist model to DB: {}", e);
}
}
+5 -7
View File
@@ -140,15 +140,13 @@ impl Agent {
// Create a JobContext for tool execution (chat doesn't have a real job)
let mut job_ctx =
JobContext::with_user(&message.user_id, "chat", "Interactive chat session")
.with_requester_id(&message.sender_id);
JobContext::with_user(&message.user_id, "chat", "Interactive chat session");
job_ctx.http_interceptor = self.deps.http_interceptor.clone();
job_ctx.user_timezone = user_tz.name().to_string();
job_ctx.metadata = serde_json::json!({
"notify_channel": message.channel,
"notify_user": message.user_id,
"notify_thread_id": message.thread_id,
"notify_metadata": message.metadata,
});
// Build system prompts once for this turn. Two variants: with tools
@@ -259,7 +257,7 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
async fn check_signals(&self) -> LoopSignal {
let sess = self.session.lock().await;
if let Some(thread) = sess.threads.get(&self.thread_id)
&& thread.state == ThreadState::Interrupted
&& thread.state() == ThreadState::Interrupted
{
return LoopSignal::Stop;
}
@@ -1177,7 +1175,6 @@ mod tests {
/// Build a minimal `Agent` for unit testing (no DB, no workspace, no extensions).
fn make_test_agent() -> Agent {
let deps = AgentDeps {
owner_id: "default".to_string(),
store: None,
llm: Arc::new(StaticLlmProvider),
cheap_llm: None,
@@ -1197,6 +1194,7 @@ mod tests {
http_interceptor: None,
transcription: None,
document_extraction: None,
event_bus: None,
};
Agent::new(
@@ -2017,7 +2015,6 @@ mod tests {
/// `max_tool_iterations` override.
fn make_test_agent_with_llm(llm: Arc<dyn LlmProvider>, max_tool_iterations: usize) -> Agent {
let deps = AgentDeps {
owner_id: "default".to_string(),
store: None,
llm,
cheap_llm: None,
@@ -2037,6 +2034,7 @@ mod tests {
http_interceptor: None,
transcription: None,
document_extraction: None,
event_bus: None,
};
Agent::new(
@@ -2131,7 +2129,6 @@ mod tests {
let max_iter = 3;
let agent = {
let deps = AgentDeps {
owner_id: "default".to_string(),
store: None,
llm,
cheap_llm: None,
@@ -2155,6 +2152,7 @@ mod tests {
http_interceptor: None,
transcription: None,
document_extraction: None,
event_bus: None,
};
Agent::new(
+11 -144
View File
@@ -26,8 +26,6 @@
use std::sync::Arc;
use std::time::Duration;
use chrono::TimeZone as _;
use chrono_tz::Tz;
use tokio::sync::mpsc;
use crate::channels::OutgoingResponse;
@@ -39,7 +37,7 @@ use crate::workspace::hygiene::HygieneConfig;
/// Configuration for the heartbeat runner.
#[derive(Debug, Clone)]
pub struct HeartbeatConfig {
/// Interval between heartbeat checks (used when fire_at is not set).
/// Interval between heartbeat checks.
pub interval: Duration,
/// Whether heartbeat is enabled.
pub enabled: bool,
@@ -49,13 +47,11 @@ pub struct HeartbeatConfig {
pub notify_user_id: Option<String>,
/// Channel to notify on heartbeat findings.
pub notify_channel: Option<String>,
/// Fixed time-of-day to fire (24h). When set, interval is ignored.
pub fire_at: Option<chrono::NaiveTime>,
/// Hour (0-23) when quiet hours start.
pub quiet_hours_start: Option<u32>,
/// Hour (0-23) when quiet hours end.
pub quiet_hours_end: Option<u32>,
/// Timezone for fire_at and quiet hours evaluation (IANA name).
/// Timezone for quiet hours evaluation (IANA name).
pub timezone: Option<String>,
}
@@ -67,7 +63,6 @@ impl Default for HeartbeatConfig {
max_failures: 3,
notify_user_id: None,
notify_channel: None,
fire_at: None,
quiet_hours_start: None,
quiet_hours_end: None,
timezone: None,
@@ -114,21 +109,6 @@ impl HeartbeatConfig {
self.notify_channel = Some(channel.into());
self
}
/// Set a fixed time-of-day to fire (overrides interval).
pub fn with_fire_at(mut self, time: chrono::NaiveTime, tz: Option<String>) -> Self {
self.fire_at = Some(time);
self.timezone = tz;
self
}
/// Resolve timezone string to chrono_tz::Tz (defaults to UTC).
fn resolved_tz(&self) -> Tz {
self.timezone
.as_deref()
.and_then(crate::timezone::parse_timezone)
.unwrap_or(chrono_tz::UTC)
}
}
/// Result of a heartbeat check.
@@ -144,33 +124,6 @@ pub enum HeartbeatResult {
Failed(String),
}
/// Compute how long to sleep until the next occurrence of `fire_at` in `tz`.
///
/// If the target time today is still in the future, sleep until then.
/// Otherwise sleep until the same time tomorrow.
fn duration_until_next_fire(fire_at: chrono::NaiveTime, tz: Tz) -> Duration {
let now = chrono::Utc::now().with_timezone(&tz);
let today = now.date_naive();
// Try to build today's target datetime in the given timezone.
// `.earliest()` picks the first occurrence if DST creates ambiguity.
let candidate = tz.from_local_datetime(&today.and_time(fire_at)).earliest();
let target = match candidate {
Some(t) if t > now => t,
_ => {
// Already past (or ambiguous) — schedule for tomorrow
let tomorrow = today + chrono::Duration::days(1);
tz.from_local_datetime(&tomorrow.and_time(fire_at))
.earliest()
.unwrap_or_else(|| now + chrono::Duration::days(1))
}
};
let secs = (target - now).num_seconds().max(1) as u64;
Duration::from_secs(secs)
}
/// Heartbeat runner for proactive periodic execution.
pub struct HeartbeatRunner {
config: HeartbeatConfig,
@@ -222,39 +175,17 @@ impl HeartbeatRunner {
return;
}
// Two scheduling modes:
// fire_at → sleep until the next occurrence (recalculated each iteration)
// interval → tokio::time::interval (drift-free, accounts for loop body time)
let mut tick_interval = if self.config.fire_at.is_none() {
let mut iv = tokio::time::interval(self.config.interval);
// Don't fire immediately on startup.
iv.tick().await;
Some(iv)
} else {
None
};
tracing::info!(
"Starting heartbeat loop with interval {:?}",
self.config.interval
);
if let Some(fire_at) = self.config.fire_at {
tracing::info!(
"Starting heartbeat loop: fire daily at {:?} {:?}",
fire_at,
self.config.timezone
);
} else {
tracing::info!(
"Starting heartbeat loop with interval {:?}",
self.config.interval
);
}
let mut interval = tokio::time::interval(self.config.interval);
// Don't run immediately on startup
interval.tick().await;
loop {
if let Some(fire_at) = self.config.fire_at {
let sleep_dur = duration_until_next_fire(fire_at, self.config.resolved_tz());
tracing::info!("Next heartbeat in {:.1}h", sleep_dur.as_secs_f64() / 3600.0);
tokio::time::sleep(sleep_dur).await;
} else if let Some(ref mut iv) = tick_interval {
iv.tick().await;
}
interval.tick().await;
// Skip during quiet hours
if self.config.is_quiet_hours() {
@@ -402,11 +333,7 @@ impl HeartbeatRunner {
return;
};
let user_id = self
.config
.notify_user_id
.as_deref()
.unwrap_or_else(|| self.workspace.user_id());
let user_id = self.config.notify_user_id.as_deref().unwrap_or("default");
// Persist to heartbeat conversation and get thread_id
let thread_id = if let Some(ref store) = self.store {
@@ -435,7 +362,6 @@ impl HeartbeatRunner {
attachments: Vec::new(),
metadata: serde_json::json!({
"source": "heartbeat",
"owner_id": self.workspace.user_id(),
}),
};
@@ -730,63 +656,4 @@ mod tests {
) -> tokio::task::JoinHandle<()> = spawn_heartbeat;
let _ = _fn_ptr;
}
// ==================== fire_at scheduling ====================
#[test]
fn test_default_config_has_no_fire_at() {
let config = HeartbeatConfig::default();
assert!(config.fire_at.is_none());
// Interval-based scheduling should be the default
assert_eq!(config.interval, Duration::from_secs(30 * 60));
}
#[test]
fn test_with_fire_at_builder() {
let time = chrono::NaiveTime::from_hms_opt(9, 0, 0).unwrap();
let config =
HeartbeatConfig::default().with_fire_at(time, Some("Pacific/Auckland".to_string()));
assert_eq!(config.fire_at, Some(time));
assert_eq!(config.timezone, Some("Pacific/Auckland".to_string()));
}
#[test]
fn test_duration_until_next_fire_is_bounded() {
// Result must always be between 1 second and ~24 hours
let time = chrono::NaiveTime::from_hms_opt(14, 0, 0).unwrap();
let dur = duration_until_next_fire(time, chrono_tz::UTC);
assert!(dur.as_secs() >= 1, "duration must be at least 1 second");
assert!(
dur.as_secs() <= 86_401,
"duration must be at most ~24 hours, got {}s",
dur.as_secs()
);
}
#[test]
fn test_duration_until_next_fire_dst_timezone_no_panic() {
// Use a timezone with DST (US Eastern) — should never panic
let tz: Tz = "America/New_York".parse().unwrap();
// Test a range of times including midnight boundaries
for hour in [0, 2, 3, 12, 23] {
let time = chrono::NaiveTime::from_hms_opt(hour, 30, 0).unwrap();
let dur = duration_until_next_fire(time, tz);
assert!(dur.as_secs() >= 1);
assert!(dur.as_secs() <= 86_401);
}
}
#[test]
fn test_resolved_tz_defaults_to_utc() {
let config = HeartbeatConfig::default();
assert_eq!(config.resolved_tz(), chrono_tz::UTC);
}
#[test]
fn test_resolved_tz_parses_iana() {
let time = chrono::NaiveTime::from_hms_opt(9, 0, 0).unwrap();
let config =
HeartbeatConfig::default().with_fire_at(time, Some("Europe/London".to_string()));
assert_eq!(config.resolved_tz(), chrono_tz::Europe::London);
}
}
+1 -1
View File
@@ -19,7 +19,7 @@ use tokio::task::JoinHandle;
use uuid::Uuid;
use crate::channels::IncomingMessage;
use crate::channels::web::types::SseEvent;
use crate::events::DomainEvent as SseEvent;
/// Route context for forwarding job monitor events back to the user's channel.
#[derive(Debug, Clone)]
+5 -1006
View File
File diff suppressed because it is too large Load Diff
+1 -10
View File
@@ -172,11 +172,6 @@ impl RoutineEngine {
EventMatcher::Message { routine, regex } => (routine, regex),
EventMatcher::System { .. } => continue,
};
if routine.user_id != message.user_id {
continue;
}
// Channel filter
if let Trigger::Event {
channel: Some(ch), ..
@@ -655,7 +650,6 @@ async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun)
send_notification(
&ctx.notify_tx,
&routine.notify,
&routine.user_id,
&routine.name,
status,
summary.as_deref(),
@@ -700,8 +694,7 @@ async fn execute_full_job(
reason: "scheduler not available".to_string(),
})?;
let mut metadata =
serde_json::json!({ "max_iterations": max_iterations, "owner_id": routine.user_id });
let mut metadata = serde_json::json!({ "max_iterations": max_iterations });
// Carry the routine's notify config in job metadata so the message tool
// can resolve channel/target per-job without global state mutation.
if let Some(channel) = &routine.notify.channel {
@@ -1214,7 +1207,6 @@ async fn execute_routine_tool(
async fn send_notification(
tx: &mpsc::Sender<OutgoingResponse>,
notify: &NotifyConfig,
owner_id: &str,
routine_name: &str,
status: RunStatus,
summary: Option<&str>,
@@ -1251,7 +1243,6 @@ async fn send_notification(
"source": "routine",
"routine_name": routine_name,
"status": status.to_string(),
"owner_id": owner_id,
"notify_user": notify.user,
"notify_channel": notify.channel,
}),
+2 -1
View File
@@ -9,11 +9,11 @@ use tokio::task::JoinHandle;
use uuid::Uuid;
use crate::agent::task::{Task, TaskContext, TaskOutput};
use crate::channels::web::types::SseEvent;
use crate::config::AgentConfig;
use crate::context::{ContextManager, JobContext, JobState};
use crate::db::Database;
use crate::error::{Error, JobError};
use crate::events::DomainEvent as SseEvent;
use crate::hooks::HookRegistry;
use crate::llm::LlmProvider;
use crate::safety::SafetyLayer;
@@ -272,6 +272,7 @@ impl Scheduler {
sse_tx: self.sse_tx.clone(),
approval_context,
http_interceptor: self.http_interceptor.clone(),
event_bus: None,
};
let worker = Worker::new(job_id, deps);
+5 -11
View File
@@ -22,17 +22,11 @@ pub struct StuckJob {
pub repair_attempts: u32,
}
/// A tool that has been detected as broken.
#[derive(Debug, Clone)]
pub struct BrokenTool {
pub name: String,
pub failure_count: u32,
pub last_error: Option<String>,
pub first_failure: DateTime<Utc>,
pub last_failure: DateTime<Utc>,
pub last_build_result: Option<serde_json::Value>,
pub repair_attempts: u32,
}
/// Backward-compatible alias for `ToolFailureRecord`.
///
/// The canonical type now lives in `crate::models::tool_failure` to break
/// the circular dependency between `db` and `agent`.
pub type BrokenTool = crate::models::tool_failure::ToolFailureRecord;
/// Result of a repair attempt.
#[derive(Debug)]
+146 -25
View File
@@ -16,8 +16,8 @@ use chrono::{DateTime, TimeDelta, Utc};
use serde::{Deserialize, Serialize};
use uuid::Uuid;
use crate::channels::web::util::truncate_preview;
use crate::llm::{ChatMessage, ToolCall};
use crate::util::truncate_preview;
/// A session containing one or more threads.
#[derive(Debug, Clone, Serialize, Deserialize)]
@@ -133,6 +133,28 @@ pub enum ThreadState {
Interrupted,
}
impl ThreadState {
/// Check whether a transition from this state to `target` is valid.
pub fn can_transition_to(self, target: ThreadState) -> bool {
use ThreadState::*;
matches!(
(self, target),
// From Idle
(Idle, Processing) |
// From Processing
(Processing, Idle) |
(Processing, AwaitingApproval) |
(Processing, Interrupted) |
// From AwaitingApproval
(AwaitingApproval, Idle) |
(AwaitingApproval, Processing) |
(AwaitingApproval, Interrupted) |
// From Interrupted
(Interrupted, Idle)
)
}
}
/// Pending auth token request.
///
/// Auth mode TTL — must stay in sync with
@@ -197,8 +219,8 @@ pub struct Thread {
pub id: Uuid,
/// Parent session ID.
pub session_id: Uuid,
/// Current state.
pub state: ThreadState,
/// Current state. Private — use `state()` to read, transition methods to mutate.
state: ThreadState,
/// Turns in this thread.
pub turns: Vec<Turn>,
/// When the thread was created.
@@ -248,6 +270,33 @@ impl Thread {
}
}
/// Get the current thread state.
pub fn state(&self) -> ThreadState {
self.state
}
/// Force-reset the state to Idle (for clear/restore operations that
/// bypass normal transitions). Prefer the transition methods for
/// normal state changes.
pub fn reset_to_idle(&mut self) {
self.state = ThreadState::Idle;
self.updated_at = Utc::now();
}
/// Force-set state to Processing (for approval flow resumption where
/// state was AwaitingApproval → Processing). Validates the transition.
pub fn set_processing(&mut self) -> Result<(), String> {
if !self.state.can_transition_to(ThreadState::Processing) {
return Err(format!(
"Cannot transition from {:?} to Processing",
self.state
));
}
self.state = ThreadState::Processing;
self.updated_at = Utc::now();
Ok(())
}
/// Get the current turn number (1-indexed for display).
pub fn turn_number(&self) -> usize {
self.turns.len() + 1
@@ -518,8 +567,8 @@ pub struct Turn {
pub response: Option<String>,
/// Tool calls made during this turn.
pub tool_calls: Vec<TurnToolCall>,
/// Turn state.
pub state: TurnState,
/// Turn state. Private — use `state()` to read, transition methods to mutate.
state: TurnState,
/// When the turn started.
pub started_at: DateTime<Utc>,
/// When the turn completed.
@@ -549,6 +598,11 @@ impl Turn {
}
}
/// Get the current turn state.
pub fn state(&self) -> TurnState {
self.state
}
/// Complete this turn.
pub fn complete(&mut self, response: impl Into<String>) {
self.response = Some(response.into());
@@ -629,11 +683,11 @@ mod tests {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("Hello");
assert_eq!(thread.state, ThreadState::Processing);
assert_eq!(thread.state(), ThreadState::Processing);
assert_eq!(thread.turns.len(), 1);
thread.complete_turn("Hi there!");
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
assert_eq!(thread.turns[0].response, Some("Hi there!".to_string()));
}
@@ -683,7 +737,7 @@ mod tests {
assert_eq!(thread.turns[0].response, Some("Hi there!".to_string()));
assert_eq!(thread.turns[1].user_input, "How are you?");
assert_eq!(thread.turns[1].response, Some("I'm good!".to_string()));
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
}
#[test]
@@ -783,7 +837,7 @@ mod tests {
assert_eq!(thread.id, specific_id);
assert_eq!(thread.session_id, session_id);
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
assert!(thread.turns.is_empty());
}
@@ -821,7 +875,7 @@ mod tests {
// Should clear all turns and stay idle
assert!(thread.turns.is_empty());
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
}
#[test]
@@ -940,17 +994,17 @@ mod tests {
let mut thread = Thread::new(Uuid::new_v4());
thread.start_turn("do something");
assert_eq!(thread.state, ThreadState::Processing);
assert_eq!(thread.state(), ThreadState::Processing);
thread.interrupt();
assert_eq!(thread.state, ThreadState::Interrupted);
assert_eq!(thread.state(), ThreadState::Interrupted);
let last_turn = thread.last_turn().unwrap();
assert_eq!(last_turn.state, TurnState::Interrupted);
assert_eq!(last_turn.state(), TurnState::Interrupted);
assert!(last_turn.completed_at.is_some());
thread.resume();
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
}
#[test]
@@ -958,15 +1012,15 @@ mod tests {
let mut thread = Thread::new(Uuid::new_v4());
// Idle thread: resume should be a no-op
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
thread.resume();
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
// Processing thread: resume should not change state
thread.start_turn("work");
assert_eq!(thread.state, ThreadState::Processing);
assert_eq!(thread.state(), ThreadState::Processing);
thread.resume();
assert_eq!(thread.state, ThreadState::Processing);
assert_eq!(thread.state(), ThreadState::Processing);
}
#[test]
@@ -976,10 +1030,10 @@ mod tests {
thread.start_turn("risky operation");
thread.fail_turn("connection timed out");
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
let turn = thread.last_turn().unwrap();
assert_eq!(turn.state, TurnState::Failed);
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());
@@ -1078,7 +1132,7 @@ mod tests {
// 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_eq!(thread.state(), ThreadState::Idle);
assert!(thread.turns.is_empty());
}
@@ -1088,7 +1142,7 @@ mod tests {
// 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_eq!(thread.state(), ThreadState::Idle);
assert!(thread.turns.is_empty());
}
@@ -1109,7 +1163,7 @@ mod tests {
};
thread.await_approval(approval);
assert_eq!(thread.state, ThreadState::AwaitingApproval);
assert_eq!(thread.state(), ThreadState::AwaitingApproval);
assert!(thread.pending_approval.is_some());
let taken = thread.take_pending_approval();
@@ -1137,7 +1191,7 @@ mod tests {
thread.await_approval(approval);
thread.clear_pending_approval();
assert_eq!(thread.state, ThreadState::Idle);
assert_eq!(thread.state(), ThreadState::Idle);
assert!(thread.pending_approval.is_none());
}
@@ -1156,7 +1210,7 @@ mod tests {
// Mutably modify through accessor
session.active_thread_mut().unwrap().start_turn("test");
assert_eq!(
session.active_thread().unwrap().state,
session.active_thread().unwrap().state(),
ThreadState::Processing
);
}
@@ -1381,4 +1435,71 @@ mod tests {
);
assert!(tool_result_content.ends_with("..."));
}
#[test]
fn thread_state_transition_table() {
use ThreadState::*;
// Valid transitions
assert!(Idle.can_transition_to(Processing));
assert!(Processing.can_transition_to(Idle));
assert!(Processing.can_transition_to(AwaitingApproval));
assert!(Processing.can_transition_to(Interrupted));
assert!(AwaitingApproval.can_transition_to(Idle));
assert!(AwaitingApproval.can_transition_to(Processing));
assert!(AwaitingApproval.can_transition_to(Interrupted));
assert!(Interrupted.can_transition_to(Idle));
// Invalid transitions
assert!(!Idle.can_transition_to(Idle));
assert!(!Idle.can_transition_to(AwaitingApproval));
assert!(!Idle.can_transition_to(Interrupted));
assert!(!Idle.can_transition_to(Completed));
assert!(!Processing.can_transition_to(Processing));
assert!(!Processing.can_transition_to(Completed));
assert!(!AwaitingApproval.can_transition_to(AwaitingApproval));
assert!(!Interrupted.can_transition_to(Processing));
assert!(!Interrupted.can_transition_to(Interrupted));
assert!(!Completed.can_transition_to(Idle));
assert!(!Completed.can_transition_to(Processing));
}
#[test]
fn thread_state_is_private() {
let thread = Thread::new(Uuid::new_v4());
// Can read via accessor
assert_eq!(thread.state(), ThreadState::Idle);
}
#[test]
fn set_processing_validates_transition() {
let mut thread = Thread::new(Uuid::new_v4());
// Idle → Processing: valid
assert!(thread.set_processing().is_ok());
assert_eq!(thread.state(), ThreadState::Processing);
// Processing → Processing: invalid
assert!(thread.set_processing().is_err());
// Complete the turn so we can test from AwaitingApproval
thread.complete_turn("done");
// AwaitingApproval → Processing: valid
thread.start_turn("test");
thread.await_approval(PendingApproval {
request_id: Uuid::new_v4(),
tool_name: "echo".into(),
parameters: serde_json::json!({}),
display_parameters: serde_json::json!({}),
description: "test".into(),
tool_call_id: "tc1".into(),
context_messages: vec![],
deferred_tool_calls: vec![],
user_timezone: None,
});
assert_eq!(thread.state(), ThreadState::AwaitingApproval);
assert!(thread.set_processing().is_ok());
assert_eq!(thread.state(), ThreadState::Processing);
}
}
+15 -19
View File
@@ -136,30 +136,26 @@ impl SessionManager {
if let Some(ext_tid) = external_thread_id
&& let Ok(ext_uuid) = Uuid::parse_str(ext_tid)
{
let thread_map = self.thread_map.read().await;
// Atomic check-and-insert: acquire write lock for the entire
// sequence to prevent TOCTOU races where another task could map
// this UUID between our check and insert.
let mut thread_map = self.thread_map.write().await;
let mapped_elsewhere = thread_map.values().any(|&v| v == ext_uuid);
drop(thread_map);
if !mapped_elsewhere {
let sess = session.lock().await;
if sess.threads.contains_key(&ext_uuid) {
drop(sess);
let exists_in_session = sess.threads.contains_key(&ext_uuid);
drop(sess);
let mut thread_map = self.thread_map.write().await;
// Re-check after acquiring write lock to prevent race condition
// where another task mapped this UUID between our read and write.
if !thread_map.values().any(|&v| v == ext_uuid) {
thread_map.insert(key, ext_uuid);
drop(thread_map);
// Ensure undo manager exists
let mut undo_managers = self.undo_managers.write().await;
undo_managers
.entry(ext_uuid)
.or_insert_with(|| Arc::new(Mutex::new(UndoManager::new())));
return (session, ext_uuid);
}
// If it was mapped elsewhere while we were unlocked, fall through
// to create a new thread, preserving channel isolation.
if exists_in_session {
thread_map.insert(key, ext_uuid);
drop(thread_map);
// Ensure undo manager exists
let mut undo_managers = self.undo_managers.write().await;
undo_managers
.entry(ext_uuid)
.or_insert_with(|| Arc::new(Mutex::new(UndoManager::new())));
return (session, ext_uuid);
}
}
}
-8
View File
@@ -427,14 +427,6 @@ impl SubmissionResult {
message: message.into(),
}
}
/// Create a non-error status message (e.g., for blocking states like approval waiting).
/// Uses Ok variant to avoid "Error:" prefix in rendering.
pub fn pending(message: impl Into<String>) -> Self {
Self::Ok {
message: Some(message.into()),
}
}
}
#[cfg(test)]
+48 -175
View File
@@ -16,12 +16,12 @@ use crate::agent::dispatcher::{
};
use crate::agent::session::{PendingApproval, Session, ThreadState};
use crate::agent::submission::SubmissionResult;
use crate::channels::web::util::truncate_preview;
use crate::channels::{IncomingMessage, StatusUpdate};
use crate::context::JobContext;
use crate::error::Error;
use crate::llm::{ChatMessage, ToolCall};
use crate::tools::redact_params;
use crate::util::truncate_preview;
const FORGED_THREAD_ID_ERROR: &str = "Invalid or unauthorized thread ID.";
@@ -186,70 +186,9 @@ impl Agent {
"Processing user input"
);
// First check thread state without holding lock during I/O
let (thread_state, approval_context) = {
let sess = session.lock().await;
let thread = sess
.threads
.get(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
let approval_context = thread.pending_approval.as_ref().map(|a| {
let desc_preview =
crate::agent::agent_loop::truncate_for_preview(&a.description, 80);
(a.tool_name.clone(), desc_preview)
});
(thread.state, approval_context)
};
tracing::debug!(
message_id = %message.id,
thread_id = %thread_id,
thread_state = ?thread_state,
"Checked thread state"
);
// Check thread state
match thread_state {
ThreadState::Processing => {
tracing::warn!(
message_id = %message.id,
thread_id = %thread_id,
"Thread is processing, rejecting new input"
);
return Ok(SubmissionResult::error(
"Turn in progress. Use /interrupt to cancel.",
));
}
ThreadState::AwaitingApproval => {
tracing::warn!(
message_id = %message.id,
thread_id = %thread_id,
"Thread awaiting approval, rejecting new input"
);
let msg = match approval_context {
Some((tool_name, desc_preview)) => format!(
"Waiting for approval: {tool_name} — {desc_preview}. Use /interrupt to cancel."
),
None => "Waiting for approval. Use /interrupt to cancel.".to_string(),
};
return Ok(SubmissionResult::pending(msg));
}
ThreadState::Completed => {
tracing::warn!(
message_id = %message.id,
thread_id = %thread_id,
"Thread completed, rejecting new input"
);
return Ok(SubmissionResult::error(
"Thread completed. Use /thread new.",
));
}
ThreadState::Idle | ThreadState::Interrupted => {
// Can proceed
}
}
// Safety validation for user input
// Safety validation BEFORE state check — these don't need the session
// lock and are the slowest part, so run them first. Then we can do the
// state check + start_turn atomically under one lock (TOCTOU fix).
let validation = self.safety().validate_input(content);
if !validation.is_valid {
let details = validation
@@ -299,7 +238,10 @@ impl Agent {
// Natural language goes through the agentic loop
// Job tools (create_job, list_jobs, etc.) are in the tool registry
// Auto-compact if needed BEFORE adding new turn
// Check thread state and auto-compact under a single lock acquisition.
// The state check must happen under the lock to prevent TOCTOU races
// where another task could change the state between our check and
// the start_turn call.
{
let mut sess = session.lock().await;
let thread = sess
@@ -307,6 +249,35 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
let thread_state = thread.state();
tracing::debug!(
message_id = %message.id,
thread_id = %thread_id,
thread_state = ?thread_state,
"Checked thread state"
);
match thread_state {
ThreadState::Processing => {
return Ok(SubmissionResult::error(
"Turn in progress. Use /interrupt to cancel.",
));
}
ThreadState::AwaitingApproval => {
return Ok(SubmissionResult::error(
"Waiting for approval. Use /interrupt to cancel.",
));
}
ThreadState::Completed => {
return Ok(SubmissionResult::error(
"Thread completed. Use /thread new.",
));
}
ThreadState::Idle | ThreadState::Interrupted => {
// Can proceed
}
}
let messages = thread.messages();
if let Some(strategy) = self.context_monitor.suggest_compaction(&messages) {
let pct = self.context_monitor.usage_percent(&messages);
@@ -414,7 +385,7 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
if thread.state == ThreadState::Interrupted {
if thread.state() == ThreadState::Interrupted {
let _ = self
.channels
.send_status(
@@ -787,7 +758,7 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
match thread.state {
match thread.state() {
ThreadState::Processing | ThreadState::AwaitingApproval => {
thread.interrupt();
Ok(SubmissionResult::ok_with_message("Interrupted."))
@@ -846,7 +817,7 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
thread.turns.clear();
thread.state = ThreadState::Idle;
thread.reset_to_idle();
// Clear undo history too
let undo_mgr = self.session_manager.get_undo_manager(thread_id).await;
@@ -873,11 +844,11 @@ impl Agent {
.get_mut(&thread_id)
.ok_or_else(|| Error::from(crate::error::JobError::NotFound { id: thread_id }))?;
if thread.state != ThreadState::AwaitingApproval {
if thread.state() != ThreadState::AwaitingApproval {
// Stale or duplicate approval (tool already executed) — silently ignore.
tracing::debug!(
%thread_id,
state = ?thread.state,
state = ?thread.state(),
"Ignoring stale approval: thread not in AwaitingApproval state"
);
return Ok(SubmissionResult::ok_with_message(""));
@@ -923,18 +894,19 @@ impl Agent {
);
}
// Reset thread state to processing
// Reset thread state to processing (AwaitingApproval → Processing)
{
let mut sess = session.lock().await;
if let Some(thread) = sess.threads.get_mut(&thread_id) {
thread.state = ThreadState::Processing;
if let Some(thread) = sess.threads.get_mut(&thread_id)
&& let Err(e) = thread.set_processing()
{
tracing::warn!(%thread_id, "Invalid approval state transition: {}", e);
}
}
// Execute the approved tool and continue the loop
let mut job_ctx =
JobContext::with_user(&message.user_id, "chat", "Interactive chat session")
.with_requester_id(&message.sender_id);
JobContext::with_user(&message.user_id, "chat", "Interactive chat session");
job_ctx.http_interceptor = self.deps.http_interceptor.clone();
// Prefer a valid timezone from the approval message, fall back to the
// resolved timezone stored when the approval was originally requested.
@@ -1926,103 +1898,4 @@ mod tests {
created_at: chrono::Utc::now(),
}
}
#[tokio::test]
async fn test_awaiting_approval_rejection_includes_tool_context() {
// Test that when a thread is in AwaitingApproval state and receives a new message,
// process_user_input rejects it with a non-error status that includes tool context.
use crate::agent::session::{PendingApproval, Session, Thread, ThreadState};
use uuid::Uuid;
let session_id = Uuid::new_v4();
let thread_id = Uuid::new_v4();
let mut thread = Thread::with_id(thread_id, session_id);
// Set thread to AwaitingApproval with a pending tool approval
let pending = PendingApproval {
request_id: Uuid::new_v4(),
tool_name: "shell".to_string(),
parameters: serde_json::json!({"command": "echo hello"}),
display_parameters: serde_json::json!({"command": "[REDACTED]"}),
description: "Execute: echo hello".to_string(),
tool_call_id: "call_0".to_string(),
context_messages: vec![],
deferred_tool_calls: vec![],
user_timezone: None,
};
thread.await_approval(pending);
let mut session = Session::new("test-user");
session.threads.insert(thread_id, thread);
// Verify thread is in AwaitingApproval state
assert_eq!(
session.threads[&thread_id].state,
ThreadState::AwaitingApproval
);
let result = extract_approval_message(&session, thread_id);
// Verify result is an Ok with a message (not an Error)
match result {
Ok(Some(msg)) => {
// Should NOT start with "Error:"
assert!(
!msg.to_lowercase().starts_with("error:"),
"Approval rejection should not have 'Error:' prefix. Got: {}",
msg
);
// Should contain "waiting for approval"
assert!(
msg.to_lowercase().contains("waiting for approval"),
"Should contain 'waiting for approval'. Got: {}",
msg
);
// Should contain the tool name
assert!(
msg.contains("shell"),
"Should contain tool name 'shell'. Got: {}",
msg
);
// Should contain the description (or truncated version)
assert!(
msg.contains("echo hello"),
"Should contain description 'echo hello'. Got: {}",
msg
);
}
_ => panic!("Expected approval rejection message"),
}
}
// Helper function to extract the approval message without needing a full Agent instance
fn extract_approval_message(
session: &crate::agent::session::Session,
thread_id: Uuid,
) -> Result<Option<String>, crate::error::Error> {
let thread = session.threads.get(&thread_id).ok_or_else(|| {
crate::error::Error::from(crate::error::JobError::NotFound { id: thread_id })
})?;
if thread.state == ThreadState::AwaitingApproval {
let approval_context = thread.pending_approval.as_ref().map(|a| {
let desc_preview =
crate::agent::agent_loop::truncate_for_preview(&a.description, 80);
(a.tool_name.clone(), desc_preview)
});
let msg = match approval_context {
Some((tool_name, desc_preview)) => format!(
"Waiting for approval: {tool_name} — {desc_preview}. Use /interrupt to cancel."
),
None => "Waiting for approval. Use /interrupt to cancel.".to_string(),
};
Ok(Some(msg))
} else {
Ok(None)
}
}
}
+77 -21
View File
@@ -14,6 +14,7 @@ use crate::channels::web::log_layer::LogBroadcaster;
use crate::config::Config;
use crate::context::ContextManager;
use crate::db::Database;
use crate::event_bus::EventBus;
use crate::extensions::ExtensionManager;
use crate::hooks::HookRegistry;
use crate::llm::{LlmProvider, RecordingLlm, SessionManager};
@@ -56,6 +57,62 @@ pub struct AppComponents {
pub session: Arc<SessionManager>,
pub catalog_entries: Vec<crate::extensions::RegistryEntry>,
pub dev_loaded_tool_names: Vec<String>,
/// Unified event bus for all system events.
pub event_bus: EventBus,
}
impl AppComponents {
/// Verify that all components expected by the config are actually present.
///
/// Logs warnings for any missing components. Called at end of `build_all()`
/// to catch wiring bugs early.
pub fn verify_readiness(&self) {
let mut warnings = Vec::new();
// Config cross-field validation
for issue in self.config.validate() {
warnings.push("config validation issue");
tracing::warn!(component = "startup_verification", "{}", issue);
}
// Note: db can legitimately be None if --no-db was passed.
// We only warn if workspace is expected but missing.
if self.workspace.is_none() && self.db.is_some() {
warnings.push("Workspace is None but database is available");
}
if self.wasm_tool_runtime.is_none() && self.config.wasm.enabled {
warnings.push("WASM runtime is None but config.wasm.enabled=true");
}
if self.extension_manager.is_none() {
warnings.push("Extension manager is None");
}
if self.skill_registry.is_none() && self.config.skills.enabled {
warnings.push("Skill registry is None but config.skills.enabled=true");
}
// Check tool registration
let missing_tools = self.tools.verify_expected_tools(&self.config);
for tool_name in &missing_tools {
warnings.push("missing expected tool");
tracing::warn!(
component = "startup_verification",
tool = tool_name,
"Expected tool not registered"
);
}
for warning in &warnings {
tracing::warn!(component = "startup_verification", "{}", warning);
}
if warnings.is_empty() {
tracing::debug!("All expected components initialized successfully");
}
}
}
/// Options that control optional init phases.
@@ -140,14 +197,12 @@ impl AppBuilder {
self.handles = Some(handles);
// Post-init: migrate disk config, reload config from DB, attach session, cleanup
if let Err(e) =
crate::bootstrap::migrate_disk_to_db(db.as_ref(), &self.config.owner_id).await
{
if let Err(e) = crate::bootstrap::migrate_disk_to_db(db.as_ref(), "default").await {
tracing::warn!("Disk-to-DB settings migration failed: {}", e);
}
let toml_path = self.toml_path.as_deref();
match Config::from_db_with_toml(db.as_ref(), &self.config.owner_id, toml_path).await {
match Config::from_db_with_toml(db.as_ref(), "default", toml_path).await {
Ok(db_config) => {
self.config = db_config;
tracing::debug!("Configuration reloaded from database");
@@ -160,9 +215,7 @@ impl AppBuilder {
}
}
self.session
.attach_store(db.clone(), &self.config.owner_id)
.await;
self.session.attach_store(db.clone(), "default").await;
// Fire-and-forget housekeeping — no need to block startup.
let db_cleanup = db.clone();
@@ -197,10 +250,9 @@ impl AppBuilder {
let store: Option<&(dyn crate::db::SettingsStore + Sync)> =
self.db.as_ref().map(|db| db.as_ref() as _);
let toml_path = self.toml_path.as_deref();
let owner_id = self.config.owner_id.clone();
if let Err(e) = self
.config
.re_resolve_llm(store, &owner_id, toml_path)
.re_resolve_llm(store, "default", toml_path)
.await
{
tracing::warn!(
@@ -229,17 +281,15 @@ impl AppBuilder {
if let Some(ref secrets) = store {
// Inject LLM API keys from encrypted storage
crate::config::inject_llm_keys_from_secrets(secrets.as_ref(), &self.config.owner_id)
.await;
crate::config::inject_llm_keys_from_secrets(secrets.as_ref(), "default").await;
// Re-resolve only the LLM config with newly available keys.
let store: Option<&(dyn crate::db::SettingsStore + Sync)> =
self.db.as_ref().map(|db| db.as_ref() as _);
let toml_path = self.toml_path.as_deref();
let owner_id = self.config.owner_id.clone();
if let Err(e) = self
.config
.re_resolve_llm(store, &owner_id, toml_path)
.re_resolve_llm(store, "default", toml_path)
.await
{
tracing::warn!("Failed to re-resolve LLM config after secret injection: {e}");
@@ -311,7 +361,7 @@ impl AppBuilder {
// Register memory tools if database is available
let workspace = if let Some(ref db) = self.db {
let mut ws = Workspace::new_with_db(&self.config.owner_id, db.clone())
let mut ws = Workspace::new_with_db("default", db.clone())
.with_search_config(&self.config.search);
if let Some(ref emb) = embeddings {
ws = ws.with_embeddings(emb.clone());
@@ -476,10 +526,9 @@ impl AppBuilder {
let tools = Arc::clone(tools);
let mcp_sm = Arc::clone(&mcp_session_manager);
let pm = Arc::clone(&mcp_process_manager);
let owner_id = self.config.owner_id.clone();
async move {
let servers_result = if let Some(ref d) = db {
load_mcp_servers_from_db(d.as_ref(), &owner_id).await
load_mcp_servers_from_db(d.as_ref(), "default").await
} else {
crate::tools::mcp::config::load_mcp_servers().await
};
@@ -499,7 +548,6 @@ impl AppBuilder {
let secrets = secrets_store.clone();
let tools = Arc::clone(&tools);
let pm = Arc::clone(&pm);
let owner_id = owner_id.clone();
join_set.spawn(async move {
let server_name = server.name.clone();
@@ -509,7 +557,7 @@ impl AppBuilder {
&mcp_sm,
&pm,
secrets,
&owner_id,
"default",
)
.await
{
@@ -651,7 +699,7 @@ impl AppBuilder {
self.config.wasm.tools_dir.clone(),
self.config.channels.wasm_channels_dir.clone(),
self.config.tunnel.public_url.clone(),
self.config.owner_id.clone(),
"default".to_string(),
self.db.clone(),
catalog_entries.clone(),
));
@@ -781,6 +829,9 @@ impl AppBuilder {
(None, None)
};
// Create unified event bus
let event_bus = EventBus::new();
let context_manager = Arc::new(ContextManager::new(self.config.agent.max_parallel_jobs));
let cost_guard = Arc::new(crate::agent::cost_guard::CostGuard::new(
crate::agent::cost_guard::CostGuardConfig {
@@ -794,7 +845,7 @@ impl AppBuilder {
tools.count()
);
Ok(AppComponents {
let components = AppComponents {
config: self.config,
db: self.db,
secrets_store: self.secrets_store,
@@ -819,7 +870,12 @@ impl AppBuilder {
session: self.session,
catalog_entries,
dev_loaded_tool_names,
})
event_bus,
};
components.verify_readiness();
Ok(components)
}
}
+6 -82
View File
@@ -67,24 +67,14 @@ pub struct IncomingMessage {
pub id: Uuid,
/// Channel this message came from.
pub channel: String,
/// Storage/persistence scope for this interaction.
///
/// For owner-capable channels this is the stable instance owner ID when the
/// configured owner is speaking; otherwise it can be a guest/sender-scoped
/// identifier to preserve isolation.
/// User identifier within the channel.
pub user_id: String,
/// Stable instance owner scope for this IronClaw deployment.
pub owner_id: String,
/// Channel-specific sender/actor identifier.
pub sender_id: String,
/// Optional display name.
pub user_name: Option<String>,
/// Message content.
pub content: String,
/// Thread/conversation ID for threaded conversations.
pub thread_id: Option<String>,
/// Stable channel/chat/thread scope for this conversation.
pub conversation_scope_id: Option<String>,
/// When the message was received.
pub received_at: DateTime<Utc>,
/// Channel-specific metadata.
@@ -94,8 +84,9 @@ pub struct IncomingMessage {
/// File or media attachments on this message.
pub attachments: Vec<IncomingAttachment>,
/// Internal-only flag: message was generated inside the process (e.g. job
/// monitor) and must bypass the normal user-input pipeline. This field is
/// not settable via metadata, so external channels cannot spoof it.
/// monitor) and must bypass the normal user-input pipeline. This field is
/// **not** settable via `with_metadata()` — only trusted code paths inside
/// the binary can set it, preventing external channels from spoofing it.
pub(crate) is_internal: bool,
}
@@ -106,17 +97,13 @@ impl IncomingMessage {
user_id: impl Into<String>,
content: impl Into<String>,
) -> Self {
let user_id = user_id.into();
Self {
id: Uuid::new_v4(),
channel: channel.into(),
owner_id: user_id.clone(),
sender_id: user_id.clone(),
user_id,
user_id: user_id.into(),
user_name: None,
content: content.into(),
thread_id: None,
conversation_scope_id: None,
received_at: Utc::now(),
metadata: serde_json::Value::Null,
timezone: None,
@@ -127,27 +114,7 @@ impl IncomingMessage {
/// Set the thread ID.
pub fn with_thread(mut self, thread_id: impl Into<String>) -> Self {
let thread_id = thread_id.into();
self.conversation_scope_id = Some(thread_id.clone());
self.thread_id = Some(thread_id);
self
}
/// Set the stable owner scope for this message.
pub fn with_owner_id(mut self, owner_id: impl Into<String>) -> Self {
self.owner_id = owner_id.into();
self
}
/// Set the channel-specific sender/actor identifier.
pub fn with_sender_id(mut self, sender_id: impl Into<String>) -> Self {
self.sender_id = sender_id.into();
self
}
/// Set the conversation scope for this message.
pub fn with_conversation_scope(mut self, scope_id: impl Into<String>) -> Self {
self.conversation_scope_id = Some(scope_id.into());
self.thread_id = Some(thread_id.into());
self
}
@@ -180,49 +147,6 @@ impl IncomingMessage {
self.is_internal = true;
self
}
/// Effective conversation scope, falling back to thread_id for legacy callers.
pub fn conversation_scope(&self) -> Option<&str> {
self.conversation_scope_id
.as_deref()
.or(self.thread_id.as_deref())
}
/// Best-effort routing target for proactive replies on the current channel.
pub fn routing_target(&self) -> Option<String> {
routing_target_from_metadata(&self.metadata).or_else(|| {
if self.sender_id.is_empty() {
None
} else {
Some(self.sender_id.clone())
}
})
}
}
/// Extract a channel-specific proactive routing target from message metadata.
pub fn routing_target_from_metadata(metadata: &serde_json::Value) -> Option<String> {
metadata
.get("signal_target")
.and_then(|value| match value {
serde_json::Value::String(s) => Some(s.clone()),
serde_json::Value::Number(n) => Some(n.to_string()),
_ => None,
})
.or_else(|| {
metadata.get("chat_id").and_then(|value| match value {
serde_json::Value::String(s) => Some(s.clone()),
serde_json::Value::Number(n) => Some(n.to_string()),
_ => None,
})
})
.or_else(|| {
metadata.get("target").and_then(|value| match value {
serde_json::Value::String(s) => Some(s.clone()),
serde_json::Value::Number(n) => Some(n.to_string()),
_ => None,
})
})
}
/// Stream of incoming messages.
+11 -105
View File
@@ -133,8 +133,7 @@ impl HttpChannel {
#[derive(Debug, Deserialize)]
struct WebhookRequest {
/// Optional caller or client identifier for sender-scoped routing.
/// The channel owner/storage scope remains fixed by server config.
/// User or client identifier (ignored, user is fixed by server config).
#[serde(default)]
user_id: Option<String>,
/// Message content.
@@ -404,38 +403,12 @@ async fn process_authenticated_request(
state: Arc<HttpChannelState>,
req: WebhookRequest,
) -> axum::response::Response {
let normalized_user_id = req
.user_id
.as_deref()
.map(str::trim)
.filter(|user_id| !user_id.is_empty());
match (req.user_id.as_deref(), normalized_user_id) {
(Some(raw_user_id), Some(user_id)) if raw_user_id != user_id => {
tracing::debug!(
provided_user_id = %raw_user_id,
normalized_sender_id = %user_id,
configured_owner_id = %state.user_id,
"HTTP webhook request provided user_id; trimming and using it as sender_id while keeping the configured owner scope"
);
}
(Some(user_id), Some(_)) => {
tracing::debug!(
provided_user_id = %user_id,
configured_owner_id = %state.user_id,
"HTTP webhook request provided user_id; using it as sender_id while keeping the configured owner scope"
);
}
(Some(raw_user_id), None) => {
tracing::debug!(
provided_user_id = %raw_user_id,
configured_owner_id = %state.user_id,
"HTTP webhook request provided a blank user_id; falling back to the configured owner scope for sender_id"
);
}
(None, None) => {}
(None, Some(_)) => unreachable!("normalized user_id requires a raw user_id"),
}
let _ = req.user_id.as_ref().map(|user_id| {
tracing::debug!(
provided_user_id = %user_id,
"HTTP webhook request provided user_id, ignoring in favor of configured user_id"
);
});
if req.content.len() > MAX_CONTENT_BYTES {
return (
@@ -541,13 +514,11 @@ async fn process_authenticated_request(
Vec::new()
};
let sender_id = normalized_user_id.unwrap_or(&state.user_id).to_string();
let mut msg = IncomingMessage::new("http", &state.user_id, &req.content)
.with_owner_id(&state.user_id)
.with_sender_id(sender_id)
.with_metadata(serde_json::json!({
let mut msg = IncomingMessage::new("http", &state.user_id, &req.content).with_metadata(
serde_json::json!({
"wait_for_response": wait_for_response,
}));
}),
);
if !attachments.is_empty() {
msg = msg.with_attachments(attachments);
@@ -711,7 +682,6 @@ mod tests {
use axum::body::Body;
use axum::http::{HeaderValue, Request};
use secrecy::SecretString;
use tokio_stream::StreamExt;
use tower::ServiceExt;
use super::*;
@@ -850,70 +820,6 @@ mod tests {
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
}
#[tokio::test]
async fn webhook_blank_user_id_falls_back_to_owner_scope() {
let secret = "test-secret-123";
let channel = test_channel(Some(secret));
let mut stream = channel.start().await.unwrap();
let app = channel.routes();
let body = serde_json::json!({
"content": "hello",
"user_id": " "
});
let body_bytes = serde_json::to_vec(&body).unwrap();
let signature = compute_signature(secret, &body_bytes);
let req = Request::builder()
.method("POST")
.uri("/webhook")
.header("content-type", "application/json")
.header("x-hub-signature-256", signature)
.body(Body::from(body_bytes))
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let msg = tokio::time::timeout(std::time::Duration::from_secs(1), stream.next())
.await
.expect("timed out waiting for webhook message")
.expect("stream should yield a webhook message");
assert_eq!(msg.sender_id, "http");
assert_eq!(msg.owner_id, "http");
}
#[tokio::test]
async fn webhook_user_id_is_trimmed_before_becoming_sender_id() {
let secret = "test-secret-123";
let channel = test_channel(Some(secret));
let mut stream = channel.start().await.unwrap();
let app = channel.routes();
let body = serde_json::json!({
"content": "hello",
"user_id": " alice "
});
let body_bytes = serde_json::to_vec(&body).unwrap();
let signature = compute_signature(secret, &body_bytes);
let req = Request::builder()
.method("POST")
.uri("/webhook")
.header("content-type", "application/json")
.header("x-hub-signature-256", signature)
.body(Body::from(body_bytes))
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
let msg = tokio::time::timeout(std::time::Duration::from_secs(1), stream.next())
.await
.expect("timed out waiting for webhook message")
.expect("stream should yield a webhook message");
assert_eq!(msg.sender_id, "alice");
assert_eq!(msg.owner_id, "http");
}
/// Regression test for issue #869: RwLock read guard was held across
/// tx.send(msg).await in `process_message()`, blocking shutdown() from
/// acquiring the write lock when the channel buffer was full.
+1 -1
View File
@@ -39,7 +39,7 @@ mod webhook_server;
pub use channel::{
AttachmentKind, Channel, ChannelSecretUpdater, IncomingAttachment, IncomingMessage,
MessageStream, OutgoingResponse, StatusUpdate, routing_target_from_metadata,
MessageStream, OutgoingResponse, StatusUpdate,
};
pub use http::{HttpChannel, HttpChannelState};
pub use manager::ChannelManager;
+7 -22
View File
@@ -200,8 +200,6 @@ fn format_json_params(params: &serde_json::Value, indent: &str) -> String {
/// REPL channel with line editing and markdown rendering.
pub struct ReplChannel {
/// Stable owner scope for this REPL instance.
user_id: String,
/// Optional single message to send (for -m flag).
single_message: Option<String>,
/// Debug mode flag (shared with input thread).
@@ -215,13 +213,7 @@ pub struct ReplChannel {
impl ReplChannel {
/// Create a new REPL channel.
pub fn new() -> Self {
Self::with_user_id("default")
}
/// Create a new REPL channel for a specific owner scope.
pub fn with_user_id(user_id: impl Into<String>) -> Self {
Self {
user_id: user_id.into(),
single_message: None,
debug_mode: Arc::new(AtomicBool::new(false)),
is_streaming: Arc::new(AtomicBool::new(false)),
@@ -231,13 +223,7 @@ impl ReplChannel {
/// Create a REPL channel that sends a single message and exits.
pub fn with_message(message: String) -> Self {
Self::with_message_for_user("default", message)
}
/// Create a REPL channel that sends a single message for a specific owner scope and exits.
pub fn with_message_for_user(user_id: impl Into<String>, message: String) -> Self {
Self {
user_id: user_id.into(),
single_message: Some(message),
debug_mode: Arc::new(AtomicBool::new(false)),
is_streaming: Arc::new(AtomicBool::new(false)),
@@ -306,7 +292,6 @@ impl Channel for ReplChannel {
async fn start(&self) -> Result<MessageStream, ChannelError> {
let (tx, rx) = mpsc::channel(32);
let single_message = self.single_message.clone();
let user_id = self.user_id.clone();
let debug_mode = Arc::clone(&self.debug_mode);
let suppress_banner = Arc::clone(&self.suppress_banner);
let esc_interrupt_triggered_for_thread = Arc::new(AtomicBool::new(false));
@@ -316,11 +301,11 @@ impl Channel for ReplChannel {
// Single message mode: send it and return
if let Some(msg) = single_message {
let incoming = IncomingMessage::new("repl", &user_id, &msg).with_timezone(&sys_tz);
let incoming = IncomingMessage::new("repl", "default", &msg).with_timezone(&sys_tz);
let _ = tx.blocking_send(incoming);
// Ensure the agent exits after handling exactly one turn in -m mode,
// even when other channels (gateway/http) are enabled.
let _ = tx.blocking_send(IncomingMessage::new("repl", &user_id, "/quit"));
let _ = tx.blocking_send(IncomingMessage::new("repl", "default", "/quit"));
return;
}
@@ -381,7 +366,7 @@ impl Channel for ReplChannel {
"/quit" | "/exit" => {
// Forward shutdown command so the agent loop exits even
// when other channels (e.g. web gateway) are still active.
let msg = IncomingMessage::new("repl", &user_id, "/quit")
let msg = IncomingMessage::new("repl", "default", "/quit")
.with_timezone(&sys_tz);
let _ = tx.blocking_send(msg);
break;
@@ -404,7 +389,7 @@ impl Channel for ReplChannel {
}
let msg =
IncomingMessage::new("repl", &user_id, line).with_timezone(&sys_tz);
IncomingMessage::new("repl", "default", line).with_timezone(&sys_tz);
if tx.blocking_send(msg).is_err() {
break;
}
@@ -412,14 +397,14 @@ impl Channel for ReplChannel {
Err(ReadlineError::Interrupted) => {
if esc_interrupt_triggered_for_thread.swap(false, Ordering::Relaxed) {
// Esc: interrupt current operation and keep REPL open.
let msg = IncomingMessage::new("repl", &user_id, "/interrupt")
let msg = IncomingMessage::new("repl", "default", "/interrupt")
.with_timezone(&sys_tz);
if tx.blocking_send(msg).is_err() {
break;
}
} else {
// Ctrl+C (VINTR): request graceful shutdown.
let msg = IncomingMessage::new("repl", &user_id, "/quit")
let msg = IncomingMessage::new("repl", "default", "/quit")
.with_timezone(&sys_tz);
let _ = tx.blocking_send(msg);
break;
@@ -431,7 +416,7 @@ impl Channel for ReplChannel {
// immediately — just drop the REPL thread silently so other
// channels (gateway, telegram, …) keep running.
if std::io::stdin().is_terminal() {
let msg = IncomingMessage::new("repl", &user_id, "/quit")
let msg = IncomingMessage::new("repl", "default", "/quit")
.with_timezone(&sys_tz);
let _ = tx.blocking_send(msg);
}
+2 -8
View File
@@ -27,7 +27,6 @@ pub struct WasmChannelLoader {
pairing_store: Arc<PairingStore>,
settings_store: Option<Arc<dyn SettingsStore>>,
secrets_store: Option<Arc<dyn SecretsStore + Send + Sync>>,
owner_scope_id: String,
}
impl WasmChannelLoader {
@@ -36,14 +35,12 @@ impl WasmChannelLoader {
runtime: Arc<WasmChannelRuntime>,
pairing_store: Arc<PairingStore>,
settings_store: Option<Arc<dyn SettingsStore>>,
owner_scope_id: impl Into<String>,
) -> Self {
Self {
runtime,
pairing_store,
settings_store,
secrets_store: None,
owner_scope_id: owner_scope_id.into(),
}
}
@@ -152,7 +149,6 @@ impl WasmChannelLoader {
self.runtime.clone(),
prepared,
capabilities,
self.owner_scope_id.clone(),
config_json,
self.pairing_store.clone(),
self.settings_store.clone(),
@@ -491,8 +487,7 @@ 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()), None, "default");
let loader = WasmChannelLoader::new(runtime, Arc::new(PairingStore::new()), None);
let dir = TempDir::new().unwrap();
let wasm_path = dir.path().join("test.wasm");
@@ -510,8 +505,7 @@ mod tests {
async fn load_from_dir_returns_empty_when_dir_missing() {
let config = WasmChannelRuntimeConfig::for_testing();
let runtime = Arc::new(WasmChannelRuntime::new(config).unwrap());
let loader =
WasmChannelLoader::new(runtime, Arc::new(PairingStore::new()), None, "default");
let loader = WasmChannelLoader::new(runtime, Arc::new(PairingStore::new()), None);
let dir = TempDir::new().unwrap();
let missing = dir.path().join("nonexistent_channels_dir");
+1 -3
View File
@@ -69,7 +69,7 @@
//! let runtime = WasmChannelRuntime::new(config)?;
//!
//! // Load channels from directory
//! let loader = WasmChannelLoader::new(runtime, pairing_store, settings_store, owner_scope_id);
//! let loader = WasmChannelLoader::new(runtime);
//! let channels = loader.load_from_dir(Path::new("~/.ironclaw/channels/")).await?;
//!
//! // Add to channel manager
@@ -90,7 +90,6 @@ pub mod setup;
pub(crate) mod signature;
#[allow(dead_code)]
pub(crate) mod storage;
mod telegram_host_config;
mod wrapper;
// Core types
@@ -108,5 +107,4 @@ pub use schema::{
ChannelCapabilitiesFile, ChannelConfig, SecretSetupSchema, SetupSchema, WebhookSchema,
};
pub use setup::{WasmChannelSetup, inject_channel_credentials, setup_wasm_channels};
pub(crate) use telegram_host_config::{TELEGRAM_CHANNEL_NAME, bot_username_setting_key};
pub use wrapper::{HttpResponse, SharedWasmChannel, WasmChannel};
-1
View File
@@ -672,7 +672,6 @@ mod tests {
runtime,
prepared,
capabilities,
"default",
"{}".to_string(),
Arc::new(PairingStore::new()),
None,
+10 -38
View File
@@ -7,9 +7,8 @@ use std::collections::HashSet;
use std::sync::Arc;
use crate::channels::wasm::{
LoadedChannel, RegisteredEndpoint, SharedWasmChannel, TELEGRAM_CHANNEL_NAME, WasmChannel,
WasmChannelLoader, WasmChannelRouter, WasmChannelRuntime, WasmChannelRuntimeConfig,
bot_username_setting_key, create_wasm_channel_router,
LoadedChannel, RegisteredEndpoint, SharedWasmChannel, WasmChannel, WasmChannelLoader,
WasmChannelRouter, WasmChannelRuntime, WasmChannelRuntimeConfig, create_wasm_channel_router,
};
use crate::config::Config;
use crate::db::Database;
@@ -49,8 +48,7 @@ pub async fn setup_wasm_channels(
let mut loader = WasmChannelLoader::new(
Arc::clone(&runtime),
Arc::clone(&pairing_store),
settings_store.clone(),
config.owner_id.clone(),
settings_store,
);
if let Some(secrets) = secrets_store {
loader = loader.with_secrets_store(Arc::clone(secrets));
@@ -72,14 +70,7 @@ pub async fn setup_wasm_channels(
let mut channel_names: Vec<String> = Vec::new();
for loaded in results.loaded {
let (name, channel) = register_channel(
loaded,
config,
secrets_store,
settings_store.as_ref(),
&wasm_router,
)
.await;
let (name, channel) = register_channel(loaded, config, secrets_store, &wasm_router).await;
channel_names.push(name.clone());
channels.push((name, channel));
}
@@ -113,16 +104,10 @@ async fn register_channel(
loaded: LoadedChannel,
config: &Config,
secrets_store: &Option<Arc<dyn SecretsStore + Send + Sync>>,
settings_store: Option<&Arc<dyn crate::db::SettingsStore>>,
wasm_router: &Arc<WasmChannelRouter>,
) -> (String, Box<dyn crate::channels::Channel>) {
let channel_name = loaded.name().to_string();
tracing::info!("Loaded WASM channel: {}", channel_name);
let owner_actor_id = config
.channels
.wasm_channel_owner_ids
.get(channel_name.as_str())
.map(ToString::to_string);
let secret_name = loaded.webhook_secret_name();
let sig_key_secret_name = loaded.signature_key_secret_name();
@@ -130,7 +115,7 @@ async fn register_channel(
let webhook_secret = if let Some(secrets) = secrets_store {
secrets
.get_decrypted(&config.owner_id, &secret_name)
.get_decrypted("default", &secret_name)
.await
.ok()
.map(|s| s.expose().to_string())
@@ -148,7 +133,7 @@ async fn register_channel(
require_secret: webhook_secret.is_some(),
}];
let channel_arc = Arc::new(loaded.channel.with_owner_actor_id(owner_actor_id.clone()));
let channel_arc = Arc::new(loaded.channel);
// Inject runtime config (tunnel URL, webhook secret, owner_id).
{
@@ -176,15 +161,6 @@ async fn register_channel(
config_updates.insert("owner_id".to_string(), serde_json::json!(owner_id));
}
if channel_name == TELEGRAM_CHANNEL_NAME
&& let Some(store) = settings_store
&& let Ok(Some(serde_json::Value::String(username))) = store
.get_setting("default", &bot_username_setting_key(&channel_name))
.await
&& !username.trim().is_empty()
{
config_updates.insert("bot_username".to_string(), serde_json::json!(username));
}
// Inject channel-specific secrets into config for channels that need
// credentials in API request bodies (e.g., Feishu token exchange).
// The credential injection system only replaces placeholders in URLs
@@ -222,7 +198,7 @@ async fn register_channel(
// Register Ed25519 signature key if declared in capabilities.
if let Some(ref sig_key_name) = sig_key_secret_name
&& let Some(secrets) = secrets_store
&& let Ok(key_secret) = secrets.get_decrypted(&config.owner_id, sig_key_name).await
&& let Ok(key_secret) = secrets.get_decrypted("default", sig_key_name).await
{
match wasm_router
.register_signature_key(&channel_name, key_secret.expose())
@@ -240,9 +216,7 @@ async fn register_channel(
// Register HMAC signing secret if declared in capabilities.
if let Some(ref hmac_secret_name) = hmac_secret_name
&& let Some(secrets) = secrets_store
&& let Ok(secret) = secrets
.get_decrypted(&config.owner_id, hmac_secret_name)
.await
&& let Ok(secret) = secrets.get_decrypted("default", hmac_secret_name).await
{
wasm_router
.register_hmac_secret(&channel_name, secret.expose())
@@ -257,7 +231,6 @@ async fn register_channel(
.as_ref()
.map(|s| s.as_ref() as &dyn SecretsStore),
&channel_name,
&config.owner_id,
)
.await
{
@@ -295,7 +268,6 @@ pub async fn inject_channel_credentials(
channel: &Arc<WasmChannel>,
secrets: Option<&dyn SecretsStore>,
channel_name: &str,
owner_id: &str,
) -> anyhow::Result<usize> {
if channel_name.trim().is_empty() {
return Ok(0);
@@ -307,7 +279,7 @@ pub async fn inject_channel_credentials(
// 1. Try injecting from persistent secrets store if available
if let Some(secrets) = secrets {
let all_secrets = secrets
.list(owner_id)
.list("default")
.await
.map_err(|e| anyhow::anyhow!("Failed to list secrets: {}", e))?;
@@ -318,7 +290,7 @@ pub async fn inject_channel_credentials(
continue;
}
let decrypted = match secrets.get_decrypted(owner_id, &secret_meta.name).await {
let decrypted = match secrets.get_decrypted("default", &secret_meta.name).await {
Ok(d) => d,
Err(e) => {
tracing::warn!(
@@ -1,6 +0,0 @@
pub const TELEGRAM_CHANNEL_NAME: &str = "telegram";
const TELEGRAM_BOT_USERNAME_SETTING_PREFIX: &str = "channels.wasm_channel_bot_usernames";
pub fn bot_username_setting_key(channel_name: &str) -> String {
format!("{TELEGRAM_BOT_USERNAME_SETTING_PREFIX}.{channel_name}")
}
File diff suppressed because it is too large Load Diff
+10 -25
View File
@@ -162,30 +162,15 @@ pub async fn chat_auth_token_handler(
.await
{
Ok(result) => {
let mut resp = ActionResponse::ok(result.message.clone());
resp.activated = Some(result.activated);
resp.auth_url = result.auth_url.clone();
resp.verification = result.verification.clone();
resp.instructions = result.verification.as_ref().map(|v| v.instructions.clone());
clear_auth_mode(&state).await;
if result.verification.is_some() {
state.sse.broadcast(SseEvent::AuthRequired {
extension_name: req.extension_name.clone(),
instructions: Some(result.message),
auth_url: None,
setup_url: None,
});
} else {
clear_auth_mode(&state).await;
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: req.extension_name.clone(),
success: true,
message: result.message.clone(),
});
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: req.extension_name.clone(),
success: true,
message: result.message,
});
}
Ok(Json(resp))
Ok(Json(ActionResponse::ok(result.message)))
}
Err(e) => {
let msg = e.to_string();
@@ -359,7 +344,7 @@ pub async fn chat_history_handler(
turn_number: t.turn_number,
user_input: t.user_input.clone(),
response: t.response.clone(),
state: format!("{:?}", t.state),
state: format!("{:?}", t.state()),
started_at: t.started_at.to_rfc3339(),
completed_at: t.completed_at.map(|dt| dt.to_rfc3339()),
tool_calls: t
@@ -512,7 +497,7 @@ pub async fn chat_threads_handler(
.into_iter()
.map(|t| ThreadInfo {
id: t.id,
state: format!("{:?}", t.state),
state: format!("{:?}", t.state()),
turn_count: t.turns.len(),
created_at: t.created_at.to_rfc3339(),
updated_at: t.updated_at.to_rfc3339(),
@@ -547,7 +532,7 @@ pub async fn chat_new_thread_handler(
let id = thread.id;
let info = ThreadInfo {
id: thread.id,
state: format!("{:?}", thread.state),
state: format!("{:?}", thread.state()),
turn_count: thread.turns.len(),
created_at: thread.created_at.to_rfc3339(),
updated_at: thread.updated_at.to_rfc3339(),
+20 -20
View File
@@ -25,34 +25,34 @@ pub async fn extensions_list_handler(
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
let pairing_store = crate::pairing::PairingStore::new();
let mut owner_bound_channels = std::collections::HashSet::new();
for ext in &installed {
if ext.kind == crate::extensions::ExtensionKind::WasmChannel
&& ext_mgr.has_wasm_channel_owner_binding(&ext.name).await
{
owner_bound_channels.insert(ext.name.clone());
}
}
let extensions = installed
.into_iter()
.map(|ext| {
let activation_status = if ext.kind == crate::extensions::ExtensionKind::WasmChannel {
let has_paired = pairing_store
.read_allow_from(&ext.name)
.map(|list| !list.is_empty())
.unwrap_or(false);
crate::channels::web::types::classify_wasm_channel_activation(
&ext,
has_paired,
owner_bound_channels.contains(&ext.name),
)
Some(if ext.activation_error.is_some() {
"failed".to_string()
} else if !ext.authenticated {
"installed".to_string()
} else if ext.active {
let has_paired = pairing_store
.read_allow_from(&ext.name)
.map(|list| !list.is_empty())
.unwrap_or(false);
if has_paired {
"active".to_string()
} else {
"pairing".to_string()
}
} else {
"configured".to_string()
})
} else if ext.kind == crate::extensions::ExtensionKind::ChannelRelay {
Some(if ext.active {
crate::channels::web::types::ExtensionActivationStatus::Active
"active".to_string()
} else if ext.authenticated {
crate::channels::web::types::ExtensionActivationStatus::Configured
"configured".to_string()
} else {
crate::channels::web::types::ExtensionActivationStatus::Installed
"installed".to_string()
})
} else {
None
+118 -243
View File
@@ -26,6 +26,7 @@ use tower_http::set_header::SetResponseHeaderLayer;
use uuid::Uuid;
use crate::agent::SessionManager;
use crate::agent::routine::{Trigger, next_cron_fire};
use crate::bootstrap::ironclaw_base_dir;
use crate::channels::IncomingMessage;
use crate::channels::relay::DEFAULT_RELAY_NAME;
@@ -35,7 +36,6 @@ use crate::channels::web::handlers::jobs::{
jobs_events_handler, jobs_list_handler, jobs_prompt_handler, jobs_restart_handler,
jobs_summary_handler,
};
use crate::channels::web::handlers::routines::{routines_delete_handler, routines_toggle_handler};
use crate::channels::web::handlers::skills::{
skills_install_handler, skills_list_handler, skills_remove_handler, skills_search_handler,
};
@@ -1163,43 +1163,19 @@ async fn chat_auth_token_handler(
.configure_token(&req.extension_name, &req.token)
.await
{
Ok(result) => {
let mut resp = if result.verification.is_some() || result.activated {
ActionResponse::ok(result.message.clone())
} else {
ActionResponse::fail(result.message.clone())
};
resp.activated = Some(result.activated);
resp.auth_url = result.auth_url.clone();
resp.verification = result.verification.clone();
resp.instructions = result.verification.as_ref().map(|v| v.instructions.clone());
Ok(result) if result.activated => {
// Clear auth mode on the active thread
clear_auth_mode(&state).await;
if result.verification.is_some() {
state.sse.broadcast(SseEvent::AuthRequired {
extension_name: req.extension_name.clone(),
instructions: Some(result.message),
auth_url: None,
setup_url: None,
});
} else if result.activated {
// Clear auth mode on the active thread
clear_auth_mode(&state).await;
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: req.extension_name.clone(),
success: true,
message: result.message.clone(),
});
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: req.extension_name.clone(),
success: true,
message: result.message,
});
} else {
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: req.extension_name.clone(),
success: false,
message: result.message,
});
}
Ok(Json(resp))
Ok(Json(ActionResponse::ok(result.message)))
}
Ok(result) => Ok(Json(ActionResponse::fail(result.message))),
Err(e) => {
let msg = e.to_string();
// Re-emit auth_required for retry on validation errors
@@ -1378,7 +1354,7 @@ async fn chat_history_handler(
turn_number: t.turn_number,
user_input: t.user_input.clone(),
response: t.response.clone(),
state: format!("{:?}", t.state),
state: format!("{:?}", t.state()),
started_at: t.started_at.to_rfc3339(),
completed_at: t.completed_at.map(|dt| dt.to_rfc3339()),
tool_calls: t
@@ -1524,7 +1500,7 @@ async fn chat_threads_handler(
.into_iter()
.map(|t| ThreadInfo {
id: t.id,
state: format!("{:?}", t.state),
state: format!("{:?}", t.state()),
turn_count: t.turns.len(),
created_at: t.created_at.to_rfc3339(),
updated_at: t.updated_at.to_rfc3339(),
@@ -1556,7 +1532,7 @@ async fn chat_new_thread_handler(
let id = thread.id;
let info = ThreadInfo {
id: thread.id,
state: format!("{:?}", thread.state),
state: format!("{:?}", thread.state()),
turn_count: thread.turns.len(),
created_at: thread.created_at.to_rfc3339(),
updated_at: thread.updated_at.to_rfc3339(),
@@ -1842,34 +1818,29 @@ async fn extensions_list_handler(
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
let pairing_store = crate::pairing::PairingStore::new();
let mut owner_bound_channels = std::collections::HashSet::new();
for ext in &installed {
if ext.kind == crate::extensions::ExtensionKind::WasmChannel
&& ext_mgr.has_wasm_channel_owner_binding(&ext.name).await
{
owner_bound_channels.insert(ext.name.clone());
}
}
let extensions = installed
.into_iter()
.map(|ext| {
let activation_status = if ext.kind == crate::extensions::ExtensionKind::WasmChannel {
let has_paired = pairing_store
.read_allow_from(&ext.name)
.map(|list| !list.is_empty())
.unwrap_or(false);
crate::channels::web::types::classify_wasm_channel_activation(
&ext,
has_paired,
owner_bound_channels.contains(&ext.name),
)
} else if ext.kind == crate::extensions::ExtensionKind::ChannelRelay {
Some(if ext.active {
ExtensionActivationStatus::Active
} else if ext.authenticated {
ExtensionActivationStatus::Configured
Some(if ext.activation_error.is_some() {
"failed".to_string()
} else if !ext.authenticated {
// No credentials configured yet.
"installed".to_string()
} else if ext.active {
// Check pairing status for active channels.
let has_paired = pairing_store
.read_allow_from(&ext.name)
.map(|list| !list.is_empty())
.unwrap_or(false);
if has_paired {
"active".to_string()
} else {
"pairing".to_string()
}
} else {
ExtensionActivationStatus::Installed
// Authenticated but not yet active.
"configured".to_string()
})
} else {
None
@@ -2234,24 +2205,20 @@ async fn extensions_setup_submit_handler(
match ext_mgr.configure(&name, &req.secrets).await {
Ok(result) => {
let mut resp = if result.verification.is_some() || result.activated {
// Broadcast completion status so chat UI can dismiss success cases while
// leaving failed auth/configuration flows visible for correction.
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: name.clone(),
success: result.activated,
message: result.message.clone(),
});
let mut resp = if result.activated {
ActionResponse::ok(result.message)
} else {
ActionResponse::fail(result.message)
};
resp.activated = Some(result.activated);
resp.auth_url = result.auth_url.clone();
resp.verification = result.verification.clone();
resp.instructions = result.verification.as_ref().map(|v| v.instructions.clone());
if result.verification.is_none() {
// Broadcast auth_completed so the chat UI can dismiss any in-progress
// auth card or setup modal that was triggered by tool_auth/tool_activate.
state.sse.broadcast(SseEvent::AuthCompleted {
extension_name: name.clone(),
success: result.activated,
message: resp.message.clone(),
});
}
resp.auth_url = result.auth_url;
Ok(Json(resp))
}
Err(e) => Ok(Json(ActionResponse::fail(e.to_string()))),
@@ -2463,6 +2430,83 @@ async fn routines_trigger_handler(
})))
}
#[derive(Deserialize)]
struct ToggleRequest {
enabled: Option<bool>,
}
async fn routines_toggle_handler(
State(state): State<Arc<GatewayState>>,
Path(id): Path<String>,
body: Option<Json<ToggleRequest>>,
) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
let store = state.store.as_ref().ok_or((
StatusCode::SERVICE_UNAVAILABLE,
"Database not available".to_string(),
))?;
let routine_id = Uuid::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid routine ID".to_string()))?;
let mut routine = store
.get_routine(routine_id)
.await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
.ok_or((StatusCode::NOT_FOUND, "Routine not found".to_string()))?;
let was_enabled = routine.enabled;
// If a specific value was provided, use it; otherwise toggle.
routine.enabled = match body {
Some(Json(req)) => req.enabled.unwrap_or(!routine.enabled),
None => !routine.enabled,
};
if routine.enabled
&& !was_enabled
&& let Trigger::Cron { schedule, timezone } = &routine.trigger
{
routine.next_fire_at = next_cron_fire(schedule, timezone.as_deref())
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
}
store
.update_routine(&routine)
.await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
Ok(Json(serde_json::json!({
"status": if routine.enabled { "enabled" } else { "disabled" },
"routine_id": routine_id,
})))
}
async fn routines_delete_handler(
State(state): State<Arc<GatewayState>>,
Path(id): Path<String>,
) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
let store = state.store.as_ref().ok_or((
StatusCode::SERVICE_UNAVAILABLE,
"Database not available".to_string(),
))?;
let routine_id = Uuid::parse_str(&id)
.map_err(|_| (StatusCode::BAD_REQUEST, "Invalid routine ID".to_string()))?;
let deleted = store
.delete_routine(routine_id)
.await
.map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
if deleted {
Ok(Json(serde_json::json!({
"status": "deleted",
"routine_id": routine_id,
})))
} else {
Err((StatusCode::NOT_FOUND, "Routine not found".to_string()))
}
}
async fn routines_runs_handler(
State(state): State<Arc<GatewayState>>,
Path(id): Path<String>,
@@ -2699,11 +2743,7 @@ struct GatewayStatusResponse {
#[cfg(test)]
mod tests {
use super::*;
use crate::channels::web::types::{
ExtensionActivationStatus, classify_wasm_channel_activation,
};
use crate::cli::oauth_defaults;
use crate::extensions::{ExtensionKind, InstalledExtension};
use crate::testing::credentials::TEST_GATEWAY_CRYPTO_KEY;
#[test]
@@ -2782,85 +2822,6 @@ mod tests {
assert!(turns.is_empty());
}
#[test]
fn test_wasm_channel_activation_status_owner_bound_counts_as_active() -> Result<(), String> {
let ext = InstalledExtension {
name: "telegram".to_string(),
kind: ExtensionKind::WasmChannel,
display_name: Some("Telegram".to_string()),
description: None,
url: None,
authenticated: true,
active: true,
tools: Vec::new(),
needs_setup: true,
has_auth: false,
installed: true,
activation_error: None,
version: None,
};
let owner_bound = classify_wasm_channel_activation(&ext, false, true);
if owner_bound != Some(ExtensionActivationStatus::Active) {
return Err(format!(
"owner-bound channel should be active, got {:?}",
owner_bound
));
}
let unbound = classify_wasm_channel_activation(&ext, false, false);
if unbound != Some(ExtensionActivationStatus::Pairing) {
return Err(format!(
"unbound channel should be pairing, got {:?}",
unbound
));
}
Ok(())
}
#[test]
fn test_channel_relay_activation_status_is_preserved() -> Result<(), String> {
let relay = InstalledExtension {
name: "signal".to_string(),
kind: ExtensionKind::ChannelRelay,
display_name: Some("Signal".to_string()),
description: None,
url: None,
authenticated: true,
active: false,
tools: Vec::new(),
needs_setup: true,
has_auth: false,
installed: true,
activation_error: None,
version: None,
};
let status = if relay.kind == crate::extensions::ExtensionKind::WasmChannel {
classify_wasm_channel_activation(&relay, false, false)
} else if relay.kind == crate::extensions::ExtensionKind::ChannelRelay {
Some(if relay.active {
ExtensionActivationStatus::Active
} else if relay.authenticated {
ExtensionActivationStatus::Configured
} else {
ExtensionActivationStatus::Installed
})
} else {
None
};
if status != Some(ExtensionActivationStatus::Configured) {
return Err(format!(
"channel relay should retain configured status, got {:?}",
status
));
}
Ok(())
}
// --- OAuth callback handler tests ---
/// Build a minimal `GatewayState` for testing the OAuth callback handler.
@@ -2974,92 +2935,6 @@ mod tests {
);
}
#[tokio::test]
async fn test_extensions_setup_submit_telegram_verification_does_not_broadcast_auth_required() {
use axum::body::Body;
use tokio::time::{Duration, timeout};
use tower::ServiceExt;
let secrets = test_secrets_store();
let (ext_mgr, _wasm_tools_dir, wasm_channels_dir) = test_ext_mgr(secrets);
std::fs::write(
wasm_channels_dir.path().join("telegram.wasm"),
b"\0asm fake",
)
.expect("write fake telegram wasm");
let caps = serde_json::json!({
"type": "channel",
"name": "telegram",
"setup": {
"required_secrets": [
{
"name": "telegram_bot_token",
"prompt": "Enter your Telegram Bot API token (from @BotFather)"
}
]
}
});
std::fs::write(
wasm_channels_dir.path().join("telegram.capabilities.json"),
serde_json::to_string(&caps).expect("serialize telegram caps"),
)
.expect("write telegram caps");
ext_mgr
.set_test_telegram_pending_verification("iclaw-7qk2m9", Some("test_hot_bot"))
.await;
let state = test_gateway_state(Some(ext_mgr));
let mut receiver = state.sse.sender().subscribe();
let app = Router::new()
.route(
"/api/extensions/{name}/setup",
post(extensions_setup_submit_handler),
)
.with_state(state);
let req_body = serde_json::json!({
"secrets": {
"telegram_bot_token": "123456789:ABCdefGhI"
}
});
let req = axum::http::Request::builder()
.method("POST")
.uri("/api/extensions/telegram/setup")
.header("content-type", "application/json")
.body(Body::from(req_body.to_string()))
.expect("request");
let resp = ServiceExt::<axum::http::Request<Body>>::oneshot(app, req)
.await
.expect("response");
assert_eq!(resp.status(), StatusCode::OK);
let body = axum::body::to_bytes(resp.into_body(), 1024 * 64)
.await
.expect("body");
let parsed: serde_json::Value = serde_json::from_slice(&body).expect("json response");
assert_eq!(parsed["success"], serde_json::Value::Bool(true));
assert_eq!(parsed["activated"], serde_json::Value::Bool(false));
assert_eq!(parsed["verification"]["code"], "iclaw-7qk2m9");
let deadline = tokio::time::Instant::now() + Duration::from_millis(100);
loop {
let remaining = deadline.saturating_duration_since(tokio::time::Instant::now());
if remaining.is_zero() {
break;
}
match timeout(remaining, receiver.recv()).await {
Ok(Ok(crate::channels::web::types::SseEvent::AuthRequired { .. })) => {
panic!("verification responses should not emit auth_required SSE events")
}
Ok(Ok(_)) => continue,
Ok(Err(_)) | Err(_) => break,
}
}
}
fn expired_flow_created_at() -> Option<std::time::Instant> {
std::time::Instant::now()
.checked_sub(oauth_defaults::OAUTH_FLOW_EXPIRY + std::time::Duration::from_secs(1))
+7 -175
View File
@@ -527,6 +527,7 @@ function enableChatInput() {
const btn = document.getElementById('send-btn');
if (input) {
input.disabled = false;
input.placeholder = I18n.t('chat.inputPlaceholder');
}
if (btn) btn.disabled = false;
}
@@ -1204,13 +1205,11 @@ function showJobCard(data) {
// --- Auth card ---
function handleAuthRequired(data) {
setAuthFlowPending(true, data.instructions);
if (data.auth_url) {
setAuthFlowPending(true, data.instructions);
// OAuth flow: show the global auth prompt with an OAuth button + optional token paste field.
showAuthCard(data);
} else {
if (getConfigureOverlay(data.extension_name)) return;
setAuthFlowPending(true, data.instructions);
// Setup flow: fetch the extension's credential schema and show the multi-field
// configure modal (the same UI used by the Extensions tab "Setup" button).
showConfigureModal(data.extension_name);
@@ -1434,11 +1433,13 @@ function setAuthFlowPending(pending, instructions) {
if (authFlowPending) {
input.disabled = true;
btn.disabled = true;
input.placeholder = instructions || 'Complete extension auth to continue chatting';
return;
}
if (!currentThreadIsReadOnly) {
input.disabled = false;
btn.disabled = false;
input.placeholder = I18n.t('chat.inputPlaceholder');
}
}
@@ -2711,11 +2712,8 @@ function renderConfigureModal(name, secrets) {
const overlay = document.createElement('div');
overlay.className = 'configure-overlay';
overlay.setAttribute('data-extension-name', name);
overlay.dataset.telegramVerificationState = 'idle';
overlay.addEventListener('click', (e) => {
if (e.target !== overlay) return;
if (name === 'telegram' && overlay.dataset.telegramVerificationState === 'waiting') return;
closeConfigureModal();
if (e.target === overlay) closeConfigureModal();
});
const modal = document.createElement('div');
@@ -2725,13 +2723,6 @@ function renderConfigureModal(name, secrets) {
header.textContent = I18n.t('config.title', { name: name });
modal.appendChild(header);
if (name === 'telegram') {
const hint = document.createElement('div');
hint.className = 'configure-hint';
hint.textContent = I18n.t('config.telegramOwnerHint');
modal.appendChild(hint);
}
const form = document.createElement('div');
form.className = 'configure-form';
@@ -2739,7 +2730,6 @@ function renderConfigureModal(name, secrets) {
for (const secret of secrets) {
const field = document.createElement('div');
field.className = 'configure-field';
field.dataset.secretName = secret.name;
const label = document.createElement('label');
label.textContent = secret.prompt;
@@ -2784,16 +2774,6 @@ function renderConfigureModal(name, secrets) {
modal.appendChild(form);
const error = document.createElement('div');
error.className = 'configure-inline-error';
error.style.display = 'none';
modal.appendChild(error);
const status = document.createElement('div');
status.className = 'configure-inline-status';
status.style.display = 'none';
modal.appendChild(status);
const actions = document.createElement('div');
actions.className = 'configure-actions';
@@ -2816,110 +2796,7 @@ function renderConfigureModal(name, secrets) {
if (fields.length > 0) fields[0].input.focus();
}
function renderTelegramVerificationChallenge(overlay, verification) {
if (!overlay || !verification) return;
const modal = overlay.querySelector('.configure-modal');
if (!modal) return;
const telegramField = modal.querySelector('.configure-field[data-secret-name="telegram_bot_token"]');
let panel = modal.querySelector('.configure-verification');
if (!panel) {
panel = document.createElement('div');
panel.className = 'configure-verification';
}
if (telegramField && telegramField.parentNode) {
telegramField.insertAdjacentElement('afterend', panel);
} else {
modal.insertBefore(
panel,
modal.querySelector('.configure-inline-error') || modal.querySelector('.configure-actions')
);
}
panel.innerHTML = '';
const title = document.createElement('div');
title.className = 'configure-verification-title';
title.textContent = I18n.t('config.telegramChallengeTitle');
panel.appendChild(title);
const instructions = document.createElement('div');
instructions.className = 'configure-verification-instructions';
instructions.textContent = verification.instructions;
panel.appendChild(instructions);
const commandLabel = document.createElement('div');
commandLabel.className = 'configure-verification-instructions';
commandLabel.textContent = I18n.t('config.telegramCommandLabel');
panel.appendChild(commandLabel);
const command = document.createElement('code');
command.className = 'configure-verification-code';
command.textContent = '/start ' + verification.code;
panel.appendChild(command);
if (verification.deep_link) {
const link = document.createElement('a');
link.className = 'configure-verification-link';
link.href = verification.deep_link;
link.target = '_blank';
link.rel = 'noreferrer noopener';
link.textContent = I18n.t('config.telegramOpenBot');
panel.appendChild(link);
}
}
function getConfigurePrimaryButton(overlay) {
return overlay && overlay.querySelector('.configure-actions button.btn-ext.activate');
}
function getConfigureCancelButton(overlay) {
return overlay && overlay.querySelector('.configure-actions button.btn-ext.remove');
}
function setConfigureInlineError(overlay, message) {
const error = overlay && overlay.querySelector('.configure-inline-error');
if (!error) return;
error.textContent = message || '';
error.style.display = message ? 'block' : 'none';
}
function clearConfigureInlineError(overlay) {
setConfigureInlineError(overlay, '');
}
function setConfigureInlineStatus(overlay, message) {
const status = overlay && overlay.querySelector('.configure-inline-status');
if (!status) return;
status.textContent = message || '';
status.style.display = message ? 'block' : 'none';
}
function setTelegramConfigureState(overlay, fields, state) {
if (!overlay) return;
overlay.dataset.telegramVerificationState = state;
const primaryBtn = getConfigurePrimaryButton(overlay);
const cancelBtn = getConfigureCancelButton(overlay);
const waiting = state === 'waiting';
const retry = state === 'retry';
setConfigureInlineStatus(overlay, waiting ? I18n.t('config.telegramOwnerWaiting') : '');
if (primaryBtn) {
primaryBtn.style.display = waiting ? 'none' : '';
primaryBtn.disabled = false;
primaryBtn.textContent = retry ? I18n.t('config.telegramStartOver') : I18n.t('config.save');
}
if (cancelBtn) cancelBtn.disabled = waiting;
}
function startTelegramAutoVerify(name, fields) {
window.setTimeout(() => submitConfigureModal(name, fields, { telegramAutoVerify: true }), 0);
}
function submitConfigureModal(name, fields, options) {
options = options || {};
function submitConfigureModal(name, fields) {
const secrets = {};
for (const f of fields) {
if (f.input.value.trim()) {
@@ -2927,16 +2804,10 @@ function submitConfigureModal(name, fields, options) {
}
}
const overlay = getConfigureOverlay(name) || document.querySelector('.configure-overlay');
const isTelegram = name === 'telegram';
clearConfigureInlineError(overlay);
// Disable buttons to prevent double-submit
const overlay = getConfigureOverlay(name) || document.querySelector('.configure-overlay');
var btns = overlay ? overlay.querySelectorAll('.configure-actions button') : [];
btns.forEach(function(b) { b.disabled = true; });
if (overlay && isTelegram) {
setTelegramConfigureState(overlay, fields, 'waiting');
}
apiFetch('/api/extensions/' + encodeURIComponent(name) + '/setup', {
method: 'POST',
@@ -2944,23 +2815,6 @@ function submitConfigureModal(name, fields, options) {
})
.then((res) => {
if (res.success) {
if (res.verification && isTelegram) {
renderTelegramVerificationChallenge(overlay, res.verification);
fields.forEach(function(f) { f.input.value = ''; });
setTelegramConfigureState(overlay, fields, 'waiting');
// Once the verification challenge is rendered inline, the global auth lock
// should not keep the chat composer disabled for this setup-driven flow.
setAuthFlowPending(false);
enableChatInput();
if (!options.telegramAutoVerify) {
startTelegramAutoVerify(name, fields);
return;
}
setTelegramConfigureState(overlay, fields, 'retry');
setConfigureInlineError(overlay, I18n.t('config.telegramStartOverHint'));
return;
}
closeConfigureModal();
if (res.auth_url) {
showAuthCard({
@@ -2976,29 +2830,11 @@ function submitConfigureModal(name, fields, options) {
} else {
// Keep modal open so the user can correct their input and retry.
btns.forEach(function(b) { b.disabled = false; });
setConfigureInlineError(overlay, res.message || 'Configuration failed');
if (isTelegram) {
const hasVerification = overlay && overlay.querySelector('.configure-verification');
if (options.telegramAutoVerify || hasVerification) {
setTelegramConfigureState(overlay, fields, 'retry');
} else {
setTelegramConfigureState(overlay, fields, 'idle');
}
}
showToast(res.message || 'Configuration failed', 'error');
}
})
.catch((err) => {
btns.forEach(function(b) { b.disabled = false; });
setConfigureInlineError(overlay, 'Configuration failed: ' + err.message);
if (isTelegram) {
const hasVerification = overlay && overlay.querySelector('.configure-verification');
if (options.telegramAutoVerify || hasVerification) {
setTelegramConfigureState(overlay, fields, 'retry');
} else {
setTelegramConfigureState(overlay, fields, 'idle');
}
}
showToast('Configuration failed: ' + err.message, 'error');
});
}
@@ -3007,10 +2843,6 @@ function closeConfigureModal(extensionName) {
if (typeof extensionName !== 'string') extensionName = null;
const existing = getConfigureOverlay(extensionName);
if (existing) existing.remove();
if (!document.querySelector('.configure-overlay') && !document.querySelector('.auth-card')) {
setAuthFlowPending(false);
enableChatInput();
}
}
// Validate that a server-supplied OAuth URL is HTTPS before opening a popup.
-7
View File
@@ -342,13 +342,6 @@ I18n.register('en', {
// Configure
'config.title': 'Configure {name}',
'config.telegramOwnerHint': 'After saving, IronClaw will show a one-time code. Send `/start CODE` to your bot in Telegram and IronClaw will finish setup automatically.',
'config.telegramChallengeTitle': 'Telegram owner verification',
'config.telegramOwnerWaiting': 'Waiting for Telegram owner verification...',
'config.telegramCommandLabel': 'Send this in Telegram:',
'config.telegramStartOver': 'Start over',
'config.telegramStartOverHint': 'Telegram verification did not complete. Click Start over to generate a new code and try again.',
'config.telegramOpenBot': 'Open bot in Telegram',
'config.optional': ' (optional)',
'config.alreadySet': '(already set — leave empty to keep)',
'config.alreadyConfigured': 'Already configured',
-6
View File
@@ -342,12 +342,6 @@ I18n.register('zh-CN', {
// 配置
'config.title': '配置 {name}',
'config.telegramOwnerHint': '保存后,IronClaw 会显示一次性验证码。将 `/start CODE` 发送给你的 Telegram 机器人,IronClaw 会自动完成设置。',
'config.telegramChallengeTitle': 'Telegram 所有者验证',
'config.telegramOwnerWaiting': '正在等待 Telegram 所有者验证...',
'config.telegramCommandLabel': '请在 Telegram 中发送:',
'config.telegramStartOver': '重新开始',
'config.telegramStartOverHint': 'Telegram 验证未完成。点击“重新开始”以生成新的验证码并重试。',
'config.optional': '(可选)',
'config.alreadySet': '(已设置 — 留空以保持不变)',
'config.alreadyConfigured': '已配置',
-78
View File
@@ -2896,84 +2896,6 @@ body {
color: var(--text-primary);
}
.configure-hint {
margin: 0 0 16px 0;
padding: 10px 12px;
border-radius: 8px;
background: var(--bg-secondary);
border: 1px solid var(--border);
color: var(--text-secondary);
font-size: 13px;
line-height: 1.5;
}
.configure-verification {
display: flex;
flex-direction: column;
gap: 10px;
margin: 16px 0 0 0;
padding: 12px;
border-radius: 8px;
background: var(--bg-secondary);
border: 1px solid var(--border);
}
.configure-verification-title {
font-size: 13px;
font-weight: 600;
color: var(--text-primary);
}
.configure-verification-instructions {
font-size: 13px;
line-height: 1.5;
color: var(--text-secondary);
}
.configure-verification-code {
display: inline-block;
width: fit-content;
padding: 6px 10px;
border-radius: 6px;
background: rgba(255, 255, 255, 0.06);
border: 1px solid var(--border);
color: var(--text-primary);
font-size: 13px;
}
.configure-verification-link {
width: fit-content;
color: var(--accent, var(--text-link, #4ea3ff));
font-size: 13px;
text-decoration: none;
}
.configure-verification-link:hover {
text-decoration: underline;
}
.configure-inline-error {
margin: 16px 0 0 0;
padding: 10px 12px;
border-radius: 8px;
background: rgba(220, 38, 38, 0.12);
border: 1px solid rgba(220, 38, 38, 0.35);
color: #fca5a5;
font-size: 13px;
line-height: 1.5;
}
.configure-inline-status {
margin: 16px 0 0 0;
padding: 10px 12px;
border-radius: 8px;
background: var(--bg-secondary);
border: 1px solid var(--border);
color: var(--text-secondary);
font-size: 13px;
line-height: 1.5;
}
.configure-form {
display: flex;
flex-direction: column;
+5 -184
View File
@@ -116,149 +116,9 @@ pub struct ApprovalRequest {
// --- SSE Event Types ---
#[derive(Debug, Clone, Serialize)]
#[serde(tag = "type")]
pub enum SseEvent {
#[serde(rename = "response")]
Response { content: String, thread_id: String },
#[serde(rename = "thinking")]
Thinking {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_started")]
ToolStarted {
name: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_completed")]
ToolCompleted {
name: String,
success: bool,
#[serde(skip_serializing_if = "Option::is_none")]
error: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
parameters: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_result")]
ToolResult {
name: String,
preview: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "stream_chunk")]
StreamChunk {
content: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "status")]
Status {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "job_started")]
JobStarted {
job_id: String,
title: String,
browse_url: String,
},
#[serde(rename = "approval_needed")]
ApprovalNeeded {
request_id: String,
tool_name: String,
description: String,
parameters: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "auth_required")]
AuthRequired {
extension_name: String,
#[serde(skip_serializing_if = "Option::is_none")]
instructions: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
auth_url: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
setup_url: Option<String>,
},
#[serde(rename = "auth_completed")]
AuthCompleted {
extension_name: String,
success: bool,
message: String,
},
#[serde(rename = "error")]
Error {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "heartbeat")]
Heartbeat,
// Sandbox job streaming events (worker + Claude Code bridge)
#[serde(rename = "job_message")]
JobMessage {
job_id: String,
role: String,
content: String,
},
#[serde(rename = "job_tool_use")]
JobToolUse {
job_id: String,
tool_name: String,
input: serde_json::Value,
},
#[serde(rename = "job_tool_result")]
JobToolResult {
job_id: String,
tool_name: String,
output: String,
},
#[serde(rename = "job_status")]
JobStatus { job_id: String, message: String },
#[serde(rename = "job_result")]
JobResult {
job_id: String,
status: String,
#[serde(skip_serializing_if = "Option::is_none")]
session_id: Option<String>,
},
/// An image was generated by a tool.
#[serde(rename = "image_generated")]
ImageGenerated {
data_url: String,
#[serde(skip_serializing_if = "Option::is_none")]
path: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
/// Suggested follow-up messages for the user.
#[serde(rename = "suggestions")]
Suggestions {
suggestions: Vec<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
/// Extension activation status change (WASM channels).
#[serde(rename = "extension_status")]
ExtensionStatus {
extension_name: String,
status: String,
#[serde(skip_serializing_if = "Option::is_none")]
message: Option<String>,
},
}
/// Re-export from `crate::events::DomainEvent` — the canonical event enum now
/// lives in a channel-neutral location so agent code doesn't depend on `channels::web`.
pub use crate::events::DomainEvent as SseEvent;
// --- Memory ---
@@ -410,40 +270,6 @@ pub struct TransitionInfo {
// --- Extensions ---
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize)]
#[serde(rename_all = "snake_case")]
pub enum ExtensionActivationStatus {
Installed,
Configured,
Pairing,
Active,
Failed,
}
pub fn classify_wasm_channel_activation(
ext: &crate::extensions::InstalledExtension,
has_paired: bool,
has_owner_binding: bool,
) -> Option<ExtensionActivationStatus> {
if ext.kind != crate::extensions::ExtensionKind::WasmChannel {
return None;
}
Some(if ext.activation_error.is_some() {
ExtensionActivationStatus::Failed
} else if !ext.authenticated {
ExtensionActivationStatus::Installed
} else if ext.active {
if has_paired || has_owner_binding {
ExtensionActivationStatus::Active
} else {
ExtensionActivationStatus::Pairing
}
} else {
ExtensionActivationStatus::Configured
})
}
#[derive(Debug, Serialize)]
pub struct ExtensionInfo {
pub name: String,
@@ -462,9 +288,9 @@ pub struct ExtensionInfo {
/// Whether this extension has an auth configuration (OAuth or manual token).
#[serde(default)]
pub has_auth: bool,
/// WASM channel activation status.
/// WASM channel activation status: "installed", "configured", "active", "failed".
#[serde(skip_serializing_if = "Option::is_none")]
pub activation_status: Option<ExtensionActivationStatus>,
pub activation_status: Option<String>,
/// Human-readable error when activation_status is "failed".
#[serde(skip_serializing_if = "Option::is_none")]
pub activation_error: Option<String>,
@@ -537,9 +363,6 @@ pub struct ActionResponse {
/// Whether the channel was successfully activated after setup.
#[serde(skip_serializing_if = "Option::is_none")]
pub activated: Option<bool>,
/// Pending manual verification challenge (for Telegram owner binding, etc.).
#[serde(skip_serializing_if = "Option::is_none")]
pub verification: Option<crate::extensions::VerificationChallenge>,
}
impl ActionResponse {
@@ -551,7 +374,6 @@ impl ActionResponse {
awaiting_token: None,
instructions: None,
activated: None,
verification: None,
}
}
@@ -563,7 +385,6 @@ impl ActionResponse {
awaiting_token: None,
instructions: None,
activated: None,
verification: None,
}
}
}
+3 -21
View File
@@ -2,28 +2,10 @@
use crate::channels::web::types::{ToolCallInfo, TurnInfo};
/// Truncate a string to at most `max_bytes` bytes at a char boundary, appending "...".
///
/// If the input is wrapped in `<tool_output …>…</tool_output>` and truncation
/// removes the closing tag, the tag is re-appended so downstream XML parsers
/// never see an unclosed element.
/// Delegates to [`crate::util::truncate_preview`] — the canonical implementation
/// now lives in the shared utility module so non-web code can use it too.
pub fn truncate_preview(s: &str, max_bytes: usize) -> String {
if s.len() <= max_bytes {
return s.to_string();
}
// Walk backwards from max_bytes to find a valid char boundary
let mut end = max_bytes;
while end > 0 && !s.is_char_boundary(end) {
end -= 1;
}
let mut result = format!("{}...", &s[..end]);
// Re-close <tool_output> if truncation cut through the closing tag.
if s.starts_with("<tool_output") && !result.ends_with("</tool_output>") {
result.push_str("\n</tool_output>");
}
result
crate::util::truncate_preview(s, max_bytes)
}
/// Build TurnInfo pairs from flat DB messages (user/tool_calls/assistant triples).
+8 -19
View File
@@ -265,25 +265,14 @@ async fn handle_client_message(
if let Some(ref ext_mgr) = state.extension_manager {
match ext_mgr.configure_token(&extension_name, &token).await {
Ok(result) => {
if result.verification.is_some() {
state.sse.broadcast(
crate::channels::web::types::SseEvent::AuthRequired {
extension_name: extension_name.clone(),
instructions: Some(result.message),
auth_url: None,
setup_url: None,
},
);
} else {
crate::channels::web::server::clear_auth_mode(state).await;
state.sse.broadcast(
crate::channels::web::types::SseEvent::AuthCompleted {
extension_name,
success: true,
message: result.message,
},
);
}
crate::channels::web::server::clear_auth_mode(state).await;
state
.sse
.broadcast(crate::channels::web::types::SseEvent::AuthCompleted {
extension_name,
success: true,
message: result.message,
});
}
Err(e) => {
let msg = format!("Auth failed: {}", e);
+4 -5
View File
@@ -405,11 +405,10 @@ fn check_routines_config() -> CheckResult {
fn check_gateway_config(settings: &Settings) -> CheckResult {
// Use the same resolve() path as runtime so invalid env values
// (e.g. GATEWAY_PORT=abc) are caught here too.
let owner_id = match crate::config::resolve_owner_id(settings) {
Ok(owner_id) => owner_id,
Err(e) => return CheckResult::Fail(format!("config error: {e}")),
};
match crate::config::ChannelsConfig::resolve(settings, &owner_id) {
let tunnel_enabled = crate::config::TunnelConfig::resolve(settings)
.map(|t| t.is_enabled())
.unwrap_or(false);
match crate::config::ChannelsConfig::resolve(settings, tunnel_enabled) {
Ok(channels) => match channels.gateway {
Some(gw) => {
if gw.auth_token.is_some() {
+32 -32
View File
@@ -223,8 +223,8 @@ async fn cmd_follow(cmd: &LogsCommand, params: &GatewayParams) -> anyhow::Result
// Process complete lines from the buffer.
while let Some(newline_pos) = buffer.find('\n') {
let line = buffer[..newline_pos].to_string();
buffer = buffer[newline_pos + 1..].to_string();
let line = buffer[..newline_pos].to_string(); // safety: find('\n') returns char boundary
buffer = buffer[newline_pos + 1..].to_string(); // safety: '\n' is single byte
// SSE format: "data: {...}" lines carry the payload.
if let Some(data) = line.strip_prefix("data: ")
@@ -487,25 +487,25 @@ mod tests {
#[test]
fn test_colorize_level() {
assert!(colorize_level("ERROR").contains("\x1b[31m"));
assert!(colorize_level("WARN").contains("\x1b[33m"));
assert!(colorize_level("INFO").contains("\x1b[32m"));
assert!(colorize_level("DEBUG").contains("\x1b[36m"));
assert!(colorize_level("TRACE").contains("\x1b[90m"));
assert_eq!(colorize_level("UNKNOWN"), "UNKNOWN");
assert!(colorize_level("ERROR").contains("\x1b[31m")); // safety: test-only
assert!(colorize_level("WARN").contains("\x1b[33m")); // safety: test-only
assert!(colorize_level("INFO").contains("\x1b[32m")); // safety: test-only
assert!(colorize_level("DEBUG").contains("\x1b[36m")); // safety: test-only
assert!(colorize_level("TRACE").contains("\x1b[90m")); // safety: test-only
assert_eq!(colorize_level("UNKNOWN"), "UNKNOWN"); // safety: test-only
}
#[test]
fn test_convert_to_local_time_valid() {
let ts = "2024-01-15T10:30:00.000Z";
let result = convert_to_local_time(ts);
assert!(result.contains("2024-01-15"));
assert!(result.contains("2024-01-15")); // safety: test-only
}
#[test]
fn test_convert_to_local_time_invalid() {
let ts = "not-a-timestamp";
assert_eq!(convert_to_local_time(ts), "not-a-timestamp");
assert_eq!(convert_to_local_time(ts), "not-a-timestamp"); // safety: test-only
}
#[test]
@@ -533,55 +533,55 @@ mod tests {
#[test]
fn test_tail_file_small() {
let dir = tempfile::tempdir().unwrap();
let dir = tempfile::tempdir().unwrap(); // safety: test-only
let path = dir.path().join("test.log");
std::fs::write(&path, "line1\nline2\nline3\nline4\nline5\n").unwrap();
std::fs::write(&path, "line1\nline2\nline3\nline4\nline5\n").unwrap(); // safety: test-only
let result = tail_file(&path, 3).unwrap();
assert_eq!(result, vec!["line3", "line4", "line5"]);
let result = tail_file(&path, 3).unwrap(); // safety: test-only
assert_eq!(result, vec!["line3", "line4", "line5"]); // safety: test-only
}
#[test]
fn test_tail_file_fewer_lines_than_limit() {
let dir = tempfile::tempdir().unwrap();
let dir = tempfile::tempdir().unwrap(); // safety: test-only
let path = dir.path().join("test.log");
std::fs::write(&path, "a\nb\n").unwrap();
std::fs::write(&path, "a\nb\n").unwrap(); // safety: test-only
let result = tail_file(&path, 200).unwrap();
assert_eq!(result, vec!["a", "b"]);
let result = tail_file(&path, 200).unwrap(); // safety: test-only
assert_eq!(result, vec!["a", "b"]); // safety: test-only
}
#[test]
fn test_tail_file_empty() {
let dir = tempfile::tempdir().unwrap();
let dir = tempfile::tempdir().unwrap(); // safety: test-only
let path = dir.path().join("test.log");
std::fs::write(&path, "").unwrap();
std::fs::write(&path, "").unwrap(); // safety: test-only
let result = tail_file(&path, 10).unwrap();
assert!(result.is_empty());
let result = tail_file(&path, 10).unwrap(); // safety: test-only
assert!(result.is_empty()); // safety: test-only
}
#[test]
fn test_tail_file_large() {
let dir = tempfile::tempdir().unwrap();
let dir = tempfile::tempdir().unwrap(); // safety: test-only
let path = dir.path().join("big.log");
// Write 10000 lines to test chunked reading.
let content: String = (0..10000).map(|i| format!("line {}\n", i)).collect();
std::fs::write(&path, &content).unwrap();
std::fs::write(&path, &content).unwrap(); // safety: test-only
let result = tail_file(&path, 5).unwrap();
assert_eq!(result.len(), 5);
assert_eq!(result[0], "line 9995");
assert_eq!(result[4], "line 9999");
let result = tail_file(&path, 5).unwrap(); // safety: test-only
assert_eq!(result.len(), 5); // safety: test-only
assert_eq!(result[0], "line 9995"); // safety: test-only
assert_eq!(result[4], "line 9999"); // safety: test-only
}
#[test]
fn test_tail_file_no_trailing_newline() {
let dir = tempfile::tempdir().unwrap();
let dir = tempfile::tempdir().unwrap(); // safety: test-only
let path = dir.path().join("test.log");
std::fs::write(&path, "line1\nline2\nline3").unwrap();
std::fs::write(&path, "line1\nline2\nline3").unwrap(); // safety: test-only
let result = tail_file(&path, 2).unwrap();
assert_eq!(result, vec!["line2", "line3"]);
let result = tail_file(&path, 2).unwrap(); // safety: test-only
assert_eq!(result, vec!["line2", "line3"]); // safety: test-only
}
}
+7 -21
View File
@@ -292,16 +292,6 @@ async fn list(
// ── Create ──────────────────────────────────────────────────
fn cli_notify_config(notify_channel: Option<String>) -> NotifyConfig {
NotifyConfig {
channel: notify_channel,
user: None,
on_attention: true,
on_failure: true,
on_success: false,
}
}
#[allow(clippy::too_many_arguments)]
async fn create(
db: &Arc<dyn Database>,
@@ -348,7 +338,13 @@ async fn create(
max_concurrent: 1,
dedup_window: None,
},
notify: cli_notify_config(notify_channel),
notify: NotifyConfig {
channel: notify_channel,
user: user_id.to_string(),
on_attention: true,
on_failure: true,
on_success: false,
},
last_run_at: None,
next_fire_at: next_fire,
run_count: 0,
@@ -733,14 +729,4 @@ mod tests {
// Must be valid UTF-8 (would have panicked otherwise).
assert!(result.is_char_boundary(result.len()));
}
#[test]
fn cli_notify_config_defaults_to_runtime_target_resolution() {
let notify = cli_notify_config(Some("telegram".to_string()));
assert_eq!(notify.channel.as_deref(), Some("telegram")); // safety: test-only assertion
assert_eq!(notify.user, None); // safety: test-only assertion
assert!(notify.on_attention); // safety: test-only assertion
assert!(notify.on_failure); // safety: test-only assertion
assert!(!notify.on_success); // safety: test-only assertion
}
}
+6 -42
View File
@@ -32,16 +32,13 @@ impl Default for BuilderModeConfig {
}
impl BuilderModeConfig {
pub(crate) fn resolve(settings: &crate::settings::Settings) -> Result<Self, ConfigError> {
let bs = &settings.builder;
pub(crate) fn resolve() -> Result<Self, ConfigError> {
Ok(Self {
enabled: parse_bool_env("BUILDER_ENABLED", bs.enabled)?,
build_dir: optional_env("BUILDER_DIR")?
.map(PathBuf::from)
.or_else(|| bs.build_dir.clone()),
max_iterations: parse_optional_env("BUILDER_MAX_ITERATIONS", bs.max_iterations)?,
timeout_secs: parse_optional_env("BUILDER_TIMEOUT_SECS", bs.timeout_secs)?,
auto_register: parse_bool_env("BUILDER_AUTO_REGISTER", bs.auto_register)?,
enabled: parse_bool_env("BUILDER_ENABLED", true)?,
build_dir: optional_env("BUILDER_DIR")?.map(PathBuf::from),
max_iterations: parse_optional_env("BUILDER_MAX_ITERATIONS", 20)?,
timeout_secs: parse_optional_env("BUILDER_TIMEOUT_SECS", 600)?,
auto_register: parse_bool_env("BUILDER_AUTO_REGISTER", true)?,
})
}
@@ -59,36 +56,3 @@ impl BuilderModeConfig {
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::config::helpers::ENV_MUTEX;
use crate::settings::Settings;
#[test]
fn resolve_falls_back_to_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.builder.max_iterations = 99;
settings.builder.auto_register = false;
let cfg = BuilderModeConfig::resolve(&settings).expect("resolve");
assert_eq!(cfg.max_iterations, 99);
assert!(!cfg.auto_register);
}
#[test]
fn env_overrides_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.builder.timeout_secs = 123;
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe { std::env::set_var("BUILDER_TIMEOUT_SECS", "3") };
let cfg = BuilderModeConfig::resolve(&settings).expect("resolve");
unsafe { std::env::remove_var("BUILDER_TIMEOUT_SECS") };
assert_eq!(cfg.timeout_secs, 3);
}
}
+335 -55
View File
@@ -91,24 +91,36 @@ pub struct SignalConfig {
}
impl ChannelsConfig {
pub(crate) fn resolve(settings: &Settings, owner_id: &str) -> Result<Self, ConfigError> {
/// Resolve channels config following `env > settings > default` for every field.
pub(crate) fn resolve(settings: &Settings, tunnel_enabled: bool) -> Result<Self, ConfigError> {
let cs = &settings.channels;
// --- HTTP webhook ---
// HTTP is enabled when env vars are set OR settings has it enabled.
let http_enabled_by_env =
optional_env("HTTP_PORT")?.is_some() || optional_env("HTTP_HOST")?.is_some();
// When a tunnel is configured, default to loopback since external
// traffic arrives through the tunnel. Without a tunnel the webhook
// server needs to accept connections from the network directly.
let default_host = if tunnel_enabled {
"127.0.0.1"
} else {
"0.0.0.0"
};
let http = if http_enabled_by_env || cs.http_enabled {
Some(HttpConfig {
host: optional_env("HTTP_HOST")?
.or_else(|| cs.http_host.clone())
.unwrap_or_else(|| "0.0.0.0".to_string()),
.unwrap_or_else(|| default_host.to_string()),
port: parse_optional_env("HTTP_PORT", cs.http_port.unwrap_or(8080))?,
webhook_secret: optional_env("HTTP_WEBHOOK_SECRET")?.map(SecretString::from),
user_id: owner_id.to_string(),
user_id: optional_env("HTTP_USER_ID")?.unwrap_or_else(|| "http".to_string()),
})
} else {
None
};
// --- Web gateway ---
let gateway_enabled = parse_bool_env("GATEWAY_ENABLED", cs.gateway_enabled)?;
let gateway = if gateway_enabled {
Some(GatewayConfig {
@@ -121,29 +133,33 @@ impl ChannelsConfig {
)?,
auth_token: optional_env("GATEWAY_AUTH_TOKEN")?
.or_else(|| cs.gateway_auth_token.clone()),
user_id: owner_id.to_string(),
user_id: optional_env("GATEWAY_USER_ID")?
.or_else(|| cs.gateway_user_id.clone())
.unwrap_or_else(|| "default".to_string()),
})
} else {
None
};
// --- Signal ---
let signal_url = optional_env("SIGNAL_HTTP_URL")?.or_else(|| cs.signal_http_url.clone());
let signal = if let Some(http_url) = signal_url {
let account = optional_env("SIGNAL_ACCOUNT")?
.or_else(|| cs.signal_account.clone())
.ok_or(ConfigError::InvalidValue {
key: "SIGNAL_ACCOUNT".to_string(),
message: "SIGNAL_ACCOUNT is required when SIGNAL_HTTP_URL is set".to_string(),
message: "SIGNAL_ACCOUNT is required when Signal is enabled".to_string(),
})?;
let allow_from =
match optional_env("SIGNAL_ALLOW_FROM")?.or_else(|| cs.signal_allow_from.clone()) {
None => vec![account.clone()],
Some(s) => s
.split(',')
.map(|e| e.trim().to_string())
.filter(|s| !s.is_empty())
.collect(),
};
let allow_from_str =
optional_env("SIGNAL_ALLOW_FROM")?.or_else(|| cs.signal_allow_from.clone());
let allow_from = match allow_from_str {
None => vec![account.clone()],
Some(s) => s
.split(',')
.map(|e| e.trim().to_string())
.filter(|s| !s.is_empty())
.collect(),
};
let dm_policy = optional_env("SIGNAL_DM_POLICY")?
.or_else(|| cs.signal_dm_policy.clone())
.unwrap_or_else(|| "pairing".to_string());
@@ -185,8 +201,18 @@ impl ChannelsConfig {
None
};
// --- CLI ---
let cli_enabled = parse_bool_env("CLI_ENABLED", cs.cli_enabled)?;
// --- WASM channels ---
let wasm_channels_dir = optional_env("WASM_CHANNELS_DIR")?
.map(PathBuf::from)
.or_else(|| cs.wasm_channels_dir.clone())
.unwrap_or_else(default_channels_dir);
let wasm_channels_enabled =
parse_bool_env("WASM_CHANNELS_ENABLED", cs.wasm_channels_enabled)?;
Ok(Self {
cli: CliConfig {
enabled: cli_enabled,
@@ -194,14 +220,8 @@ impl ChannelsConfig {
http,
gateway,
signal,
wasm_channels_dir: optional_env("WASM_CHANNELS_DIR")?
.map(PathBuf::from)
.or_else(|| cs.wasm_channels_dir.clone())
.unwrap_or_else(default_channels_dir),
wasm_channels_enabled: parse_bool_env(
"WASM_CHANNELS_ENABLED",
cs.wasm_channels_enabled,
)?,
wasm_channels_dir,
wasm_channels_enabled,
wasm_channel_owner_ids: {
let mut ids = cs.wasm_channel_owner_ids.clone();
// Backwards compat: TELEGRAM_OWNER_ID env var
@@ -232,8 +252,6 @@ fn default_channels_dir() -> PathBuf {
#[cfg(test)]
mod tests {
use crate::config::channels::*;
use crate::config::helpers::ENV_MUTEX;
use crate::settings::Settings;
#[test]
fn cli_config_fields() {
@@ -380,6 +398,69 @@ mod tests {
assert!(!cfg.wasm_channels_enabled);
}
/// When a tunnel is active and HTTP_HOST is not explicitly set, the
/// webhook server should default to loopback to avoid unnecessary exposure.
#[test]
fn http_host_defaults_to_loopback_with_tunnel() {
// Set HTTP_PORT to trigger HttpConfig creation, but leave HTTP_HOST unset
// so the default kicks in.
unsafe {
std::env::set_var("HTTP_PORT", "9999");
std::env::remove_var("HTTP_HOST");
}
let settings = crate::settings::Settings::default();
let cfg = ChannelsConfig::resolve(&settings, true).unwrap();
unsafe {
std::env::remove_var("HTTP_PORT");
}
let http = cfg.http.expect("HttpConfig should be present");
assert_eq!(
http.host, "127.0.0.1",
"tunnel active should default to loopback"
);
assert_eq!(http.port, 9999);
}
/// Without a tunnel, the webhook server defaults to 0.0.0.0 so external
/// services can reach it directly.
#[test]
fn http_host_defaults_to_all_interfaces_without_tunnel() {
unsafe {
std::env::set_var("HTTP_PORT", "9998");
std::env::remove_var("HTTP_HOST");
}
let settings = crate::settings::Settings::default();
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
unsafe {
std::env::remove_var("HTTP_PORT");
}
let http = cfg.http.expect("HttpConfig should be present");
assert_eq!(
http.host, "0.0.0.0",
"no tunnel should default to all interfaces"
);
}
/// An explicit HTTP_HOST always wins regardless of tunnel state.
#[test]
fn explicit_http_host_overrides_tunnel_default() {
unsafe {
std::env::set_var("HTTP_PORT", "9997");
std::env::set_var("HTTP_HOST", "192.168.1.50");
}
let settings = crate::settings::Settings::default();
let cfg = ChannelsConfig::resolve(&settings, true).unwrap();
unsafe {
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
}
let http = cfg.http.expect("HttpConfig should be present");
assert_eq!(
http.host, "192.168.1.50",
"explicit host should override tunnel default"
);
}
#[test]
fn default_channels_dir_ends_with_channels() {
let dir = default_channels_dir();
@@ -390,43 +471,242 @@ mod tests {
}
#[test]
fn resolve_uses_settings_channel_values_with_owner_scope_user_ids() {
let _guard = ENV_MUTEX.lock().unwrap_or_else(|e| e.into_inner());
let mut settings = Settings::default();
settings.channels.http_enabled = true;
settings.channels.http_host = Some("127.0.0.2".to_string());
settings.channels.http_port = Some(8181);
settings.channels.gateway_enabled = true;
settings.channels.gateway_host = Some("127.0.0.3".to_string());
settings.channels.gateway_port = Some(9191);
settings.channels.gateway_auth_token = Some("tok".to_string());
settings.channels.signal_http_url = Some("http://127.0.0.1:8080".to_string());
settings.channels.signal_account = Some("+15551234567".to_string());
settings.channels.signal_allow_from = Some("+15551234567,+15557654321".to_string());
settings.channels.wasm_channels_dir = Some(PathBuf::from("/tmp/settings-channels"));
settings.channels.wasm_channels_enabled = false;
fn default_gateway_port_constant() {
assert_eq!(DEFAULT_GATEWAY_PORT, 3000);
}
let cfg = ChannelsConfig::resolve(&settings, "owner-scope").expect("resolve");
/// With default settings and no env vars, gateway should use defaults.
#[test]
fn resolve_gateway_defaults_from_settings() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
// Clear env vars that would interfere
unsafe {
std::env::remove_var("GATEWAY_ENABLED");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let http = cfg.http.expect("http config");
assert_eq!(http.host, "127.0.0.2");
assert_eq!(http.port, 8181);
assert_eq!(http.user_id, "owner-scope");
let settings = crate::settings::Settings::default();
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
let gateway = cfg.gateway.expect("gateway config");
assert_eq!(gateway.host, "127.0.0.3");
assert_eq!(gateway.port, 9191);
assert_eq!(gateway.auth_token.as_deref(), Some("tok"));
assert_eq!(gateway.user_id, "owner-scope");
let gw = cfg.gateway.expect("gateway should be enabled by default");
assert_eq!(gw.host, "127.0.0.1");
assert_eq!(gw.port, DEFAULT_GATEWAY_PORT);
assert!(gw.auth_token.is_none());
assert_eq!(gw.user_id, "default");
}
let signal = cfg.signal.expect("signal config");
assert_eq!(signal.account, "+15551234567");
assert_eq!(signal.allow_from, vec!["+15551234567", "+15557654321"]);
/// Settings values should be used when no env vars are set.
#[test]
fn resolve_gateway_from_settings() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
unsafe {
std::env::remove_var("GATEWAY_ENABLED");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let mut settings = crate::settings::Settings::default();
settings.channels.gateway_port = Some(4000);
settings.channels.gateway_host = Some("0.0.0.0".to_string());
settings.channels.gateway_auth_token = Some("db-token-123".to_string());
settings.channels.gateway_user_id = Some("myuser".to_string());
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
let gw = cfg.gateway.expect("gateway should be enabled");
assert_eq!(gw.port, 4000);
assert_eq!(gw.host, "0.0.0.0");
assert_eq!(gw.auth_token.as_deref(), Some("db-token-123"));
assert_eq!(gw.user_id, "myuser");
}
/// Env vars should override settings values.
#[test]
fn resolve_env_overrides_settings() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
unsafe {
std::env::set_var("GATEWAY_PORT", "5000");
std::env::set_var("GATEWAY_HOST", "10.0.0.1");
std::env::set_var("GATEWAY_AUTH_TOKEN", "env-token");
std::env::remove_var("GATEWAY_ENABLED");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let mut settings = crate::settings::Settings::default();
settings.channels.gateway_port = Some(4000);
settings.channels.gateway_host = Some("0.0.0.0".to_string());
settings.channels.gateway_auth_token = Some("db-token".to_string());
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
let gw = cfg.gateway.expect("gateway should be enabled");
assert_eq!(gw.port, 5000, "env should override settings");
assert_eq!(gw.host, "10.0.0.1", "env should override settings");
assert_eq!(
cfg.wasm_channels_dir,
PathBuf::from("/tmp/settings-channels")
gw.auth_token.as_deref(),
Some("env-token"),
"env should override settings"
);
assert!(!cfg.wasm_channels_enabled);
// Cleanup
unsafe {
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
}
}
/// CLI enabled should fall back to settings.
#[test]
fn resolve_cli_enabled_from_settings() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
unsafe {
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("GATEWAY_ENABLED");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let mut settings = crate::settings::Settings::default();
settings.channels.cli_enabled = false;
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
assert!(!cfg.cli.enabled, "settings should disable CLI");
}
/// HTTP channel should activate when settings has it enabled.
#[test]
fn resolve_http_from_settings() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
unsafe {
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("HTTP_WEBHOOK_SECRET");
std::env::remove_var("HTTP_USER_ID");
std::env::remove_var("GATEWAY_ENABLED");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let mut settings = crate::settings::Settings::default();
settings.channels.http_enabled = true;
settings.channels.http_port = Some(9090);
settings.channels.http_host = Some("10.0.0.1".to_string());
let cfg = ChannelsConfig::resolve(&settings, false).unwrap();
let http = cfg.http.expect("HTTP should be enabled from settings");
assert_eq!(http.port, 9090);
assert_eq!(http.host, "10.0.0.1");
}
/// Settings round-trip through DB map for new gateway fields.
#[test]
fn settings_gateway_fields_db_roundtrip() {
let mut settings = crate::settings::Settings::default();
settings.channels.gateway_port = Some(4000);
settings.channels.gateway_host = Some("0.0.0.0".to_string());
settings.channels.gateway_auth_token = Some("tok-abc".to_string());
settings.channels.gateway_user_id = Some("myuser".to_string());
settings.channels.cli_enabled = false;
let map = settings.to_db_map();
let restored = crate::settings::Settings::from_db_map(&map);
assert_eq!(restored.channels.gateway_port, Some(4000));
assert_eq!(restored.channels.gateway_host.as_deref(), Some("0.0.0.0"));
assert_eq!(
restored.channels.gateway_auth_token.as_deref(),
Some("tok-abc")
);
assert_eq!(restored.channels.gateway_user_id.as_deref(), Some("myuser"));
assert!(!restored.channels.cli_enabled);
}
/// Invalid boolean env values must produce errors, not silently degrade.
#[test]
fn resolve_rejects_invalid_bool_env() {
let _lock = crate::config::helpers::ENV_MUTEX.lock();
let settings = crate::settings::Settings::default();
// GATEWAY_ENABLED=maybe should error
unsafe {
std::env::set_var("GATEWAY_ENABLED", "maybe");
std::env::remove_var("HTTP_PORT");
std::env::remove_var("HTTP_HOST");
std::env::remove_var("SIGNAL_HTTP_URL");
std::env::remove_var("CLI_ENABLED");
std::env::remove_var("WASM_CHANNELS_ENABLED");
std::env::remove_var("GATEWAY_PORT");
std::env::remove_var("GATEWAY_HOST");
std::env::remove_var("GATEWAY_AUTH_TOKEN");
std::env::remove_var("GATEWAY_USER_ID");
std::env::remove_var("WASM_CHANNELS_DIR");
std::env::remove_var("TELEGRAM_OWNER_ID");
}
let result = ChannelsConfig::resolve(&settings, false);
assert!(result.is_err(), "GATEWAY_ENABLED=maybe should be rejected");
// CLI_ENABLED=on should error
unsafe {
std::env::remove_var("GATEWAY_ENABLED");
std::env::set_var("CLI_ENABLED", "on");
}
let result = ChannelsConfig::resolve(&settings, false);
assert!(result.is_err(), "CLI_ENABLED=on should be rejected");
// WASM_CHANNELS_ENABLED=yes should error
unsafe {
std::env::remove_var("CLI_ENABLED");
std::env::set_var("WASM_CHANNELS_ENABLED", "yes");
}
let result = ChannelsConfig::resolve(&settings, false);
assert!(
result.is_err(),
"WASM_CHANNELS_ENABLED=yes should be rejected"
);
// Cleanup
unsafe {
std::env::remove_var("WASM_CHANNELS_ENABLED");
}
}
}
+2 -19
View File
@@ -7,19 +7,17 @@ use crate::settings::Settings;
pub struct HeartbeatConfig {
/// Whether heartbeat is enabled.
pub enabled: bool,
/// Interval between heartbeat checks in seconds (used when fire_at is not set).
/// Interval between heartbeat checks in seconds.
pub interval_secs: u64,
/// Channel to notify on heartbeat findings.
pub notify_channel: Option<String>,
/// User ID to notify on heartbeat findings.
pub notify_user: Option<String>,
/// Fixed time-of-day to fire (HH:MM, 24h). When set, interval_secs is ignored.
pub fire_at: Option<chrono::NaiveTime>,
/// Hour (0-23) when quiet hours start.
pub quiet_hours_start: Option<u32>,
/// Hour (0-23) when quiet hours end.
pub quiet_hours_end: Option<u32>,
/// Timezone for fire_at and quiet hours evaluation (IANA name).
/// Timezone for quiet hours evaluation (IANA name).
pub timezone: Option<String>,
}
@@ -30,7 +28,6 @@ impl Default for HeartbeatConfig {
interval_secs: 1800, // 30 minutes
notify_channel: None,
notify_user: None,
fire_at: None,
quiet_hours_start: None,
quiet_hours_end: None,
timezone: None,
@@ -40,19 +37,6 @@ impl Default for HeartbeatConfig {
impl HeartbeatConfig {
pub(crate) fn resolve(settings: &Settings) -> Result<Self, ConfigError> {
let fire_at_str =
optional_env("HEARTBEAT_FIRE_AT")?.or_else(|| settings.heartbeat.fire_at.clone());
let fire_at = fire_at_str
.map(|s| {
chrono::NaiveTime::parse_from_str(&s, "%H:%M").map_err(|e| {
ConfigError::InvalidValue {
key: "HEARTBEAT_FIRE_AT".to_string(),
message: format!("must be HH:MM (24h), e.g. '14:00': {e}"),
}
})
})
.transpose()?;
Ok(Self {
enabled: parse_bool_env("HEARTBEAT_ENABLED", settings.heartbeat.enabled)?,
interval_secs: parse_optional_env(
@@ -63,7 +47,6 @@ impl HeartbeatConfig {
.or_else(|| settings.heartbeat.notify_channel.clone()),
notify_user: optional_env("HEARTBEAT_NOTIFY_USER")?
.or_else(|| settings.heartbeat.notify_user.clone()),
fire_at,
quiet_hours_start: parse_option_env::<u32>("HEARTBEAT_QUIET_START")?
.or(settings.heartbeat.quiet_hours_start)
.map(|h| {
+19 -61
View File
@@ -9,6 +9,7 @@ use crate::llm::config::*;
use crate::llm::registry::{ProviderProtocol, ProviderRegistry};
use crate::llm::session::SessionConfig;
use crate::settings::Settings;
impl LlmConfig {
/// Create a test-friendly config without reading env vars.
#[cfg(feature = "libsql")]
@@ -38,8 +39,6 @@ impl LlmConfig {
provider: None,
bedrock: None,
request_timeout_secs: 120,
cheap_model: None,
smart_routing_cascade: false,
}
}
@@ -170,14 +169,6 @@ impl LlmConfig {
let request_timeout_secs = parse_optional_env("LLM_REQUEST_TIMEOUT_SECS", 120)?;
// Generic cheap model (works with any backend).
// Falls back to NearAI-specific cheap_model in provider chain logic.
let cheap_model = optional_env("LLM_CHEAP_MODEL")?;
// Generic smart routing cascade flag.
// Defaults to true. Overrides NearAI-specific smart_routing_cascade.
let smart_routing_cascade = parse_optional_env("SMART_ROUTING_CASCADE", true)?;
Ok(Self {
backend: if is_nearai {
"nearai".to_string()
@@ -193,8 +184,6 @@ impl LlmConfig {
provider,
bedrock,
request_timeout_secs,
cheap_model,
smart_routing_cascade,
})
}
@@ -252,30 +241,8 @@ impl LlmConfig {
)
};
// Codex auth.json override: when LLM_USE_CODEX_AUTH=true,
// credentials from the Codex CLI's auth.json take highest priority
// (over env vars AND secrets store). In ChatGPT mode, the base URL
// is also overridden to the private ChatGPT backend endpoint.
let mut codex_base_url_override: Option<String> = None;
let codex_creds = if parse_optional_env("LLM_USE_CODEX_AUTH", false)? {
let path = optional_env("CODEX_AUTH_PATH")?
.map(std::path::PathBuf::from)
.unwrap_or_else(crate::llm::codex_auth::default_codex_auth_path);
crate::llm::codex_auth::load_codex_credentials(&path)
} else {
None
};
let codex_refresh_token = codex_creds.as_ref().and_then(|c| c.refresh_token.clone());
let codex_auth_path = codex_creds.as_ref().and_then(|c| c.auth_path.clone());
let api_key = if let Some(creds) = codex_creds {
if creds.is_chatgpt_mode {
codex_base_url_override = Some(creds.base_url().to_string());
}
Some(creds.token)
} else if let Some(env_var) = api_key_env {
// Resolve API key from env (including secrets store overlay)
// Resolve API key from env
let api_key = if let Some(env_var) = api_key_env {
optional_env(env_var)?.map(SecretString::from)
} else {
None
@@ -292,28 +259,22 @@ impl LlmConfig {
}
}
// Resolve base URL: codex override > env var > settings (backward compat) > registry default
let is_codex_chatgpt = codex_base_url_override.is_some();
let base_url = codex_base_url_override
.or_else(|| {
if let Some(env_var) = base_url_env {
optional_env(env_var).ok().flatten()
} else {
None
}
})
.or_else(|| {
// Backward compat: check legacy settings fields
match backend {
"ollama" => settings.ollama_base_url.clone(),
"openai_compatible" | "openrouter" => {
settings.openai_compatible_base_url.clone()
}
_ => None,
}
})
.or_else(|| default_base_url.map(String::from))
.unwrap_or_default();
// Resolve base URL: env var > settings (backward compat) > registry default
let base_url = if let Some(env_var) = base_url_env {
optional_env(env_var)?
} else {
None
}
.or_else(|| {
// Backward compat: check legacy settings fields
match backend {
"ollama" => settings.ollama_base_url.clone(),
"openai_compatible" | "openrouter" => settings.openai_compatible_base_url.clone(),
_ => None,
}
})
.or_else(|| default_base_url.map(String::from))
.unwrap_or_default();
if base_url_required
&& base_url.is_empty()
@@ -379,9 +340,6 @@ impl LlmConfig {
model,
extra_headers,
oauth_token,
is_codex_chatgpt,
refresh_token: codex_refresh_token,
auth_path: codex_auth_path,
cache_retention,
unsupported_params,
})
+57 -44
View File
@@ -26,7 +26,7 @@ mod tunnel;
mod wasm;
use std::collections::HashMap;
use std::sync::{LazyLock, Mutex, Once};
use std::sync::{LazyLock, Mutex};
use crate::error::ConfigError;
use crate::settings::Settings;
@@ -74,12 +74,10 @@ pub use self::helpers::{env_or_override, set_runtime_env};
/// their data. Whichever runs first initialises the map; the second merges in.
static INJECTED_VARS: LazyLock<Mutex<HashMap<String, String>>> =
LazyLock::new(|| Mutex::new(HashMap::new()));
static WARNED_EXPLICIT_DEFAULT_OWNER_ID: Once = Once::new();
/// Main configuration for the agent.
#[derive(Debug, Clone)]
pub struct Config {
pub owner_id: String,
pub database: DatabaseConfig,
pub llm: LlmConfig,
pub embeddings: EmbeddingsConfig,
@@ -120,7 +118,6 @@ impl Config {
installed_skills_dir: std::path::PathBuf,
) -> Self {
Self {
owner_id: "default".to_string(),
database: DatabaseConfig {
backend: DatabaseBackend::LibSql,
url: secrecy::SecretString::from("unused://test".to_string()),
@@ -231,7 +228,13 @@ impl Config {
pub async fn from_env_with_toml(
toml_path: Option<&std::path::Path>,
) -> Result<Self, ConfigError> {
let settings = load_bootstrap_settings(toml_path)?;
let _ = dotenvy::dotenv();
crate::bootstrap::load_ironclaw_env();
let mut settings = Settings::load();
// Overlay TOML config file (values win over JSON settings)
Self::apply_toml_overlay(&mut settings, toml_path)?;
Self::build(&settings).await
}
@@ -303,25 +306,26 @@ impl Config {
/// Build config from settings (shared by from_env and from_db).
async fn build(settings: &Settings) -> Result<Self, ConfigError> {
let owner_id = resolve_owner_id(settings)?;
// Resolve tunnel first so channels can default to loopback when a
// tunnel handles external exposure (no need to bind 0.0.0.0).
let tunnel = TunnelConfig::resolve(settings)?;
Ok(Self {
owner_id: owner_id.clone(),
database: DatabaseConfig::resolve()?,
llm: LlmConfig::resolve(settings)?,
embeddings: EmbeddingsConfig::resolve(settings)?,
tunnel: TunnelConfig::resolve(settings)?,
channels: ChannelsConfig::resolve(settings, &owner_id)?,
channels: ChannelsConfig::resolve(settings, tunnel.is_enabled())?,
tunnel,
agent: AgentConfig::resolve(settings)?,
safety: resolve_safety_config(settings)?,
wasm: WasmConfig::resolve(settings)?,
safety: resolve_safety_config()?,
wasm: WasmConfig::resolve()?,
secrets: SecretsConfig::resolve().await?,
builder: BuilderModeConfig::resolve(settings)?,
builder: BuilderModeConfig::resolve()?,
heartbeat: HeartbeatConfig::resolve(settings)?,
hygiene: HygieneConfig::resolve()?,
routines: RoutineConfig::resolve()?,
sandbox: SandboxModeConfig::resolve(settings)?,
claude_code: ClaudeCodeConfig::resolve(settings)?,
sandbox: SandboxModeConfig::resolve()?,
claude_code: ClaudeCodeConfig::resolve()?,
skills: SkillsConfig::resolve()?,
transcription: TranscriptionConfig::resolve(settings)?,
search: WorkspaceSearchConfig::resolve()?,
@@ -331,43 +335,52 @@ impl Config {
relay: RelayConfig::from_env(),
})
}
}
pub(crate) fn load_bootstrap_settings(
toml_path: Option<&std::path::Path>,
) -> Result<Settings, ConfigError> {
let _ = dotenvy::dotenv();
crate::bootstrap::load_ironclaw_env();
/// Validate cross-field invariants.
///
/// Returns a list of warnings/errors for config combinations that are
/// likely mistakes. Called during startup for early feedback.
pub fn validate(&self) -> Vec<String> {
let mut issues = Vec::new();
let mut settings = Settings::load();
Config::apply_toml_overlay(&mut settings, toml_path)?;
Ok(settings)
}
// Heartbeat enabled but no workspace path hints
if self.heartbeat.enabled && self.database.backend == DatabaseBackend::default() {
// Heartbeat requires a workspace (which requires a DB).
// This is a soft warning — the system will still start.
}
pub(crate) fn resolve_owner_id(settings: &Settings) -> Result<String, ConfigError> {
let env_owner_id = self::helpers::optional_env("IRONCLAW_OWNER_ID")?;
let settings_owner_id = settings.owner_id.clone();
let configured_owner_id = env_owner_id.clone().or(settings_owner_id.clone());
// Sandbox enabled but Docker might not be available
if self.sandbox.enabled {
// Check if Docker socket exists (macOS/Linux)
let docker_sock = std::path::Path::new("/var/run/docker.sock");
if !docker_sock.exists() {
issues.push(
"Sandbox is enabled but /var/run/docker.sock not found. \
Docker may not be running."
.to_string(),
);
}
}
let owner_id = configured_owner_id
.map(|value| value.trim().to_string())
.filter(|value| !value.is_empty())
.unwrap_or_else(|| "default".to_string());
// WASM enabled but tools directory missing
if self.wasm.enabled && !self.wasm.tools_dir.exists() {
issues.push(format!(
"WASM is enabled but tools directory '{}' does not exist",
self.wasm.tools_dir.display()
));
}
if owner_id == "default"
&& (env_owner_id.is_some()
|| settings_owner_id
.as_deref()
.is_some_and(|value| !value.trim().is_empty()))
{
WARNED_EXPLICIT_DEFAULT_OWNER_ID.call_once(|| {
tracing::warn!(
"IRONCLAW_OWNER_ID resolved to the legacy 'default' scope explicitly; durable state will keep legacy owner behavior"
// Skills enabled but local dir missing
if self.skills.enabled && !self.skills.local_dir.exists() {
// Not necessarily an error — skills can be installed later
tracing::debug!(
"Skills enabled but local_dir '{}' does not exist yet",
self.skills.local_dir.display()
);
});
}
}
Ok(owner_id)
issues
}
}
/// Load API keys from the encrypted secrets store into a thread-safe overlay.
+3 -42
View File
@@ -3,48 +3,9 @@ use crate::error::ConfigError;
pub use ironclaw_safety::SafetyConfig;
pub(crate) fn resolve_safety_config(
settings: &crate::settings::Settings,
) -> Result<SafetyConfig, ConfigError> {
let ss = &settings.safety;
pub(crate) fn resolve_safety_config() -> Result<SafetyConfig, ConfigError> {
Ok(SafetyConfig {
max_output_length: parse_optional_env("SAFETY_MAX_OUTPUT_LENGTH", ss.max_output_length)?,
injection_check_enabled: parse_bool_env(
"SAFETY_INJECTION_CHECK_ENABLED",
ss.injection_check_enabled,
)?,
max_output_length: parse_optional_env("SAFETY_MAX_OUTPUT_LENGTH", 100_000)?,
injection_check_enabled: parse_bool_env("SAFETY_INJECTION_CHECK_ENABLED", true)?,
})
}
#[cfg(test)]
mod tests {
use super::*;
use crate::config::helpers::ENV_MUTEX;
use crate::settings::Settings;
#[test]
fn resolve_falls_back_to_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.safety.max_output_length = 42;
settings.safety.injection_check_enabled = false;
let cfg = resolve_safety_config(&settings).expect("resolve");
assert_eq!(cfg.max_output_length, 42);
assert!(!cfg.injection_check_enabled);
}
#[test]
fn env_overrides_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.safety.max_output_length = 42;
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe { std::env::set_var("SAFETY_MAX_OUTPUT_LENGTH", "7") };
let cfg = resolve_safety_config(&settings).expect("resolve");
unsafe { std::env::remove_var("SAFETY_MAX_OUTPUT_LENGTH") };
assert_eq!(cfg.max_output_length, 7);
}
}
+11 -121
View File
@@ -52,20 +52,11 @@ impl Default for SandboxModeConfig {
}
impl SandboxModeConfig {
pub(crate) fn resolve(settings: &crate::settings::Settings) -> Result<Self, ConfigError> {
let ss = &settings.sandbox;
pub(crate) fn resolve() -> Result<Self, ConfigError> {
let extra_domains = optional_env("SANDBOX_EXTRA_DOMAINS")?
.map(|s| s.split(',').map(|d| d.trim().to_string()).collect())
.unwrap_or_else(|| {
if ss.extra_allowed_domains.is_empty() {
Vec::new()
} else {
ss.extra_allowed_domains.clone()
}
});
.unwrap_or_default();
// reaper/orphan fields have no Settings counterpart — env > default only.
let reaper_interval_secs: u64 = parse_optional_env("SANDBOX_REAPER_INTERVAL_SECS", 300)?;
let orphan_threshold_secs: u64 = parse_optional_env("SANDBOX_ORPHAN_THRESHOLD_SECS", 600)?;
@@ -85,15 +76,14 @@ impl SandboxModeConfig {
}
Ok(Self {
enabled: parse_bool_env("SANDBOX_ENABLED", ss.enabled)?,
policy: parse_string_env("SANDBOX_POLICY", ss.policy.clone())?,
// allow_full_access has no Settings counterpart — env > default only.
enabled: parse_bool_env("SANDBOX_ENABLED", true)?,
policy: parse_string_env("SANDBOX_POLICY", "readonly")?,
allow_full_access: parse_bool_env("SANDBOX_ALLOW_FULL_ACCESS", false)?,
timeout_secs: parse_optional_env("SANDBOX_TIMEOUT_SECS", ss.timeout_secs)?,
memory_limit_mb: parse_optional_env("SANDBOX_MEMORY_LIMIT_MB", ss.memory_limit_mb)?,
cpu_shares: parse_optional_env("SANDBOX_CPU_SHARES", ss.cpu_shares)?,
image: parse_string_env("SANDBOX_IMAGE", ss.image.clone())?,
auto_pull_image: parse_bool_env("SANDBOX_AUTO_PULL", ss.auto_pull_image)?,
timeout_secs: parse_optional_env("SANDBOX_TIMEOUT_SECS", 120)?,
memory_limit_mb: parse_optional_env("SANDBOX_MEMORY_LIMIT_MB", 2048)?,
cpu_shares: parse_optional_env("SANDBOX_CPU_SHARES", 1024)?,
image: parse_string_env("SANDBOX_IMAGE", "ironclaw-worker:latest")?,
auto_pull_image: parse_bool_env("SANDBOX_AUTO_PULL", true)?,
extra_allowed_domains: extra_domains,
reaper_interval_secs,
orphan_threshold_secs,
@@ -210,7 +200,7 @@ impl ClaudeCodeConfig {
/// Load from environment variables only (used inside containers where
/// there is no database or full config).
pub fn from_env() -> Self {
match Self::resolve_env_only() {
match Self::resolve() {
Ok(c) => c,
Err(e) => {
tracing::warn!("Failed to resolve ClaudeCodeConfig: {e}, using defaults");
@@ -263,33 +253,7 @@ impl ClaudeCodeConfig {
None
}
pub(crate) fn resolve(settings: &crate::settings::Settings) -> Result<Self, ConfigError> {
let defaults = Self::default();
Ok(Self {
// Use settings.sandbox.claude_code_enabled as fallback (written by setup wizard).
enabled: parse_bool_env("CLAUDE_CODE_ENABLED", settings.sandbox.claude_code_enabled)?,
config_dir: optional_env("CLAUDE_CONFIG_DIR")?
.map(std::path::PathBuf::from)
.unwrap_or(defaults.config_dir),
model: parse_string_env("CLAUDE_CODE_MODEL", defaults.model)?,
max_turns: parse_optional_env("CLAUDE_CODE_MAX_TURNS", defaults.max_turns)?,
memory_limit_mb: parse_optional_env(
"CLAUDE_CODE_MEMORY_LIMIT_MB",
defaults.memory_limit_mb,
)?,
allowed_tools: optional_env("CLAUDE_CODE_ALLOWED_TOOLS")?
.map(|s| {
s.split(',')
.map(|t| t.trim().to_string())
.filter(|t| !t.is_empty())
.collect()
})
.unwrap_or(defaults.allowed_tools),
})
}
/// Resolve from env vars only, no Settings. Used inside containers.
fn resolve_env_only() -> Result<Self, ConfigError> {
pub(crate) fn resolve() -> Result<Self, ConfigError> {
let defaults = Self::default();
Ok(Self {
enabled: parse_bool_env("CLAUDE_CODE_ENABLED", defaults.enabled)?,
@@ -590,80 +554,6 @@ mod tests {
);
}
// ── Settings fallback tests ──────────────────────────────────────
#[test]
fn sandbox_resolve_falls_back_to_settings() {
let _guard = crate::config::helpers::ENV_MUTEX
.lock()
.expect("env mutex poisoned");
let mut settings = crate::settings::Settings::default();
settings.sandbox.cpu_shares = 99;
settings.sandbox.auto_pull_image = false;
settings.sandbox.enabled = false;
let cfg = SandboxModeConfig::resolve(&settings).expect("resolve");
assert!(!cfg.enabled);
assert_eq!(cfg.cpu_shares, 99);
assert!(!cfg.auto_pull_image);
}
#[test]
fn sandbox_env_overrides_settings() {
let _guard = crate::config::helpers::ENV_MUTEX
.lock()
.expect("env mutex poisoned");
let mut settings = crate::settings::Settings::default();
settings.sandbox.timeout_secs = 999;
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe { std::env::set_var("SANDBOX_TIMEOUT_SECS", "5") };
let cfg = SandboxModeConfig::resolve(&settings).expect("resolve");
unsafe { std::env::remove_var("SANDBOX_TIMEOUT_SECS") };
assert_eq!(cfg.timeout_secs, 5);
}
// ── ClaudeCodeConfig settings fallback tests ────────────────────
#[test]
fn claude_code_resolve_uses_settings_enabled() {
let _guard = crate::config::helpers::ENV_MUTEX
.lock()
.expect("env mutex poisoned");
let mut settings = crate::settings::Settings::default();
settings.sandbox.claude_code_enabled = true;
let cfg = ClaudeCodeConfig::resolve(&settings).expect("resolve");
assert!(cfg.enabled);
}
#[test]
fn claude_code_resolve_defaults_disabled() {
let _guard = crate::config::helpers::ENV_MUTEX
.lock()
.expect("env mutex poisoned");
let settings = crate::settings::Settings::default();
let cfg = ClaudeCodeConfig::resolve(&settings).expect("resolve");
assert!(!cfg.enabled);
}
#[test]
fn claude_code_env_overrides_settings() {
let _guard = crate::config::helpers::ENV_MUTEX
.lock()
.expect("env mutex poisoned");
let mut settings = crate::settings::Settings::default();
settings.sandbox.claude_code_enabled = true;
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe { std::env::set_var("CLAUDE_CODE_ENABLED", "false") };
let cfg = ClaudeCodeConfig::resolve(&settings).expect("resolve");
unsafe { std::env::remove_var("CLAUDE_CODE_ENABLED") };
assert!(!cfg.enabled);
}
#[test]
fn test_readonly_policy_unaffected() {
let config = SandboxModeConfig {
+13 -64
View File
@@ -9,15 +9,11 @@ use crate::settings::Settings;
pub struct TranscriptionConfig {
/// Whether audio transcription is enabled.
pub enabled: bool,
/// Provider: "openai" (default) or "chat_completions".
/// Provider: "openai" (default).
pub provider: String,
/// OpenAI API key (reuses OPENAI_API_KEY).
pub openai_api_key: Option<SecretString>,
/// Explicit transcription API key (overrides provider-specific keys).
pub api_key: Option<SecretString>,
/// LLM API key (reuses LLM_API_KEY, used as fallback for chat_completions).
pub llm_api_key: Option<SecretString>,
/// Model to use (default depends on provider).
/// Model to use (default: "whisper-1").
pub model: String,
/// Base URL override for the transcription API.
pub base_url: Option<String>,
@@ -29,8 +25,6 @@ impl Default for TranscriptionConfig {
enabled: false,
provider: "openai".to_string(),
openai_api_key: None,
api_key: None,
llm_api_key: None,
model: "whisper-1".to_string(),
base_url: None,
}
@@ -48,15 +42,8 @@ impl TranscriptionConfig {
optional_env("TRANSCRIPTION_PROVIDER")?.unwrap_or_else(|| "openai".to_string());
let openai_api_key = optional_env("OPENAI_API_KEY")?.map(SecretString::from);
let api_key = optional_env("TRANSCRIPTION_API_KEY")?.map(SecretString::from);
let llm_api_key = optional_env("LLM_API_KEY")?.map(SecretString::from);
let default_model = match provider.as_str() {
"chat_completions" => "google/gemini-2.0-flash-001",
_ => "whisper-1",
};
let model =
optional_env("TRANSCRIPTION_MODEL")?.unwrap_or_else(|| default_model.to_string());
let model = optional_env("TRANSCRIPTION_MODEL")?.unwrap_or_else(|| "whisper-1".to_string());
let base_url = optional_env("TRANSCRIPTION_BASE_URL")?;
@@ -64,67 +51,29 @@ impl TranscriptionConfig {
enabled,
provider,
openai_api_key,
api_key,
llm_api_key,
model,
base_url,
})
}
/// Resolve the API key for the configured provider.
///
/// Priority: `TRANSCRIPTION_API_KEY` > provider-specific key.
fn resolve_api_key(&self) -> Option<&SecretString> {
self.api_key
.as_ref()
.or_else(|| match self.provider.as_str() {
"chat_completions" => self.llm_api_key.as_ref().or(self.openai_api_key.as_ref()),
_ => self.openai_api_key.as_ref(),
})
}
/// Create the transcription provider if enabled and configured.
pub fn create_provider(&self) -> Option<Box<dyn crate::transcription::TranscriptionProvider>> {
if !self.enabled {
return None;
}
let api_key = self.resolve_api_key()?;
// Currently only OpenAI Whisper is supported; more providers can be
// added here with a match on self.provider.
let api_key = self.openai_api_key.as_ref()?;
tracing::info!(model = %self.model, "Audio transcription enabled via OpenAI Whisper");
match self.provider.as_str() {
"chat_completions" => {
tracing::info!(
model = %self.model,
"Audio transcription enabled via Chat Completions API"
);
let mut provider = crate::transcription::OpenAiWhisperProvider::new(api_key.clone())
.with_model(&self.model);
let mut provider = crate::transcription::ChatCompletionsTranscriptionProvider::new(
api_key.clone(),
)
.with_model(&self.model);
if let Some(ref base_url) = self.base_url {
provider = provider.with_base_url(base_url);
}
Some(Box::new(provider))
}
_ => {
tracing::info!(
model = %self.model,
"Audio transcription enabled via OpenAI Whisper"
);
let mut provider =
crate::transcription::OpenAiWhisperProvider::new(api_key.clone())
.with_model(&self.model);
if let Some(ref base_url) = self.base_url {
provider = provider.with_base_url(base_url);
}
Some(Box::new(provider))
}
if let Some(ref base_url) = self.base_url {
provider = provider.with_base_url(base_url);
}
Some(Box::new(provider))
}
}
+7 -50
View File
@@ -44,30 +44,20 @@ fn default_tools_dir() -> PathBuf {
}
impl WasmConfig {
pub(crate) fn resolve(settings: &crate::settings::Settings) -> Result<Self, ConfigError> {
let ws = &settings.wasm;
pub(crate) fn resolve() -> Result<Self, ConfigError> {
Ok(Self {
enabled: parse_bool_env("WASM_ENABLED", ws.enabled)?,
enabled: parse_bool_env("WASM_ENABLED", true)?,
tools_dir: optional_env("WASM_TOOLS_DIR")?
.map(PathBuf::from)
.or_else(|| ws.tools_dir.clone())
.unwrap_or_else(default_tools_dir),
default_memory_limit: parse_optional_env(
"WASM_DEFAULT_MEMORY_LIMIT",
ws.default_memory_limit,
10 * 1024 * 1024,
)?,
default_timeout_secs: parse_optional_env(
"WASM_DEFAULT_TIMEOUT_SECS",
ws.default_timeout_secs,
)?,
default_fuel_limit: parse_optional_env(
"WASM_DEFAULT_FUEL_LIMIT",
ws.default_fuel_limit,
)?,
cache_compiled: parse_bool_env("WASM_CACHE_COMPILED", ws.cache_compiled)?,
cache_dir: optional_env("WASM_CACHE_DIR")?
.map(PathBuf::from)
.or_else(|| ws.cache_dir.clone()),
default_timeout_secs: parse_optional_env("WASM_DEFAULT_TIMEOUT_SECS", 60)?,
default_fuel_limit: parse_optional_env("WASM_DEFAULT_FUEL_LIMIT", 10_000_000)?,
cache_compiled: parse_bool_env("WASM_CACHE_COMPILED", true)?,
cache_dir: optional_env("WASM_CACHE_DIR")?.map(PathBuf::from),
})
}
@@ -91,36 +81,3 @@ impl WasmConfig {
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::config::helpers::ENV_MUTEX;
use crate::settings::Settings;
#[test]
fn resolve_falls_back_to_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.wasm.default_memory_limit = 42;
settings.wasm.cache_compiled = false;
let cfg = WasmConfig::resolve(&settings).expect("resolve");
assert_eq!(cfg.default_memory_limit, 42);
assert!(!cfg.cache_compiled);
}
#[test]
fn env_overrides_settings() {
let _guard = ENV_MUTEX.lock().expect("env mutex poisoned");
let mut settings = Settings::default();
settings.wasm.default_fuel_limit = 42;
// SAFETY: Under ENV_MUTEX, no concurrent env access.
unsafe { std::env::set_var("WASM_DEFAULT_FUEL_LIMIT", "7") };
let cfg = WasmConfig::resolve(&settings).expect("resolve");
unsafe { std::env::remove_var("WASM_DEFAULT_FUEL_LIMIT") };
assert_eq!(cfg.default_fuel_limit, 7);
}
}
+3 -223
View File
@@ -46,17 +46,11 @@ impl ContextManager {
description: impl Into<String>,
) -> Result<Uuid, JobError> {
// Hold write lock for the entire check-insert to prevent TOCTOU races
// where two concurrent calls both pass the parallel_count check.
// where two concurrent calls both pass the active_count check.
let mut contexts = self.contexts.write().await;
// Only count jobs that consume execution slots (Pending, InProgress, Stuck).
// Completed and Submitted jobs are no longer actively executing and shouldn't
// block new job creation.
let parallel_count = contexts
.values()
.filter(|c| c.state.is_parallel_blocking())
.count();
let active_count = contexts.values().filter(|c| c.state.is_active()).count();
if parallel_count >= self.max_jobs {
if active_count >= self.max_jobs {
return Err(JobError::MaxJobsExceeded { max: self.max_jobs });
}
@@ -971,218 +965,4 @@ mod tests {
// And it's in the initial state (Pending), not modified by concurrent workers
assert_eq!(returned_ctx.state, crate::context::JobState::Pending); // safety: test code
}
#[tokio::test]
async fn sequential_routines_unlimited_completed_not_counted() {
// TEST: Sequential (non-parallel) routines should NOT be limited by max_jobs.
//
// Completed/Submitted jobs should NOT count toward the parallel job limit,
// since they're no longer actively consuming execution resources.
//
// Scenario: Create 10 sequential routines, each completing before the next starts.
// Currently FAILS because Completed jobs still count as "active".
// After fix, should PASS because only Pending/InProgress/Stuck count.
let manager = ContextManager::new(5); // max 5 truly parallel jobs
// Try to create and complete 10 sequential routines
for i in 0..10 {
let result = manager
.create_job(format!("Sequential Routine {}", i), "one at a time")
.await;
match result {
Ok(job_id) => {
// Simulate execution: Pending -> InProgress -> Completed
manager
.update_context(job_id, |ctx| {
ctx.transition_to(crate::context::JobState::InProgress, None)
})
.await
.unwrap()
.unwrap();
manager
.update_context(job_id, |ctx| {
ctx.transition_to(crate::context::JobState::Completed, None)
})
.await
.unwrap()
.unwrap();
println!("✓ Routine {} created and completed", i);
}
Err(JobError::MaxJobsExceeded { max }) => {
panic!(
"✗ Routine {} FAILED to create: MaxJobsExceeded (max={}).\n\
This shows the bug: Completed jobs from routines 0-4 are still counting \
toward the limit even though they're not running.\n\
After the fix, this test should pass because Completed jobs won't count.",
i, max
);
}
Err(e) => {
panic!("Unexpected error for routine {}: {:?}", i, e);
}
}
}
// If we reach here, all 10 routines succeeded (bug is fixed)
assert_eq!(manager.all_jobs().await.len(), 10);
println!("✓ SUCCESS: All 10 sequential routines created despite max_jobs=5 limit");
println!(" This is correct: Completed jobs don't count toward parallel limit");
}
#[tokio::test]
async fn parallel_jobs_limit_enforced_for_active_jobs() {
// TEST: Parallel (simultaneous) jobs ARE limited by max_jobs.
//
// Jobs in Pending/InProgress/Stuck states consume execution slots.
// The 6th truly-active job should fail because the limit is 5.
//
// This test verifies the limit DOES work correctly for parallel execution.
let manager = ContextManager::new(5); // max 5 parallel jobs
// Create 5 jobs and make them InProgress (simulating parallel execution)
let mut job_ids = Vec::new();
for i in 0..5 {
let job_id = manager
.create_job(format!("Parallel Job {}", i), "running in parallel")
.await
.expect("First 5 jobs should create successfully");
job_ids.push(job_id);
// Transition to InProgress (simulating active execution)
manager
.update_context(job_id, |ctx| {
ctx.transition_to(crate::context::JobState::InProgress, None)
})
.await
.unwrap()
.unwrap();
}
// Verify all 5 jobs are InProgress
for job_id in &job_ids {
let ctx = manager.get_context(*job_id).await.unwrap();
assert_eq!(
ctx.state,
crate::context::JobState::InProgress,
"All jobs should be InProgress"
);
}
// Check active count - should be 5 (all InProgress)
let active_count = manager.active_count().await;
assert_eq!(
active_count, 5,
"Active count should be 5 (all InProgress jobs count)"
);
// Try to create a 6th job - should FAIL because limit is reached
let result = manager.create_job("Parallel Job 6", "sixth job").await;
match result {
Err(JobError::MaxJobsExceeded { max: 5 }) => {
println!("✓ SUCCESS: Parallel job limit correctly enforced at 5 active jobs");
println!("✓ 6th InProgress job correctly blocked when 5 are already running");
}
Ok(_) => {
panic!(
"FAILED: 6th parallel job should have been blocked \
but was created. Limit enforcement is broken."
);
}
Err(e) => {
panic!(
"UNEXPECTED ERROR: Expected MaxJobsExceeded but got: {:?}",
e
);
}
}
}
#[tokio::test]
async fn completed_jobs_should_free_slots_after_fix() {
// TEST: After the fix, Completed jobs should NOT count toward the limit.
//
// This test demonstrates that when a job transitions from InProgress -> Completed,
// it should free up a slot in the parallel execution limit.
//
// Currently FAILS (bug not fixed), proving Completed jobs incorrectly stay in the limit.
// After fix, this will PASS (Completed jobs freed their slot).
let manager = ContextManager::new(5); // max 5 parallel jobs
// Create 5 InProgress jobs (fill the limit)
let mut job_ids = Vec::new();
for i in 0..5 {
let job_id = manager
.create_job(format!("Job {}", i), "parallel")
.await
.unwrap();
job_ids.push(job_id);
manager
.update_context(job_id, |ctx| {
ctx.transition_to(crate::context::JobState::InProgress, None)
})
.await
.unwrap()
.unwrap();
}
// Verify limit is hit
let result = manager.create_job("Job 5", "should fail").await;
assert!(
matches!(result, Err(JobError::MaxJobsExceeded { max: 5 })),
"Limit should be hit with 5 InProgress jobs"
);
println!("✓ Limit enforced: 5 InProgress jobs block 6th creation");
// Now transition job 0 from InProgress -> Completed
manager
.update_context(job_ids[0], |ctx| {
ctx.transition_to(crate::context::JobState::Completed, None)
})
.await
.unwrap()
.unwrap();
println!("✓ Job 0 transitioned: InProgress -> Completed");
// Try to create a 6th job - this will FAIL until the bug is fixed
let result = manager
.create_job("Job 5 (retry)", "after 1 Completed")
.await;
match result {
Ok(job_6) => {
println!("✓ SUCCESS: 6th job created after job 0 completed");
println!("✓ This proves Completed jobs don't count toward the limit (BUG FIXED)");
// Verify we can transition it to InProgress
manager
.update_context(job_6, |ctx| {
ctx.transition_to(crate::context::JobState::InProgress, None)
})
.await
.unwrap()
.unwrap();
println!("✓ 6th job now InProgress: 4 remaining + 1 new = 5 limit reached");
}
Err(JobError::MaxJobsExceeded { max: 5 }) => {
panic!(
"✗ BUG NOT FIXED: 6th job creation still blocked after freeing slot.\n\
State: 1 Completed (job 0) + 4 InProgress (jobs 1-4) = 5 active\n\
BUG: Completed job 0 still counts toward limit\n\
EXPECTED: Only 4 InProgress count, 1 slot free"
);
}
Err(e) => {
panic!("Unexpected error: {:?}", e);
}
}
}
}
+1 -79
View File
@@ -9,7 +9,7 @@ use rust_decimal::Decimal;
use serde::{Deserialize, Serialize};
use uuid::Uuid;
use crate::llm::recording::HttpInterceptor;
use crate::observability::HttpInterceptor;
/// Error returned when a job exceeds its token budget.
#[derive(Debug, thiserror::Error)]
@@ -48,14 +48,6 @@ impl JobState {
pub fn can_transition_to(&self, target: JobState) -> bool {
use JobState::*;
// Allow idempotent Completed -> Completed transition.
// Both the execution loop and the worker wrapper may race to mark a
// job complete; the second call should be a harmless no-op rather
// than an error that masks the successful completion.
if matches!((self, target), (Completed, Completed)) {
return true;
}
matches!(
(self, target),
// From Pending
@@ -81,15 +73,6 @@ impl JobState {
pub fn is_active(&self) -> bool {
!self.is_terminal()
}
/// Check if this job consumes a parallel execution slot.
///
/// Only jobs in Pending, InProgress, or Stuck states consume execution resources
/// and should count toward the parallel job limit. Completed and Submitted jobs
/// are in the state machine but are no longer actively executing.
pub fn is_parallel_blocking(&self) -> bool {
matches!(self, Self::Pending | Self::InProgress | Self::Stuck)
}
}
impl std::fmt::Display for JobState {
@@ -130,9 +113,6 @@ pub struct JobContext {
pub state: JobState,
/// User ID that owns this job (for workspace scoping).
pub user_id: String,
/// Channel-specific requester/actor ID, when different from the owner scope.
#[serde(skip_serializing_if = "Option::is_none")]
pub requester_id: Option<String>,
/// Conversation ID if linked to a conversation.
pub conversation_id: Option<Uuid>,
/// Job title.
@@ -214,7 +194,6 @@ impl JobContext {
job_id: Uuid::new_v4(),
state: JobState::Pending,
user_id: user_id.into(),
requester_id: None,
conversation_id: None,
title: title.into(),
description: description.into(),
@@ -246,12 +225,6 @@ impl JobContext {
self
}
/// Set the channel-specific requester/actor ID.
pub fn with_requester_id(mut self, requester_id: impl Into<String>) -> Self {
self.requester_id = Some(requester_id.into());
self
}
/// Transition to a new state.
pub fn transition_to(
&mut self,
@@ -265,18 +238,6 @@ impl JobContext {
));
}
// Idempotent: already in the target state, skip recording a duplicate
// transition. This handles the Completed -> Completed race between
// execution_loop and the worker wrapper.
if self.state == new_state {
tracing::debug!(
job_id = %self.job_id,
state = %self.state,
"idempotent state transition (already in target state), skipping"
);
return Ok(());
}
let transition = StateTransition {
from: self.state,
to: new_state,
@@ -379,45 +340,6 @@ mod tests {
assert!(!JobState::Accepted.can_transition_to(JobState::InProgress));
}
#[test]
fn test_completed_to_completed_is_idempotent() {
// Regression test for the race condition where both execution_loop
// and the worker wrapper call mark_completed(). The second call
// must succeed without error and must not record a duplicate
// transition.
let mut ctx = JobContext::new("Test", "Idempotent completion test");
ctx.transition_to(JobState::InProgress, None).unwrap();
ctx.transition_to(JobState::Completed, Some("first".into()))
.unwrap();
assert_eq!(ctx.state, JobState::Completed);
let transitions_before = ctx.transitions.len();
// Second Completed -> Completed must be a no-op
let result = ctx.transition_to(JobState::Completed, Some("duplicate".into()));
assert!(
result.is_ok(),
"Completed -> Completed should be idempotent"
);
assert_eq!(ctx.state, JobState::Completed);
assert_eq!(
ctx.transitions.len(),
transitions_before,
"idempotent transition should not record a new history entry"
);
}
#[test]
fn test_other_self_transitions_still_rejected() {
// Ensure we only allow Completed -> Completed, not arbitrary X -> X.
assert!(!JobState::Pending.can_transition_to(JobState::Pending));
assert!(!JobState::InProgress.can_transition_to(JobState::InProgress));
assert!(!JobState::Failed.can_transition_to(JobState::Failed));
assert!(!JobState::Stuck.can_transition_to(JobState::Stuck));
assert!(!JobState::Submitted.can_transition_to(JobState::Submitted));
assert!(!JobState::Accepted.can_transition_to(JobState::Accepted));
assert!(!JobState::Cancelled.can_transition_to(JobState::Cancelled));
}
#[test]
fn test_terminal_states() {
assert!(JobState::Accepted.is_terminal());
+143
View File
@@ -0,0 +1,143 @@
//! AuditStore implementation for libSQL.
use async_trait::async_trait;
use uuid::Uuid;
use crate::db::{AuditFilter, AuditRecord, AuditStore};
use crate::error::DatabaseError;
use super::LibSqlBackend;
fn parse_opt_uuid(row: &libsql::Row, idx: i32) -> Option<Uuid> {
super::get_opt_text(row, idx).and_then(|s| Uuid::parse_str(&s).ok())
}
#[async_trait]
impl AuditStore for LibSqlBackend {
async fn append_audit_events(&self, events: &[AuditRecord]) -> Result<(), DatabaseError> {
if events.is_empty() {
return Ok(());
}
let conn = self.connect().await?;
// Use a transaction for the batch insert.
conn.execute("BEGIN", ())
.await
.map_err(|e| DatabaseError::Query(format!("audit begin: {e}")))?;
for event in events {
conn.execute(
"INSERT INTO audit_log (event_id, event_type, source_module, source_component, \
category, session_id, thread_id, job_id, user_id, payload, created_at) \
VALUES (?1, ?2, ?3, ?4, ?5, ?6, ?7, ?8, ?9, ?10, ?11)",
libsql::params![
event.event_id as i64,
event.event_type.clone(),
event.source_module.clone(),
event.source_component.clone(),
event.category.clone(),
event.session_id.map(|u| u.to_string()),
event.thread_id.map(|u| u.to_string()),
event.job_id.map(|u| u.to_string()),
event.user_id.clone(),
serde_json::to_string(&event.payload).unwrap_or_default(),
super::fmt_ts(&event.created_at),
],
)
.await
.map_err(|e| DatabaseError::Query(format!("audit insert: {e}")))?;
}
conn.execute("COMMIT", ())
.await
.map_err(|e| DatabaseError::Query(format!("audit commit: {e}")))?;
Ok(())
}
async fn query_audit_log(
&self,
filter: &AuditFilter,
) -> Result<Vec<AuditRecord>, DatabaseError> {
let conn = self.connect().await?;
let mut query = String::from(
"SELECT event_id, event_type, source_module, source_component, category, \
session_id, thread_id, job_id, user_id, payload, created_at \
FROM audit_log WHERE 1=1",
);
let mut params: Vec<libsql::Value> = Vec::new();
let mut idx = 1;
if let Some(ref sid) = filter.session_id {
query.push_str(&format!(" AND session_id = ?{idx}"));
params.push(sid.to_string().into());
idx += 1;
}
if let Some(ref jid) = filter.job_id {
query.push_str(&format!(" AND job_id = ?{idx}"));
params.push(jid.to_string().into());
idx += 1;
}
if let Some(ref uid) = filter.user_id {
query.push_str(&format!(" AND user_id = ?{idx}"));
params.push(uid.clone().into());
idx += 1;
}
if let Some(ref et) = filter.event_type {
query.push_str(&format!(" AND event_type = ?{idx}"));
params.push(et.clone().into());
idx += 1;
}
if let Some(ref after) = filter.after {
query.push_str(&format!(" AND created_at > ?{idx}"));
params.push(super::fmt_ts(after).into());
idx += 1;
}
if let Some(ref before) = filter.before {
query.push_str(&format!(" AND created_at < ?{idx}"));
params.push(super::fmt_ts(before).into());
idx += 1;
}
query.push_str(" ORDER BY created_at DESC");
let limit = filter.limit.unwrap_or(1000);
query.push_str(&format!(" LIMIT ?{idx}"));
params.push(limit.into());
let rows = conn
.query(&query, libsql::params_from_iter(params))
.await
.map_err(|e| DatabaseError::Query(format!("audit_log query: {e}")))?;
let mut records = Vec::new();
let mut rows = rows;
while let Some(row) = rows
.next()
.await
.map_err(|e| DatabaseError::Query(format!("audit_log row: {e}")))?
{
let event_id: i64 = super::get_i64(&row, 0);
let payload_str: String = super::get_text(&row, 9);
let payload: serde_json::Value = serde_json::from_str(&payload_str).unwrap_or_default();
records.push(AuditRecord {
event_id: event_id as u64,
event_type: super::get_text(&row, 1),
source_module: super::get_text(&row, 2),
source_component: super::get_text(&row, 3),
category: super::get_text(&row, 4),
session_id: parse_opt_uuid(&row, 5),
thread_id: parse_opt_uuid(&row, 6),
job_id: parse_opt_uuid(&row, 7),
user_id: super::get_opt_text(&row, 8),
payload,
created_at: super::get_ts(&row, 10),
});
}
Ok(records)
}
}
-1
View File
@@ -106,7 +106,6 @@ impl JobStore for LibSqlBackend {
job_id: get_text(&row, 0).parse().unwrap_or_default(),
state,
user_id: get_text(&row, 6),
requester_id: None,
conversation_id: get_opt_text(&row, 1).and_then(|s| s.parse().ok()),
title: get_text(&row, 2),
description: get_text(&row, 3),
+3 -23
View File
@@ -6,6 +6,7 @@
//! - Turso cloud with embedded replica (sync to cloud)
//! - In-memory (for testing)
mod audit;
mod conversations;
mod jobs;
mod routines;
@@ -247,17 +248,6 @@ pub(crate) fn opt_text_owned(s: Option<String>) -> libsql::Value {
}
}
pub(crate) fn normalize_notify_user(value: Option<String>) -> Option<String> {
value.and_then(|value| {
let trimmed = value.trim();
if trimmed.is_empty() || trimmed == "default" {
None
} else {
Some(trimmed.to_string())
}
})
}
/// Extract an i64 column, defaulting to 0.
pub(crate) fn get_i64(row: &libsql::Row, idx: i32) -> i64 {
row.get::<i64>(idx).unwrap_or(0)
@@ -389,7 +379,7 @@ pub(crate) fn row_to_routine_libsql(row: &libsql::Row) -> Result<Routine, Databa
},
notify: NotifyConfig {
channel: get_opt_text(row, 12),
user: normalize_notify_user(get_opt_text(row, 13)),
user: get_text(row, 13),
on_success: get_i64(row, 14) != 0,
on_failure: get_i64(row, 15) != 0,
on_attention: get_i64(row, 16) != 0,
@@ -430,17 +420,7 @@ mod tests {
use chrono::{TimeZone, Utc};
use crate::db::Database;
use crate::db::libsql::{LibSqlBackend, normalize_notify_user, parse_timestamp};
#[test]
fn test_normalize_notify_user_treats_legacy_default_as_missing() {
assert_eq!(normalize_notify_user(None), None); // safety: test-only assertion
assert_eq!(normalize_notify_user(Some(String::new())), None); // safety: test-only assertion
assert_eq!(normalize_notify_user(Some(" ".to_string())), None); // safety: test-only assertion
assert_eq!(normalize_notify_user(Some("default".to_string())), None); // safety: test-only assertion
let normalized = normalize_notify_user(Some("123456789".to_string()));
assert_eq!(normalized, Some("123456789".to_string())); // safety: test-only assertion
}
use crate::db::libsql::{LibSqlBackend, parse_timestamp};
#[test]
fn test_parse_timestamp_accepts_rfc3339_and_legacy_naive_formats() {
+2 -2
View File
@@ -57,7 +57,7 @@ impl RoutineStore for LibSqlBackend {
max_concurrent,
dedup_window_secs,
opt_text(routine.notify.channel.as_deref()),
opt_text(routine.notify.user.as_deref()),
routine.notify.user.as_str(),
routine.notify.on_success as i64,
routine.notify.on_failure as i64,
routine.notify.on_attention as i64,
@@ -250,7 +250,7 @@ impl RoutineStore for LibSqlBackend {
max_concurrent,
dedup_window_secs,
opt_text(routine.notify.channel.as_deref()),
opt_text(routine.notify.user.as_deref()),
routine.notify.user.as_str(),
routine.notify.on_success as i64,
routine.notify.on_failure as i64,
routine.notify.on_attention as i64,
+22 -65
View File
@@ -462,7 +462,7 @@ CREATE TABLE IF NOT EXISTS routines (
max_concurrent INTEGER NOT NULL DEFAULT 1,
dedup_window_secs INTEGER,
notify_channel TEXT,
notify_user TEXT,
notify_user TEXT NOT NULL DEFAULT 'default',
notify_on_success INTEGER NOT NULL DEFAULT 0,
notify_on_failure INTEGER NOT NULL DEFAULT 1,
notify_on_attention INTEGER NOT NULL DEFAULT 1,
@@ -546,9 +546,7 @@ CREATE INDEX IF NOT EXISTS idx_tool_failures_unrepaired ON tool_failures(tool_na
-- routines
CREATE INDEX IF NOT EXISTS idx_routines_next_fire ON routines(next_fire_at);
CREATE INDEX IF NOT EXISTS idx_routines_event_triggers
ON routines(trigger_type, user_id)
WHERE enabled = 1 AND trigger_type IN ('event', 'system_event');
CREATE INDEX IF NOT EXISTS idx_routines_event_triggers ON routines(user_id);
-- routine_runs
CREATE INDEX IF NOT EXISTS idx_routine_runs_status ON routine_runs(status);
@@ -660,70 +658,29 @@ ALTER TABLE agent_jobs ADD COLUMN total_tokens_used INTEGER NOT NULL DEFAULT 0;
),
(
13,
"routine_notify_user_nullable",
// Remove the legacy 'default' sentinel from routine notify_user.
// SQLite cannot drop NOT NULL / DEFAULT constraints in place, so we
// rebuild the table and normalize existing 'default' values to NULL.
"audit_log",
// Append-only audit log for security-relevant system events.
r#"
PRAGMA foreign_keys=OFF;
CREATE TABLE IF NOT EXISTS routines_new (
id TEXT PRIMARY KEY,
name TEXT NOT NULL,
description TEXT NOT NULL DEFAULT '',
user_id TEXT NOT NULL,
enabled INTEGER NOT NULL DEFAULT 1,
trigger_type TEXT NOT NULL,
trigger_config TEXT NOT NULL,
action_type TEXT NOT NULL,
action_config TEXT NOT NULL,
cooldown_secs INTEGER NOT NULL DEFAULT 300,
max_concurrent INTEGER NOT NULL DEFAULT 1,
dedup_window_secs INTEGER,
notify_channel TEXT,
notify_user TEXT,
notify_on_success INTEGER NOT NULL DEFAULT 0,
notify_on_failure INTEGER NOT NULL DEFAULT 1,
notify_on_attention INTEGER NOT NULL DEFAULT 1,
state TEXT NOT NULL DEFAULT '{}',
last_run_at TEXT,
next_fire_at TEXT,
run_count INTEGER NOT NULL DEFAULT 0,
consecutive_failures INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
updated_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
UNIQUE (user_id, name)
CREATE TABLE IF NOT EXISTS audit_log (
id INTEGER PRIMARY KEY AUTOINCREMENT,
event_id INTEGER NOT NULL,
event_type TEXT NOT NULL,
source_module TEXT NOT NULL,
source_component TEXT NOT NULL,
category TEXT NOT NULL,
session_id TEXT,
thread_id TEXT,
job_id TEXT,
user_id TEXT,
payload TEXT NOT NULL DEFAULT '{}',
created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
);
INSERT INTO routines_new (
id, name, description, user_id, enabled,
trigger_type, trigger_config, action_type, action_config,
cooldown_secs, max_concurrent, dedup_window_secs,
notify_channel, notify_user, notify_on_success, notify_on_failure, notify_on_attention,
state, last_run_at, next_fire_at, run_count, consecutive_failures,
created_at, updated_at
)
SELECT
id, name, description, user_id, enabled,
trigger_type, trigger_config, action_type, action_config,
cooldown_secs, max_concurrent, dedup_window_secs,
notify_channel,
CASE WHEN notify_user = 'default' THEN NULL ELSE notify_user END,
notify_on_success, notify_on_failure, notify_on_attention,
state, last_run_at, next_fire_at, run_count, consecutive_failures,
created_at, updated_at
FROM routines;
DROP TABLE routines;
ALTER TABLE routines_new RENAME TO routines;
CREATE INDEX IF NOT EXISTS idx_routines_user ON routines(user_id);
CREATE INDEX IF NOT EXISTS idx_routines_next_fire ON routines(next_fire_at);
CREATE INDEX IF NOT EXISTS idx_routines_event_triggers
ON routines(trigger_type, user_id)
WHERE enabled = 1 AND trigger_type IN ('event', 'system_event');
PRAGMA foreign_keys=ON;
CREATE INDEX IF NOT EXISTS idx_audit_log_created_at ON audit_log (created_at);
CREATE INDEX IF NOT EXISTS idx_audit_log_job_id ON audit_log (job_id);
CREATE INDEX IF NOT EXISTS idx_audit_log_session_id ON audit_log (session_id);
CREATE INDEX IF NOT EXISTS idx_audit_log_user_id ON audit_log (user_id);
CREATE INDEX IF NOT EXISTS idx_audit_log_event_type ON audit_log (event_type);
"#,
),
];
+70 -3
View File
@@ -29,8 +29,6 @@ use chrono::{DateTime, Utc};
use rust_decimal::Decimal;
use uuid::Uuid;
use crate::agent::BrokenTool;
use crate::agent::routine::{Routine, RoutineRun, RunStatus};
use crate::context::{ActionRecord, JobContext, JobState};
use crate::error::DatabaseError;
use crate::error::WorkspaceError;
@@ -38,6 +36,8 @@ use crate::history::{
AgentJobRecord, AgentJobSummary, ConversationMessage, ConversationSummary, JobEventRecord,
LlmCallRecord, SandboxJobRecord, SandboxJobSummary, SettingRow,
};
use crate::models::routine::{Routine, RoutineRun, RunStatus};
use crate::models::tool_failure::ToolFailureRecord;
use crate::workspace::{MemoryChunk, MemoryDocument, WorkspaceEntry};
use crate::workspace::{SearchConfig, SearchResult};
@@ -534,7 +534,10 @@ pub trait ToolFailureStore: Send + Sync {
tool_name: &str,
error_message: &str,
) -> Result<(), DatabaseError>;
async fn get_broken_tools(&self, threshold: i32) -> Result<Vec<BrokenTool>, DatabaseError>;
async fn get_broken_tools(
&self,
threshold: i32,
) -> Result<Vec<ToolFailureRecord>, DatabaseError>;
async fn mark_tool_repaired(&self, tool_name: &str) -> Result<(), DatabaseError>;
async fn increment_repair_attempts(&self, tool_name: &str) -> Result<(), DatabaseError>;
}
@@ -638,6 +641,70 @@ pub trait WorkspaceStore: Send + Sync {
) -> Result<Vec<SearchResult>, WorkspaceError>;
}
// ==================== Audit Log ====================
/// An audit record destined for the append-only `audit_log` table.
#[derive(Debug, Clone, serde::Serialize)]
pub struct AuditRecord {
/// Bus sequence number.
pub event_id: u64,
/// Short event type name (e.g. "state_transition", "tool_execution").
pub event_type: String,
/// Source module.
pub source_module: String,
/// Source component.
pub source_component: String,
/// Event category.
pub category: String,
/// Session ID (if applicable).
pub session_id: Option<Uuid>,
/// Thread ID (if applicable).
pub thread_id: Option<Uuid>,
/// Job ID (if applicable).
pub job_id: Option<Uuid>,
/// User ID (if applicable).
pub user_id: Option<String>,
/// Full event payload as JSON.
pub payload: serde_json::Value,
/// When the event was created.
pub created_at: DateTime<Utc>,
}
/// Filter for querying the audit log.
#[derive(Debug, Default)]
pub struct AuditFilter {
/// Filter by session ID.
pub session_id: Option<Uuid>,
/// Filter by job ID.
pub job_id: Option<Uuid>,
/// Filter by user ID.
pub user_id: Option<String>,
/// Filter by event type.
pub event_type: Option<String>,
/// Only events after this time.
pub after: Option<DateTime<Utc>>,
/// Only events before this time.
pub before: Option<DateTime<Utc>>,
/// Maximum number of records to return.
pub limit: Option<i64>,
}
/// Append-only audit log persistence.
///
/// Intentionally separate from `Database` — not all backends need to implement
/// this (and it can be a standalone trait object for the audit sink).
#[async_trait]
pub trait AuditStore: Send + Sync {
/// Append audit records (batch insert). No update. No delete.
async fn append_audit_events(&self, events: &[AuditRecord]) -> Result<(), DatabaseError>;
/// Query the audit log with filters.
async fn query_audit_log(
&self,
filter: &AuditFilter,
) -> Result<Vec<AuditRecord>, DatabaseError>;
}
/// Backend-agnostic database supertrait.
///
/// Combines all sub-traits into one. Existing `Arc<dyn Database>` consumers
+159
View File
@@ -707,3 +707,162 @@ impl WorkspaceStore for PgBackend {
.await
}
}
// ==================== AuditStore ====================
#[async_trait]
impl crate::db::AuditStore for PgBackend {
async fn append_audit_events(
&self,
events: &[crate::db::AuditRecord],
) -> Result<(), DatabaseError> {
if events.is_empty() {
return Ok(());
}
let client = self
.store
.pool()
.get()
.await
.map_err(|e| DatabaseError::Pool(e.to_string()))?;
// Build a batch INSERT for all events in a single round-trip.
let mut query = String::from(
"INSERT INTO audit_log (event_id, event_type, source_module, source_component, \
category, session_id, thread_id, job_id, user_id, payload, created_at) VALUES ",
);
let mut params: Vec<Box<dyn tokio_postgres::types::ToSql + Sync + Send>> = Vec::new();
let mut param_idx = 1;
for (i, event) in events.iter().enumerate() {
if i > 0 {
query.push_str(", ");
}
query.push_str(&format!(
"(${}, ${}, ${}, ${}, ${}, ${}, ${}, ${}, ${}, ${}, ${})",
param_idx,
param_idx + 1,
param_idx + 2,
param_idx + 3,
param_idx + 4,
param_idx + 5,
param_idx + 6,
param_idx + 7,
param_idx + 8,
param_idx + 9,
param_idx + 10
));
param_idx += 11;
params.push(Box::new(event.event_id as i64));
params.push(Box::new(event.event_type.clone()));
params.push(Box::new(event.source_module.clone()));
params.push(Box::new(event.source_component.clone()));
params.push(Box::new(event.category.clone()));
params.push(Box::new(event.session_id));
params.push(Box::new(event.thread_id));
params.push(Box::new(event.job_id));
params.push(Box::new(event.user_id.clone()));
params.push(Box::new(event.payload.clone()));
params.push(Box::new(event.created_at));
}
let param_refs: Vec<&(dyn tokio_postgres::types::ToSql + Sync)> =
params.iter().map(|p| p.as_ref() as _).collect();
client // safety: single batch INSERT, no multi-step transaction needed
.execute(&query, &param_refs)
.await
.map_err(|e| DatabaseError::Query(format!("audit_log insert failed: {e}")))?;
Ok(())
}
async fn query_audit_log(
&self,
filter: &crate::db::AuditFilter,
) -> Result<Vec<crate::db::AuditRecord>, DatabaseError> {
let client = self
.store
.pool()
.get()
.await
.map_err(|e| DatabaseError::Pool(e.to_string()))?;
let mut query = String::from(
"SELECT event_id, event_type, source_module, source_component, category, \
session_id, thread_id, job_id, user_id, payload, created_at \
FROM audit_log WHERE 1=1",
);
let mut params: Vec<Box<dyn tokio_postgres::types::ToSql + Sync + Send>> = Vec::new();
let mut idx = 1;
if let Some(ref sid) = filter.session_id {
query.push_str(&format!(" AND session_id = ${idx}"));
params.push(Box::new(*sid));
idx += 1;
}
if let Some(ref jid) = filter.job_id {
query.push_str(&format!(" AND job_id = ${idx}"));
params.push(Box::new(*jid));
idx += 1;
}
if let Some(ref uid) = filter.user_id {
query.push_str(&format!(" AND user_id = ${idx}"));
params.push(Box::new(uid.clone()));
idx += 1;
}
if let Some(ref et) = filter.event_type {
query.push_str(&format!(" AND event_type = ${idx}"));
params.push(Box::new(et.clone()));
idx += 1;
}
if let Some(ref after) = filter.after {
query.push_str(&format!(" AND created_at > ${idx}"));
params.push(Box::new(*after));
idx += 1;
}
if let Some(ref before) = filter.before {
query.push_str(&format!(" AND created_at < ${idx}"));
params.push(Box::new(*before));
idx += 1;
}
query.push_str(" ORDER BY created_at DESC");
let limit = filter.limit.unwrap_or(1000);
query.push_str(&format!(" LIMIT ${idx}"));
params.push(Box::new(limit));
let param_refs: Vec<&(dyn tokio_postgres::types::ToSql + Sync)> =
params.iter().map(|p| p.as_ref() as _).collect();
let rows = client
.query(&query, &param_refs)
.await
.map_err(|e| DatabaseError::Query(format!("audit_log query failed: {e}")))?;
let records = rows
.iter()
.map(|row| {
let event_id: i64 = row.get("event_id");
crate::db::AuditRecord {
event_id: event_id as u64,
event_type: row.get("event_type"),
source_module: row.get("source_module"),
source_component: row.get("source_component"),
category: row.get("category"),
session_id: row.get("session_id"),
thread_id: row.get("thread_id"),
job_id: row.get("job_id"),
user_id: row.get("user_id"),
payload: row.get("payload"),
created_at: row.get("created_at"),
}
})
.collect();
Ok(records)
}
}
+9 -27
View File
@@ -5,22 +5,13 @@
//! certificates — the same TLS stack that `reqwest` already uses for HTTP.
use deadpool_postgres::{Pool, Runtime};
use thiserror::Error;
use tokio_postgres::NoTls;
use tokio_postgres_rustls::MakeRustlsConnect;
use crate::config::SslMode;
#[derive(Debug, Error)]
pub enum CreatePoolError {
#[error("{0}")]
Pool(#[from] deadpool_postgres::CreatePoolError),
#[error("postgres TLS configuration failed: {0}")]
TlsConfig(#[from] rustls::Error),
}
/// Build a rustls-based TLS connector using the platform's root certificate store.
fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
fn make_rustls_connector() -> MakeRustlsConnect {
let mut root_store = rustls::RootCertStore::empty();
let native = rustls_native_certs::load_native_certs();
for e in &native.errors {
@@ -34,15 +25,10 @@ fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
if root_store.is_empty() {
tracing::error!("no system root certificates found -- TLS connections will fail");
}
// `--all-features` brings in both aws-lc-rs and ring-backed rustls providers.
// Pick the same ring provider reqwest already uses so postgres TLS setup stays deterministic.
let config = rustls::ClientConfig::builder_with_provider(
rustls::crypto::ring::default_provider().into(),
)
.with_safe_default_protocol_versions()?
.with_root_certificates(root_store)
.with_no_client_auth();
Ok(MakeRustlsConnect::new(config))
let config = rustls::ClientConfig::builder()
.with_root_certificates(root_store)
.with_no_client_auth();
MakeRustlsConnect::new(config)
}
/// Create a [`deadpool_postgres::Pool`] with the appropriate TLS connector.
@@ -59,16 +45,12 @@ fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
pub fn create_pool(
config: &deadpool_postgres::Config,
ssl_mode: SslMode,
) -> Result<Pool, CreatePoolError> {
) -> Result<Pool, deadpool_postgres::CreatePoolError> {
match ssl_mode {
SslMode::Disable => config
.create_pool(Some(Runtime::Tokio1), NoTls)
.map_err(CreatePoolError::from),
SslMode::Disable => config.create_pool(Some(Runtime::Tokio1), NoTls),
SslMode::Prefer | SslMode::Require => {
let tls = make_rustls_connector()?;
config
.create_pool(Some(Runtime::Tokio1), tls)
.map_err(CreatePoolError::from)
let tls = make_rustls_connector();
config.create_pool(Some(Runtime::Tokio1), tls)
}
}
}
-3
View File
@@ -122,9 +122,6 @@ pub enum ChannelError {
#[error("Failed to send response on channel {name}: {reason}")]
SendFailed { name: String, reason: String },
#[error("Channel {name} is missing a routing target: {reason}")]
MissingRoutingTarget { name: String, reason: String },
#[error("Invalid message format: {0}")]
InvalidMessage(String),
+302
View File
@@ -0,0 +1,302 @@
//! The unified event bus.
//!
//! Single broadcast channel through which all system events flow.
//! Sinks subscribe and filter by category or payload type.
use std::sync::Arc;
use std::sync::atomic::{AtomicU64, Ordering};
use chrono::Utc;
use tokio::sync::broadcast;
use super::event::{
EventCategory, EventContext, EventPayload, EventSource, SystemEvent, TelemetryPayload,
};
/// Buffer size for the broadcast channel.
const BUS_BUFFER: usize = 1024;
/// Unified event bus backed by `broadcast::Sender<Arc<SystemEvent>>`.
///
/// `Arc`-wrapping avoids deep-cloning payloads across multiple sinks.
/// The monotonic sequence counter ensures total ordering.
#[derive(Clone)]
pub struct EventBus {
tx: broadcast::Sender<Arc<SystemEvent>>,
seq: Arc<AtomicU64>,
}
impl EventBus {
/// Create a new event bus.
pub fn new() -> Self {
let (tx, _) = broadcast::channel(BUS_BUFFER);
Self {
tx,
seq: Arc::new(AtomicU64::new(1)),
}
}
/// Emit a raw event with explicit category.
pub fn emit(
&self,
source: EventSource,
category: EventCategory,
context: EventContext,
payload: EventPayload,
) {
let event = Arc::new(SystemEvent {
id: self.seq.fetch_add(1, Ordering::Relaxed),
timestamp: Utc::now(),
source,
category,
context,
payload,
});
// Ignore send error (no active receivers is fine).
let _ = self.tx.send(event);
}
/// Emit an event, auto-classifying category from the payload.
pub fn emit_auto(&self, source: EventSource, context: EventContext, payload: EventPayload) {
let category = payload.default_category();
self.emit(source, category, context, payload);
}
/// Emit a `DomainEvent` (most common path — SSE broadcast).
pub fn emit_domain(
&self,
source: EventSource,
context: EventContext,
event: crate::events::DomainEvent,
) {
self.emit(
source,
EventCategory::Ephemeral,
context,
EventPayload::Domain(event),
);
}
/// Emit a `StateChange` for cache invalidation.
pub fn emit_state_change(&self, change: crate::state_bus::StateChange) {
self.emit(
EventSource::new("system", "state_bus"),
EventCategory::StateChange,
EventContext::empty(),
EventPayload::StateChange(change),
);
}
/// Emit a state machine transition (recorded in audit log).
#[allow(clippy::too_many_arguments)]
pub fn emit_transition(
&self,
source: EventSource,
context: EventContext,
entity_type: impl Into<String>,
entity_id: impl Into<String>,
from_state: impl Into<String>,
to_state: impl Into<String>,
reason: Option<String>,
) {
self.emit(
source,
EventCategory::Audit,
context,
EventPayload::StateTransition {
entity_type: entity_type.into(),
entity_id: entity_id.into(),
from_state: from_state.into(),
to_state: to_state.into(),
reason,
},
);
}
/// Emit a tool execution record.
#[allow(clippy::too_many_arguments)]
pub fn emit_tool_execution(
&self,
source: EventSource,
context: EventContext,
tool_name: impl Into<String>,
parameters_hash: impl Into<String>,
duration_ms: u64,
success: bool,
error: Option<String>,
) {
self.emit(
source,
EventCategory::Audit,
context,
EventPayload::ToolExecution {
tool_name: tool_name.into(),
parameters_hash: parameters_hash.into(),
duration_ms,
success,
error,
},
);
}
/// Emit a telemetry event.
pub fn emit_telemetry(
&self,
source: EventSource,
context: EventContext,
telemetry: TelemetryPayload,
) {
self.emit(
source,
EventCategory::Metric,
context,
EventPayload::Telemetry(telemetry),
);
}
/// Subscribe to all events on this bus.
pub fn subscribe(&self) -> broadcast::Receiver<Arc<SystemEvent>> {
self.tx.subscribe()
}
/// Get the current sequence number (for testing/debugging).
pub fn current_seq(&self) -> u64 {
self.seq.load(Ordering::Relaxed)
}
}
impl Default for EventBus {
fn default() -> Self {
Self::new()
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::events::DomainEvent;
use tokio_stream::StreamExt;
use tokio_stream::wrappers::BroadcastStream;
#[tokio::test]
async fn emit_and_receive() {
let bus = EventBus::new();
let mut rx = bus.subscribe();
bus.emit_domain(
EventSource::new("test", "unit"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
let event = rx.recv().await.expect("should receive event"); // safety: test-only
assert_eq!(event.id, 1); // safety: test-only
assert_eq!(event.category, EventCategory::Ephemeral); // safety: test-only
assert!(matches!( // safety: test-only
event.payload,
EventPayload::Domain(DomainEvent::Heartbeat)
));
}
#[tokio::test]
async fn monotonic_sequence() {
let bus = EventBus::new();
let mut rx = bus.subscribe();
for _ in 0..5 {
bus.emit_domain(
EventSource::new("test", "seq"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
}
let mut last_id = 0;
for _ in 0..5 {
let event = rx.recv().await.expect("should receive event"); // safety: test-only
assert!(event.id > last_id, "IDs must be monotonically increasing"); // safety: test-only
last_id = event.id;
}
}
#[tokio::test]
async fn multiple_subscribers() {
let bus = EventBus::new();
let mut rx1 = bus.subscribe();
let mut rx2 = bus.subscribe();
bus.emit_state_change(crate::state_bus::StateChange::ConfigReloaded);
let e1 = rx1.recv().await.expect("subscriber 1 should receive"); // safety: test-only
let e2 = rx2.recv().await.expect("subscriber 2 should receive"); // safety: test-only
assert_eq!(e1.id, e2.id); // safety: test-only
}
#[tokio::test]
async fn no_subscriber_does_not_panic() {
let bus = EventBus::new();
bus.emit_domain(
EventSource::new("test", "noop"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
// Should not panic
}
#[tokio::test]
async fn auto_category_from_payload() {
let bus = EventBus::new();
let mut rx = bus.subscribe();
bus.emit_auto(
EventSource::new("test", "auto"),
EventContext::empty(),
EventPayload::StateTransition {
entity_type: "thread".into(),
entity_id: "abc".into(),
from_state: "Idle".into(),
to_state: "Processing".into(),
reason: None,
},
);
let event = rx.recv().await.expect("should receive event"); // safety: test-only
assert_eq!(event.category, EventCategory::Audit); // safety: test-only
}
#[tokio::test]
async fn stream_adapter_works() {
let bus = EventBus::new();
let rx = bus.subscribe();
let mut stream = BroadcastStream::new(rx);
bus.emit_domain(
EventSource::new("test", "stream"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
let event = stream // safety: test-only
.next()
.await
.expect("stream should yield") // safety: test-only
.expect("no lag"); // safety: test-only
assert_eq!(event.id, 1); // safety: test-only
}
#[tokio::test]
async fn clone_shares_bus() {
let bus1 = EventBus::new();
let bus2 = bus1.clone();
let mut rx = bus1.subscribe();
bus2.emit_domain(
EventSource::new("test", "clone"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
let event = rx.recv().await.expect("should receive from cloned bus"); // safety: test-only
assert_eq!(event.id, 1); // safety: test-only
}
}
+233
View File
@@ -0,0 +1,233 @@
//! Core event types for the unified event bus.
//!
//! `SystemEvent` is the tagged envelope that wraps all event payloads with
//! metadata (source, category, context). All events flow through one bus;
//! sinks filter by category or payload type.
use chrono::{DateTime, Utc};
use serde::Serialize;
use uuid::Uuid;
/// Monotonic event envelope carrying metadata + payload.
#[derive(Debug, Clone, Serialize)]
pub struct SystemEvent {
/// Monotonic sequence number assigned by the bus.
pub id: u64,
/// When the event was created.
pub timestamp: DateTime<Utc>,
/// Which module/component produced this event.
pub source: EventSource,
/// Classification controlling sink routing.
pub category: EventCategory,
/// Contextual identifiers for correlation.
pub context: EventContext,
/// The event-specific data.
pub payload: EventPayload,
}
/// Which module and component produced the event.
#[derive(Debug, Clone, Serialize)]
pub struct EventSource {
/// Top-level module (e.g. "agent", "worker", "orchestrator").
pub module: String,
/// Specific component within the module (e.g. "dispatcher", "scheduler").
pub component: String,
}
impl EventSource {
pub fn new(module: impl Into<String>, component: impl Into<String>) -> Self {
Self {
module: module.into(),
component: component.into(),
}
}
}
/// Event classification for sink routing.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize)]
pub enum EventCategory {
/// Security-relevant events that must be persisted (append-only audit log).
Audit,
/// Transient events (SSE broadcast, status updates) — OK to drop.
Ephemeral,
/// State machine transitions — recorded for debugging and audit.
StateChange,
/// Numeric metrics and telemetry.
Metric,
}
/// Contextual identifiers for event correlation.
#[derive(Debug, Clone, Default, Serialize)]
pub struct EventContext {
/// Session ID (if applicable).
#[serde(skip_serializing_if = "Option::is_none")]
pub session_id: Option<Uuid>,
/// Thread ID (if applicable).
#[serde(skip_serializing_if = "Option::is_none")]
pub thread_id: Option<Uuid>,
/// Job ID (if applicable).
#[serde(skip_serializing_if = "Option::is_none")]
pub job_id: Option<Uuid>,
/// User ID (if applicable).
#[serde(skip_serializing_if = "Option::is_none")]
pub user_id: Option<String>,
}
impl EventContext {
pub fn empty() -> Self {
Self::default()
}
pub fn with_job(job_id: Uuid) -> Self {
Self {
job_id: Some(job_id),
..Default::default()
}
}
pub fn with_thread(session_id: Uuid, thread_id: Uuid) -> Self {
Self {
session_id: Some(session_id),
thread_id: Some(thread_id),
..Default::default()
}
}
pub fn with_user(user_id: impl Into<String>) -> Self {
Self {
user_id: Some(user_id.into()),
..Default::default()
}
}
}
/// Telemetry payload for metrics events.
#[derive(Debug, Clone, Serialize)]
pub enum TelemetryPayload {
/// LLM call latency and token usage.
LlmCall {
provider: String,
model: String,
duration_ms: u64,
tokens_used: Option<u64>,
success: bool,
},
/// Channel message processed.
ChannelMessage { channel: String, direction: String },
/// Heartbeat tick.
HeartbeatTick,
}
/// The event-specific data carried inside a `SystemEvent`.
#[derive(Debug, Clone, Serialize)]
#[serde(tag = "kind")]
pub enum EventPayload {
/// Wraps an existing `DomainEvent` — SSE wire format unchanged.
Domain(crate::events::DomainEvent),
/// State invalidation notification (wraps existing `StateChange`).
StateChange(crate::state_bus::StateChange),
/// Telemetry / metrics data.
Telemetry(TelemetryPayload),
/// A validated state machine transition.
StateTransition {
entity_type: String,
entity_id: String,
from_state: String,
to_state: String,
#[serde(skip_serializing_if = "Option::is_none")]
reason: Option<String>,
},
/// Tool execution record.
ToolExecution {
tool_name: String,
/// SHA-256 prefix of parameters (not the raw params — privacy).
parameters_hash: String,
duration_ms: u64,
success: bool,
#[serde(skip_serializing_if = "Option::is_none")]
error: Option<String>,
},
/// Authentication / authorization event.
AuthEvent {
action: String,
target: String,
success: bool,
},
/// Configuration change.
ConfigChange { key: String, changed_by: String },
}
impl EventPayload {
/// Classify this payload into a category for sink routing.
pub fn default_category(&self) -> EventCategory {
match self {
Self::Domain(_) => EventCategory::Ephemeral,
Self::StateChange(_) => EventCategory::StateChange,
Self::Telemetry(_) => EventCategory::Metric,
Self::StateTransition { .. } => EventCategory::Audit,
Self::ToolExecution { .. } => EventCategory::Audit,
Self::AuthEvent { .. } => EventCategory::Audit,
Self::ConfigChange { .. } => EventCategory::Audit,
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn event_source_construction() {
let source = EventSource::new("agent", "dispatcher");
assert_eq!(source.module, "agent"); // safety: test-only
assert_eq!(source.component, "dispatcher"); // safety: test-only
}
#[test]
fn event_context_builders() {
let ctx = EventContext::empty();
assert!(ctx.session_id.is_none()); // safety: test-only
let job_id = Uuid::new_v4();
let ctx = EventContext::with_job(job_id);
assert_eq!(ctx.job_id, Some(job_id)); // safety: test-only
let sid = Uuid::new_v4();
let tid = Uuid::new_v4();
let ctx = EventContext::with_thread(sid, tid);
assert_eq!(ctx.session_id, Some(sid)); // safety: test-only
assert_eq!(ctx.thread_id, Some(tid)); // safety: test-only
let ctx = EventContext::with_user("alice");
assert_eq!(ctx.user_id.as_deref(), Some("alice")); // safety: test-only
}
#[test]
fn payload_default_categories() {
assert_eq!( // safety: test-only
EventPayload::Domain(crate::events::DomainEvent::Heartbeat).default_category(),
EventCategory::Ephemeral
);
assert_eq!( // safety: test-only
EventPayload::StateTransition {
entity_type: "thread".into(),
entity_id: "abc".into(),
from_state: "Idle".into(),
to_state: "Processing".into(),
reason: None,
}
.default_category(),
EventCategory::Audit
);
assert_eq!( // safety: test-only
EventPayload::Telemetry(TelemetryPayload::HeartbeatTick).default_category(),
EventCategory::Metric
);
}
}
+21
View File
@@ -0,0 +1,21 @@
//! Unified event bus — the single source of truth for system events.
//!
//! All producers (agent, tools, scheduler, channels) emit events through one
//! `EventBus`. Sinks subscribe and filter by category or payload type:
//!
//! - **SSE sink** → forwards `Domain` payloads to `SseManager` (web gateway)
//! - **Audit sink** → persists `Audit` events to the append-only audit log
//! - **State sink** → forwards `StateChange` payloads for cache invalidation
//! - **Metrics sink** → delegates `Metric`/`Telemetry` to `Observer` trait
//!
//! Hook events remain separate — hooks are bidirectional interceptors (can
//! reject/modify), the bus is unidirectional fire-and-forget.
pub mod bus;
pub mod event;
pub mod sinks;
pub use bus::EventBus;
pub use event::{
EventCategory, EventContext, EventPayload, EventSource, SystemEvent, TelemetryPayload,
};
+161
View File
@@ -0,0 +1,161 @@
//! Audit sink — persists `Audit`-category events to the append-only audit log.
//!
//! Batches events (up to 32, or 500ms timeout) before flushing to the database.
//! On DB failure, falls back to a local JSONL file so audit data is never lost.
use std::sync::Arc;
use std::time::Duration;
use tokio::sync::broadcast;
use crate::db::AuditStore;
use crate::event_bus::EventBus;
use crate::event_bus::event::{EventCategory, SystemEvent};
/// Maximum events to batch before flushing.
const BATCH_SIZE: usize = 32;
/// Maximum time to wait before flushing a partial batch.
const FLUSH_INTERVAL: Duration = Duration::from_millis(500);
/// Spawn the audit sink as a background task.
pub fn spawn(bus: &EventBus, store: Arc<dyn AuditStore>) -> tokio::task::JoinHandle<()> {
let mut rx = bus.subscribe();
tokio::spawn(async move {
let mut batch: Vec<Arc<SystemEvent>> = Vec::with_capacity(BATCH_SIZE);
let mut flush_timer = tokio::time::interval(FLUSH_INTERVAL);
// First tick completes immediately — skip it.
flush_timer.tick().await;
loop {
tokio::select! {
result = rx.recv() => {
match result {
Ok(event) => {
if event.category == EventCategory::Audit {
batch.push(event);
if batch.len() >= BATCH_SIZE {
flush_batch(&store, &mut batch).await;
}
}
}
Err(broadcast::error::RecvError::Lagged(n)) => {
tracing::warn!(skipped = n, "Audit sink lagged behind event bus");
}
Err(broadcast::error::RecvError::Closed) => {
// Flush remaining events before shutdown.
if !batch.is_empty() {
flush_batch(&store, &mut batch).await;
}
tracing::debug!("Event bus closed, audit sink shutting down");
break;
}
}
}
_ = flush_timer.tick() => {
if !batch.is_empty() {
flush_batch(&store, &mut batch).await;
}
}
}
}
})
}
async fn flush_batch(store: &Arc<dyn AuditStore>, batch: &mut Vec<Arc<SystemEvent>>) {
let records: Vec<crate::db::AuditRecord> = batch
.iter()
.map(|e| crate::db::AuditRecord {
event_id: e.id,
event_type: event_type_name(&e.payload),
source_module: e.source.module.clone(),
source_component: e.source.component.clone(),
category: format!("{:?}", e.category),
session_id: e.context.session_id,
thread_id: e.context.thread_id,
job_id: e.context.job_id,
user_id: e.context.user_id.clone(),
payload: serde_json::to_value(&e.payload).unwrap_or_default(),
created_at: e.timestamp,
})
.collect();
if let Err(e) = store.append_audit_events(&records).await {
tracing::error!(count = records.len(), error = %e, "Failed to persist audit events to DB, falling back to file");
fallback_to_file(&records);
}
batch.clear();
}
/// Extract a short event type name from the payload for indexing.
fn event_type_name(payload: &crate::event_bus::event::EventPayload) -> String {
use crate::event_bus::event::EventPayload;
match payload {
EventPayload::Domain(_) => "domain".to_string(),
EventPayload::StateChange(_) => "state_change".to_string(),
EventPayload::Telemetry(_) => "telemetry".to_string(),
EventPayload::StateTransition { .. } => "state_transition".to_string(),
EventPayload::ToolExecution { .. } => "tool_execution".to_string(),
EventPayload::AuthEvent { .. } => "auth_event".to_string(),
EventPayload::ConfigChange { .. } => "config_change".to_string(),
}
}
/// Fallback: append audit records as JSONL to a local file.
fn fallback_to_file(records: &[crate::db::AuditRecord]) {
let fallback_path = crate::bootstrap::ironclaw_base_dir().join("audit.fallback.jsonl");
let file = match std::fs::OpenOptions::new()
.create(true)
.append(true)
.open(&fallback_path)
{
Ok(f) => f,
Err(e) => {
tracing::error!(path = %fallback_path.display(), error = %e, "Cannot open audit fallback file");
return;
}
};
let mut writer = std::io::BufWriter::new(file);
for record in records {
if let Err(e) = serde_json::to_writer(&mut writer, record) {
tracing::error!(error = %e, "Failed to write audit record to fallback file");
} else {
use std::io::Write;
let _ = writer.write_all(b"\n");
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn event_type_names() {
use crate::event_bus::event::EventPayload;
assert_eq!( // safety: test-only
event_type_name(&EventPayload::StateTransition {
entity_type: "t".into(),
entity_id: "i".into(),
from_state: "a".into(),
to_state: "b".into(),
reason: None,
}),
"state_transition"
);
assert_eq!( // safety: test-only
event_type_name(&EventPayload::ToolExecution {
tool_name: "echo".into(),
parameters_hash: "abc".into(),
duration_ms: 10,
success: true,
error: None,
}),
"tool_execution"
);
}
}
+132
View File
@@ -0,0 +1,132 @@
//! Metrics sink — filters `Telemetry`/`Metric` events and delegates to `Observer`.
//!
//! Bridges the unified event bus to the existing `Observer` trait so that
//! `LogObserver`, future OpenTelemetry exporters, etc. continue to work.
use std::sync::Arc;
use std::time::Duration;
use tokio::sync::broadcast;
use crate::event_bus::EventBus;
use crate::event_bus::event::{EventCategory, EventPayload, SystemEvent, TelemetryPayload};
use crate::observability::traits::{Observer, ObserverEvent};
/// Spawn the metrics sink as a background task.
pub fn spawn(bus: &EventBus, observer: Arc<dyn Observer>) -> tokio::task::JoinHandle<()> {
let mut rx = bus.subscribe();
tokio::spawn(async move {
loop {
match rx.recv().await {
Ok(event) => forward_if_metric(&event, &observer),
Err(broadcast::error::RecvError::Lagged(n)) => {
tracing::warn!(skipped = n, "Metrics sink lagged behind event bus");
}
Err(broadcast::error::RecvError::Closed) => {
tracing::debug!("Event bus closed, metrics sink shutting down");
break;
}
}
}
})
}
fn forward_if_metric(event: &Arc<SystemEvent>, observer: &Arc<dyn Observer>) {
if event.category != EventCategory::Metric {
return;
}
if let EventPayload::Telemetry(ref telemetry) = event.payload {
match telemetry {
TelemetryPayload::LlmCall {
provider,
model,
duration_ms,
success,
..
} => {
observer.record_event(&ObserverEvent::LlmResponse {
provider: provider.clone(),
model: model.clone(),
duration: Duration::from_millis(*duration_ms),
success: *success,
error_message: None,
});
}
TelemetryPayload::ChannelMessage { channel, direction } => {
observer.record_event(&ObserverEvent::ChannelMessage {
channel: channel.clone(),
direction: direction.clone(),
});
}
TelemetryPayload::HeartbeatTick => {
observer.record_event(&ObserverEvent::HeartbeatTick);
}
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::event_bus::event::{EventContext, EventSource};
use crate::observability::traits::ObserverMetric;
use std::sync::Mutex;
struct RecordingObserver {
events: Mutex<Vec<String>>,
}
impl RecordingObserver {
fn new() -> Self {
Self {
events: Mutex::new(Vec::new()),
}
}
fn recorded(&self) -> Vec<String> {
self.events.lock().expect("test lock").clone() // safety: test-only
}
}
impl Observer for RecordingObserver {
fn record_event(&self, event: &ObserverEvent) {
let name = match event {
ObserverEvent::LlmResponse { .. } => "llm_response",
ObserverEvent::ChannelMessage { .. } => "channel_message",
ObserverEvent::HeartbeatTick => "heartbeat_tick",
_ => "other",
};
self.events
.lock()
.expect("test lock") // safety: test-only
.push(name.to_string());
}
fn record_metric(&self, _metric: &ObserverMetric) {}
fn name(&self) -> &str {
"test-recorder"
}
}
#[tokio::test]
async fn forwards_telemetry_to_observer() {
let bus = EventBus::new();
let observer = Arc::new(RecordingObserver::new());
let _handle = spawn(&bus, Arc::clone(&observer) as Arc<dyn Observer>);
bus.emit_telemetry(
EventSource::new("test", "metrics"),
EventContext::empty(),
TelemetryPayload::HeartbeatTick,
);
// Give the sink a moment to process
tokio::time::sleep(std::time::Duration::from_millis(50)).await;
let recorded = observer.recorded();
assert_eq!(recorded, vec!["heartbeat_tick"]); // safety: test-only
}
}
+48
View File
@@ -0,0 +1,48 @@
//! Event bus sinks — subscribers that consume events by category.
//!
//! Each sink runs as a background task, filtering events and routing
//! them to the appropriate subsystem.
pub mod audit_sink;
pub mod metrics_sink;
pub mod sse_sink;
pub mod state_sink;
use std::sync::Arc;
use crate::event_bus::EventBus;
/// Spawn all configured sinks as background tasks.
///
/// Returns `JoinHandle`s so the caller can abort them on shutdown.
pub fn spawn_sinks(
bus: &EventBus,
sse_tx: Option<tokio::sync::broadcast::Sender<crate::events::DomainEvent>>,
state_bus: Option<Arc<crate::state_bus::StateBus>>,
observer: Option<Arc<dyn crate::observability::Observer>>,
audit_store: Option<Arc<dyn crate::db::AuditStore>>,
) -> Vec<tokio::task::JoinHandle<()>> {
let mut handles = Vec::new();
// SSE sink — bridges Domain events to the web gateway
if let Some(tx) = sse_tx {
handles.push(sse_sink::spawn(bus, tx));
}
// State sink — bridges StateChange events to the StateBus
if let Some(sb) = state_bus {
handles.push(state_sink::spawn(bus, sb));
}
// Metrics sink — bridges Telemetry/Metric events to Observer
if let Some(obs) = observer {
handles.push(metrics_sink::spawn(bus, obs));
}
// Audit sink — persists Audit events to the database
if let Some(store) = audit_store {
handles.push(audit_sink::spawn(bus, store));
}
handles
}
+96
View File
@@ -0,0 +1,96 @@
//! SSE sink — filters `Domain` payloads and forwards to `SseManager`.
//!
//! Drop-in replacement for direct `sse_tx.send()` calls. The web gateway's
//! SSE wire format is unchanged because `DomainEvent` serialization is
//! identical.
use std::sync::Arc;
use tokio::sync::broadcast;
use crate::event_bus::EventBus;
use crate::event_bus::event::{EventPayload, SystemEvent};
use crate::events::DomainEvent;
/// Spawn the SSE sink as a background task.
pub fn spawn(
bus: &EventBus,
sse_tx: broadcast::Sender<DomainEvent>,
) -> tokio::task::JoinHandle<()> {
let mut rx = bus.subscribe();
tokio::spawn(async move {
loop {
match rx.recv().await {
Ok(event) => forward_if_domain(&event, &sse_tx),
Err(broadcast::error::RecvError::Lagged(n)) => {
tracing::warn!(skipped = n, "SSE sink lagged behind event bus");
}
Err(broadcast::error::RecvError::Closed) => {
tracing::debug!("Event bus closed, SSE sink shutting down");
break;
}
}
}
})
}
fn forward_if_domain(event: &Arc<SystemEvent>, sse_tx: &broadcast::Sender<DomainEvent>) {
if let EventPayload::Domain(ref domain_event) = event.payload {
// Ignore send error — no SSE subscribers is fine.
let _ = sse_tx.send(domain_event.clone());
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::event_bus::event::{EventContext, EventSource};
#[tokio::test]
async fn forwards_domain_events() {
let bus = EventBus::new();
let (sse_tx, mut sse_rx) = broadcast::channel::<DomainEvent>(16);
let _handle = spawn(&bus, sse_tx);
bus.emit_domain(
EventSource::new("test", "sse"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
let received = tokio::time::timeout(std::time::Duration::from_millis(100), sse_rx.recv())
.await
.expect("should receive within timeout") // safety: test-only
.expect("should not error"); // safety: test-only
assert!(matches!(received, DomainEvent::Heartbeat)); // safety: test-only
}
#[tokio::test]
async fn ignores_non_domain_events() {
let bus = EventBus::new();
let (sse_tx, mut sse_rx) = broadcast::channel::<DomainEvent>(16);
let _handle = spawn(&bus, sse_tx);
// Emit a non-domain event
bus.emit_state_change(crate::state_bus::StateChange::ConfigReloaded);
// Then emit a domain event so we know the sink is running
bus.emit_domain(
EventSource::new("test", "sse"),
EventContext::empty(),
DomainEvent::Heartbeat,
);
let received = tokio::time::timeout(std::time::Duration::from_millis(100), sse_rx.recv())
.await
.expect("should receive within timeout") // safety: test-only
.expect("should not error"); // safety: test-only
// Only the Heartbeat should arrive, not the StateChange
assert!(matches!(received, DomainEvent::Heartbeat)); // safety: test-only
}
}
+63
View File
@@ -0,0 +1,63 @@
//! State sink — filters `StateChange` payloads and forwards to `StateBus`.
//!
//! Replaces direct `StateBus::publish()` calls. Modules that need state
//! invalidation subscribe to the `StateBus` as before — the sink bridges
//! the unified event bus to the existing invalidation mechanism.
use std::sync::Arc;
use tokio::sync::broadcast;
use crate::event_bus::EventBus;
use crate::event_bus::event::{EventPayload, SystemEvent};
use crate::state_bus::StateBus;
/// Spawn the state sink as a background task.
pub fn spawn(bus: &EventBus, state_bus: Arc<StateBus>) -> tokio::task::JoinHandle<()> {
let mut rx = bus.subscribe();
tokio::spawn(async move {
loop {
match rx.recv().await {
Ok(event) => forward_if_state_change(&event, &state_bus),
Err(broadcast::error::RecvError::Lagged(n)) => {
tracing::warn!(skipped = n, "State sink lagged behind event bus");
}
Err(broadcast::error::RecvError::Closed) => {
tracing::debug!("Event bus closed, state sink shutting down");
break;
}
}
}
})
}
fn forward_if_state_change(event: &Arc<SystemEvent>, state_bus: &StateBus) {
if let EventPayload::StateChange(ref change) = event.payload {
state_bus.publish(change.clone());
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::state_bus::StateChange;
#[tokio::test]
async fn forwards_state_changes() {
let bus = EventBus::new();
let state_bus = Arc::new(StateBus::new());
let mut state_rx = state_bus.subscribe();
let _handle = spawn(&bus, Arc::clone(&state_bus));
bus.emit_state_change(StateChange::ConfigReloaded);
let received = tokio::time::timeout(std::time::Duration::from_millis(100), state_rx.recv())
.await
.expect("should receive within timeout") // safety: test-only
.expect("should not error"); // safety: test-only
assert!(matches!(received, StateChange::ConfigReloaded)); // safety: test-only
}
}
+159
View File
@@ -0,0 +1,159 @@
//! Domain events for cross-module communication.
//!
//! `DomainEvent` is the canonical event type published by the agent, scheduler,
//! and other core modules. Channel-specific code (web gateway, CLI, etc.)
//! subscribes and maps these to its wire format.
//!
//! By living in `src/events.rs` rather than `channels::web::types`, these events
//! can be used by any module without creating a dependency on a specific channel.
use serde::Serialize;
/// Domain events emitted by the agent and related subsystems.
///
/// The `#[serde(tag = "type")]` attribute ensures each variant serializes with
/// a `"type"` discriminator field, matching the SSE wire format expected by
/// the web gateway.
#[derive(Debug, Clone, Serialize)]
#[serde(tag = "type")]
pub enum DomainEvent {
#[serde(rename = "response")]
Response { content: String, thread_id: String },
#[serde(rename = "thinking")]
Thinking {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_started")]
ToolStarted {
name: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_completed")]
ToolCompleted {
name: String,
success: bool,
#[serde(skip_serializing_if = "Option::is_none")]
error: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
parameters: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "tool_result")]
ToolResult {
name: String,
preview: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "stream_chunk")]
StreamChunk {
content: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "status")]
Status {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "job_started")]
JobStarted {
job_id: String,
title: String,
browse_url: String,
},
#[serde(rename = "approval_needed")]
ApprovalNeeded {
request_id: String,
tool_name: String,
description: String,
parameters: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "auth_required")]
AuthRequired {
extension_name: String,
#[serde(skip_serializing_if = "Option::is_none")]
instructions: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
auth_url: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
setup_url: Option<String>,
},
#[serde(rename = "auth_completed")]
AuthCompleted {
extension_name: String,
success: bool,
message: String,
},
#[serde(rename = "error")]
Error {
message: String,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
#[serde(rename = "heartbeat")]
Heartbeat,
// Sandbox job streaming events (worker + Claude Code bridge)
#[serde(rename = "job_message")]
JobMessage {
job_id: String,
role: String,
content: String,
},
#[serde(rename = "job_tool_use")]
JobToolUse {
job_id: String,
tool_name: String,
input: serde_json::Value,
},
#[serde(rename = "job_tool_result")]
JobToolResult {
job_id: String,
tool_name: String,
output: String,
},
#[serde(rename = "job_status")]
JobStatus { job_id: String, message: String },
#[serde(rename = "job_result")]
JobResult {
job_id: String,
status: String,
#[serde(skip_serializing_if = "Option::is_none")]
session_id: Option<String>,
},
/// An image was generated by a tool.
#[serde(rename = "image_generated")]
ImageGenerated {
data_url: String,
#[serde(skip_serializing_if = "Option::is_none")]
path: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
/// Suggested follow-up messages for the user.
#[serde(rename = "suggestions")]
Suggestions {
suggestions: Vec<String>,
#[serde(skip_serializing_if = "Option::is_none")]
thread_id: Option<String>,
},
/// Extension activation status change (WASM channels).
#[serde(rename = "extension_status")]
ExtensionStatus {
extension_name: String,
status: String,
#[serde(skip_serializing_if = "Option::is_none")]
message: Option<String>,
},
}
+68 -1567
View File
File diff suppressed because it is too large Load Diff
-13
View File
@@ -453,17 +453,6 @@ pub struct ActivateResult {
///
/// Returned by `ExtensionManager::configure()`, the single entrypoint
/// for providing secrets to any extension (chat auth, gateway setup, etc.).
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct VerificationChallenge {
/// One-time code the user must send back to the integration.
pub code: String,
/// Human-readable instructions for completing verification.
pub instructions: String,
/// Deep-link or shortcut URL that prefills the verification payload when supported.
#[serde(skip_serializing_if = "Option::is_none")]
pub deep_link: Option<String>,
}
#[derive(Debug, Clone)]
pub struct ConfigureResult {
/// Human-readable status message.
@@ -472,8 +461,6 @@ pub struct ConfigureResult {
pub activated: bool,
/// OAuth authorization URL (if OAuth flow was started).
pub auth_url: Option<String>,
/// Pending manual verification challenge (for Telegram owner binding, etc.).
pub verification: Option<VerificationChallenge>,
}
fn default_true() -> bool {
-1
View File
@@ -227,7 +227,6 @@ impl Store {
job_id: row.get("id"),
state,
user_id: row.get::<_, String>("user_id"),
requester_id: None,
conversation_id: row.get("conversation_id"),
title: row.get("title"),
description: row.get("description"),
+5
View File
@@ -51,16 +51,20 @@ pub mod document_extraction;
pub mod error;
pub mod estimation;
pub mod evaluation;
pub mod event_bus;
pub mod events;
pub mod extensions;
pub mod history;
pub mod hooks;
#[cfg(feature = "import")]
pub mod import;
pub mod llm;
pub mod models;
pub mod observability;
pub mod orchestrator;
pub mod pairing;
pub mod registry;
pub mod resilience;
pub mod safety;
pub mod sandbox;
pub mod secrets;
@@ -68,6 +72,7 @@ pub mod service;
pub mod settings;
pub mod setup;
pub mod skills;
pub mod state_bus;
pub mod timezone;
pub mod tools;
pub mod tracing_fmt;
-10
View File
@@ -7,12 +7,8 @@ Multi-provider LLM integration with circuit breaker, retry, failover, and respon
| File | Role |
|------|------|
| `mod.rs` | Provider factory (`create_llm_provider`, `build_provider_chain`); `LlmBackend` enum |
| `config.rs` | LLM config types (`LlmConfig`, `RegistryProviderConfig`, `NearAiConfig`, `BedrockConfig`) |
| `error.rs` | `LlmError` enum used by all providers |
| `provider.rs` | `LlmProvider` trait, `ChatMessage`, `ToolCall`, `CompletionRequest`, `sanitize_tool_messages` |
| `nearai_chat.rs` | NEAR AI Chat Completions provider (dual auth: session token or API key) |
| `codex_auth.rs` | Reads Codex CLI `auth.json`, extracts tokens, refreshes ChatGPT OAuth access tokens |
| `codex_chatgpt.rs` | Custom Responses API provider for Codex ChatGPT backend (`/backend-api/codex`) |
| `reasoning.rs` | `Reasoning` struct, `ReasoningContext`, `RespondResult`, `ActionPlan`, `ToolSelection`; thinking-tag stripping; `SILENT_REPLY_TOKEN` |
| `session.rs` | NEAR AI session token management with disk + DB persistence, OAuth login flow |
| `circuit_breaker.rs` | Circuit breaker: Closed → Open → HalfOpen state machine |
@@ -39,12 +35,6 @@ Set via `LLM_BACKEND` env var:
| `tinfoil` | Tinfoil TEE inference | `TINFOIL_API_KEY`, `TINFOIL_MODEL` |
| `bedrock` | AWS Bedrock (requires `--features bedrock`) | `BEDROCK_REGION`, `BEDROCK_MODEL`, `AWS_PROFILE` |
Codex auth reuse:
- Set `LLM_USE_CODEX_AUTH=true` to load credentials from `~/.codex/auth.json` (override with `CODEX_AUTH_PATH`).
- If Codex is logged in with API-key mode, IronClaw uses the standard OpenAI endpoint.
- If Codex is logged in with ChatGPT OAuth mode, IronClaw routes to the private `chatgpt.com/backend-api/codex` Responses API via `codex_chatgpt.rs`.
- ChatGPT mode supports one automatic 401 refresh using the refresh token persisted in `auth.json`.
## AWS Bedrock Provider
Uses the native Converse API via `aws-sdk-bedrockruntime` (`bedrock.rs`). Requires `--features bedrock` at build time — not in default features due to heavy AWS SDK dependencies.
+4 -126
View File
@@ -34,9 +34,7 @@ const DEFAULT_MAX_TOKENS: u32 = 8192;
/// Anthropic provider using OAuth Bearer authentication.
pub struct AnthropicOAuthProvider {
client: Client,
/// OAuth token, wrapped in RwLock so it can be updated after a successful
/// Keychain refresh (fixes #1136: stale token reuse after expiry).
token: std::sync::RwLock<SecretString>,
token: SecretString,
model: String,
base_url: Option<String>,
active_model: std::sync::RwLock<String>,
@@ -73,7 +71,7 @@ impl AnthropicOAuthProvider {
Ok(Self {
client,
token: std::sync::RwLock::new(token),
token,
model: config.model.clone(),
base_url,
active_model,
@@ -100,22 +98,6 @@ impl AnthropicOAuthProvider {
}
}
/// Read the current token from the RwLock.
fn current_token(&self) -> String {
match self.token.read() {
Ok(guard) => guard.expose_secret().to_string(),
Err(poisoned) => poisoned.into_inner().expose_secret().to_string(),
}
}
/// Update the stored token after a successful Keychain refresh.
fn update_token(&self, new_token: SecretString) {
match self.token.write() {
Ok(mut guard) => *guard = new_token,
Err(poisoned) => *poisoned.into_inner() = new_token,
}
}
async fn send_request<R: for<'de> Deserialize<'de>>(
&self,
body: &AnthropicRequest,
@@ -127,7 +109,7 @@ impl AnthropicOAuthProvider {
let response = self
.client
.post(&url)
.bearer_auth(self.current_token())
.bearer_auth(self.token.expose_secret())
.header("anthropic-version", ANTHROPIC_API_VERSION)
.header("anthropic-beta", ANTHROPIC_OAUTH_BETA)
.header("Content-Type", "application/json")
@@ -143,14 +125,12 @@ impl AnthropicOAuthProvider {
if !status.is_success() {
// Parse Retry-After header before consuming the body.
// Falls back to 60s if header is missing or unparseable (prevents "retry after None" errors).
let retry_after = response
.headers()
.get("retry-after")
.and_then(|v| v.to_str().ok())
.and_then(|v| v.parse::<u64>().ok())
.map(std::time::Duration::from_secs)
.or(Some(std::time::Duration::from_secs(60)));
.map(std::time::Duration::from_secs);
let response_text = response
.text()
@@ -161,11 +141,6 @@ impl AnthropicOAuthProvider {
// OAuth tokens from `claude login` expire in ~8-12h. Attempt
// to re-extract a fresh token from the OS credential store
// (macOS Keychain / Linux credentials file) before giving up.
//
// Brief delay to give Claude Code time to complete its async
// Keychain refresh write (fixes race in #1136).
tokio::time::sleep(std::time::Duration::from_millis(500)).await;
if let Some(fresh) = crate::config::ClaudeCodeConfig::extract_oauth_token() {
let fresh_token = SecretString::from(fresh);
// Retry once with the refreshed token
@@ -184,11 +159,6 @@ impl AnthropicOAuthProvider {
reason: e.to_string(),
})?;
if retry.status().is_success() {
// Persist the refreshed token so subsequent requests
// don't hit 401 again (fixes #1136).
self.update_token(fresh_token);
tracing::info!("Anthropic OAuth token refreshed from credential store");
let text = retry.text().await.map_err(|e| LlmError::RequestFailed {
provider: "anthropic_oauth".to_string(),
reason: format!("Failed to read response body: {}", e),
@@ -689,96 +659,4 @@ mod tests {
assert_eq!(tool_calls.len(), 1);
assert_eq!(tool_calls[0].name, "search");
}
/// Regression test for #1136: token field must be mutable via RwLock
/// so that a refreshed token persists across subsequent requests.
#[test]
fn test_token_update_persists() {
let original = SecretString::from("old_token".to_string());
let token = std::sync::RwLock::new(original);
// Read the original
assert_eq!(token.read().unwrap().expose_secret(), "old_token");
// Simulate a successful refresh
let refreshed = SecretString::from("new_token".to_string());
*token.write().unwrap() = refreshed;
// Subsequent reads see the updated token
assert_eq!(token.read().unwrap().expose_secret(), "new_token");
}
// -- Retry-After header parsing tests (regression for rate limit "None" bug) --
#[test]
fn test_retry_after_parsing_delay_seconds() {
// Verify delay-seconds format is parsed correctly
let header_value = "45";
let duration = parse_retry_after_anthropic_for_test(header_value);
assert_eq!(
duration,
Some(std::time::Duration::from_secs(45)),
"Should parse delay-seconds format"
);
}
#[test]
fn test_retry_after_fallback_missing_header() {
// Regression test: When Retry-After header is missing,
// should fall back to 60s instead of None
let duration = parse_retry_after_anthropic_for_test("");
assert_eq!(
duration,
Some(std::time::Duration::from_secs(60)),
"Missing header should fallback to 60s"
);
}
#[test]
fn test_retry_after_fallback_invalid_format() {
// Regression test: When Retry-After header is in unexpected format,
// should fall back to 60s instead of None
let invalid_formats = vec![
"invalid",
"not-a-number",
"30.5", // float instead of int
"abc123",
"Mon, 02 Mar 2026 18:00:00 GMT", // RFC2822 not supported in anthropic version
];
for format in invalid_formats {
let duration = parse_retry_after_anthropic_for_test(format);
assert_eq!(
duration,
Some(std::time::Duration::from_secs(60)),
"Invalid format '{}' should fallback to 60s",
format
);
}
}
#[test]
fn test_retry_after_zero_seconds_accepted() {
// Verify zero seconds is a valid retry delay
let duration = parse_retry_after_anthropic_for_test("0");
assert_eq!(duration, Some(std::time::Duration::ZERO));
}
#[test]
fn test_retry_after_large_number() {
// Verify large numbers are accepted
let duration = parse_retry_after_anthropic_for_test("7200"); // 2 hours
assert_eq!(duration, Some(std::time::Duration::from_secs(7200)));
}
/// Helper function to test Retry-After header parsing logic for Anthropic
/// (simulates the parsing done in send_request without actual HTTP, including fallback)
fn parse_retry_after_anthropic_for_test(header_value: &str) -> Option<std::time::Duration> {
header_value
.trim()
.parse::<u64>()
.ok()
.map(std::time::Duration::from_secs)
.or(Some(std::time::Duration::from_secs(60)))
}
}
-377
View File
@@ -1,377 +0,0 @@
//! Read Codex CLI credentials for LLM authentication.
//!
//! When `LLM_USE_CODEX_AUTH=true`, IronClaw reads the Codex CLI's
//! `auth.json` file (default: `~/.codex/auth.json`) and extracts
//! credentials. This lets IronClaw piggyback on a Codex login without
//! implementing its own OAuth flow.
//!
//! Codex supports two auth modes:
//! - **API key** (`auth_mode: "apiKey"`) → uses `OPENAI_API_KEY` field
//! against `api.openai.com/v1`.
//! - **ChatGPT** (`auth_mode: "chatgpt"`) → uses `tokens.access_token`
//! (OAuth JWT) against `chatgpt.com/backend-api/codex`.
//!
//! When in ChatGPT mode, the provider supports automatic token refresh
//! on 401 responses using the `refresh_token` from `auth.json`.
use std::path::{Path, PathBuf};
use secrecy::{ExposeSecret, SecretString};
use serde::{Deserialize, Serialize};
/// ChatGPT backend API endpoint used by Codex in ChatGPT auth mode.
const CHATGPT_BACKEND_URL: &str = "https://chatgpt.com/backend-api/codex";
/// Standard OpenAI API endpoint used by Codex in API key mode.
const OPENAI_API_URL: &str = "https://api.openai.com/v1";
/// OAuth token refresh endpoint (same as Codex CLI).
const REFRESH_TOKEN_URL: &str = "https://auth.openai.com/oauth/token";
/// OAuth client ID used for token refresh (same as Codex CLI).
const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
/// Credentials extracted from Codex's `auth.json`.
#[derive(Debug, Clone)]
pub struct CodexCredentials {
/// The bearer token (API key or ChatGPT access_token).
pub token: SecretString,
/// Whether this is a ChatGPT OAuth token (vs. an OpenAI API key).
pub is_chatgpt_mode: bool,
/// OAuth refresh token (only present in ChatGPT mode).
pub refresh_token: Option<SecretString>,
/// Path to the auth.json file (for persisting refreshed tokens).
pub auth_path: Option<PathBuf>,
}
impl CodexCredentials {
/// Returns the correct base URL for the auth mode.
///
/// - ChatGPT mode → `https://chatgpt.com/backend-api/codex`
/// - API key mode → `https://api.openai.com/v1`
pub fn base_url(&self) -> &'static str {
if self.is_chatgpt_mode {
CHATGPT_BACKEND_URL
} else {
OPENAI_API_URL
}
}
}
/// Partial representation of Codex's `$CODEX_HOME/auth.json`.
#[derive(Debug, Deserialize)]
struct CodexAuthJson {
auth_mode: Option<String>,
#[serde(rename = "OPENAI_API_KEY")]
openai_api_key: Option<String>,
tokens: Option<CodexTokens>,
}
#[derive(Debug, Deserialize)]
struct CodexTokens {
access_token: SecretString,
refresh_token: Option<SecretString>,
}
/// Request body for OAuth token refresh.
#[derive(Serialize)]
struct RefreshRequest<'a> {
client_id: &'a str,
grant_type: &'a str,
refresh_token: &'a str,
}
/// Response from the OAuth token refresh endpoint.
#[derive(Debug, Deserialize)]
struct RefreshResponse {
access_token: SecretString,
refresh_token: Option<SecretString>,
}
/// Default path used by Codex CLI: `~/.codex/auth.json`.
pub fn default_codex_auth_path() -> PathBuf {
let home_dir = dirs::home_dir().unwrap_or_else(|| {
tracing::warn!(
"Could not determine home directory; falling back to current working directory for Codex auth.json path"
);
PathBuf::from(".")
});
home_dir.join(".codex").join("auth.json")
}
/// Load credentials from a Codex `auth.json` file.
///
/// Returns `None` if the file is missing, unreadable, or contains
/// no usable credentials.
pub fn load_codex_credentials(path: &Path) -> Option<CodexCredentials> {
let content = match std::fs::read_to_string(path) {
Ok(c) => c,
Err(e) => {
tracing::debug!("Could not read Codex auth file {}: {}", path.display(), e);
return None;
}
};
let auth: CodexAuthJson = match serde_json::from_str(&content) {
Ok(a) => a,
Err(e) => {
tracing::warn!("Failed to parse Codex auth file {}: {}", path.display(), e);
return None;
}
};
let is_chatgpt = auth
.auth_mode
.as_deref()
.map(|m| m == "chatgpt" || m == "chatgptAuthTokens")
.unwrap_or(false);
// API key mode: use OPENAI_API_KEY field.
if !is_chatgpt {
if let Some(key) = auth.openai_api_key.filter(|k| !k.is_empty()) {
tracing::info!("Loaded API key from Codex auth.json (API key mode)");
return Some(CodexCredentials {
token: SecretString::from(key),
is_chatgpt_mode: false,
refresh_token: None,
auth_path: None,
});
}
// If auth_mode was explicitly `apiKey`, do not fall back to checking for a token.
if auth.auth_mode.is_some() {
return None;
}
}
// ChatGPT mode: use access_token as bearer token.
if let Some(tokens) = auth.tokens
&& !tokens.access_token.expose_secret().is_empty()
{
tracing::info!(
"Loaded access token from Codex auth.json (ChatGPT mode, base_url={})",
CHATGPT_BACKEND_URL
);
return Some(CodexCredentials {
token: tokens.access_token,
is_chatgpt_mode: true,
refresh_token: tokens.refresh_token,
auth_path: Some(path.to_path_buf()),
});
}
tracing::debug!(
"Codex auth.json at {} contains no usable credentials",
path.display()
);
None
}
/// Attempt to refresh an expired access token using the refresh token.
///
/// On success, returns the new `access_token` and persists the refreshed
/// tokens back to `auth.json`. This follows the same OAuth protocol as
/// Codex CLI (`POST https://auth.openai.com/oauth/token`).
///
/// Returns `None` if the refresh token is missing, the request fails,
/// or the response is malformed.
pub async fn refresh_access_token(
client: &reqwest::Client,
refresh_token: &SecretString,
auth_path: Option<&Path>,
) -> Option<SecretString> {
let req = RefreshRequest {
client_id: CLIENT_ID,
grant_type: "refresh_token",
refresh_token: refresh_token.expose_secret(),
};
tracing::info!("Attempting to refresh Codex OAuth access token");
let resp = match client
.post(REFRESH_TOKEN_URL)
.header("Content-Type", "application/json")
.json(&req)
.timeout(std::time::Duration::from_secs(10))
.send()
.await
{
Ok(r) => r,
Err(e) => {
tracing::warn!("Token refresh request failed: {e}");
return None;
}
};
if !resp.status().is_success() {
let status = resp.status();
let body = resp.text().await.unwrap_or_default();
tracing::warn!("Token refresh failed: HTTP {status}: {body}");
if status.as_u16() == 401 {
tracing::warn!(
"Refresh token may be expired or revoked. \
Please re-authenticate with: codex --login"
);
}
return None;
}
let refresh_resp: RefreshResponse = match resp.json().await {
Ok(r) => r,
Err(e) => {
tracing::warn!("Failed to parse token refresh response: {e}");
return None;
}
};
let new_access_token = refresh_resp.access_token.clone();
// Persist refreshed tokens back to auth.json
if let Some(path) = auth_path {
if let Err(e) = persist_refreshed_tokens(
path,
refresh_resp.access_token.expose_secret(),
refresh_resp
.refresh_token
.as_ref()
.map(ExposeSecret::expose_secret),
) {
tracing::warn!(
"Failed to persist refreshed tokens to {}: {e}",
path.display()
);
} else {
tracing::info!("Refreshed tokens persisted to {}", path.display());
}
}
Some(new_access_token)
}
/// Update `auth.json` with refreshed tokens, preserving other fields.
fn persist_refreshed_tokens(
path: &Path,
new_access_token: &str,
new_refresh_token: Option<&str>,
) -> Result<(), Box<dyn std::error::Error>> {
let content = std::fs::read_to_string(path)?;
let mut json: serde_json::Value = serde_json::from_str(&content)?;
if let Some(tokens) = json.get_mut("tokens") {
tokens["access_token"] = serde_json::Value::String(new_access_token.to_string());
if let Some(rt) = new_refresh_token {
tokens["refresh_token"] = serde_json::Value::String(rt.to_string());
}
}
let updated = serde_json::to_string_pretty(&json)?;
let tmp_path = path.with_extension("json.tmp");
std::fs::write(&tmp_path, updated)?;
if let Err(e) = std::fs::rename(&tmp_path, path) {
let _ = std::fs::remove_file(&tmp_path);
return Err(Box::new(e));
}
set_auth_file_permissions(path)?;
Ok(())
}
#[cfg(unix)]
fn set_auth_file_permissions(path: &Path) -> Result<(), Box<dyn std::error::Error>> {
use std::os::unix::fs::PermissionsExt;
std::fs::set_permissions(path, std::fs::Permissions::from_mode(0o600))?;
Ok(())
}
#[cfg(not(unix))]
fn set_auth_file_permissions(_path: &Path) -> Result<(), Box<dyn std::error::Error>> {
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
use std::io::Write;
use tempfile::NamedTempFile;
#[test]
fn loads_api_key_mode() {
let mut f = NamedTempFile::new().unwrap();
writeln!(
f,
r#"{{"auth_mode":"apiKey","OPENAI_API_KEY":"sk-test-123"}}"#
)
.unwrap();
let creds = load_codex_credentials(f.path()).expect("should load");
assert_eq!(creds.token.expose_secret(), "sk-test-123");
assert!(!creds.is_chatgpt_mode);
assert_eq!(creds.base_url(), OPENAI_API_URL);
}
#[test]
fn loads_chatgpt_mode() {
let mut f = NamedTempFile::new().unwrap();
writeln!(
f,
r#"{{"auth_mode":"chatgpt","tokens":{{"id_token":{{}},"access_token":"eyJ-test","refresh_token":"rt-x"}}}}"#
)
.unwrap();
let creds = load_codex_credentials(f.path()).expect("should load");
assert_eq!(creds.token.expose_secret(), "eyJ-test");
assert!(creds.is_chatgpt_mode);
assert_eq!(
creds
.refresh_token
.as_ref()
.expect("refresh token should be present")
.expose_secret(),
"rt-x"
);
assert_eq!(creds.base_url(), CHATGPT_BACKEND_URL);
}
#[test]
fn api_key_mode_ignores_tokens() {
let mut f = NamedTempFile::new().unwrap();
writeln!(
f,
r#"{{"auth_mode":"apiKey","OPENAI_API_KEY":"sk-priority","tokens":{{"id_token":{{}},"access_token":"eyJ-fallback","refresh_token":"rt-x"}}}}"#
)
.unwrap();
let creds = load_codex_credentials(f.path()).expect("should load");
assert_eq!(creds.token.expose_secret(), "sk-priority");
assert!(!creds.is_chatgpt_mode);
}
#[test]
fn returns_none_for_missing_file() {
assert!(load_codex_credentials(Path::new("/tmp/nonexistent_codex_auth.json")).is_none());
}
#[test]
fn returns_none_for_empty_json() {
let mut f = NamedTempFile::new().unwrap();
writeln!(f, "{{}}").unwrap();
assert!(load_codex_credentials(f.path()).is_none());
}
#[test]
fn returns_none_for_empty_key() {
let mut f = NamedTempFile::new().unwrap();
writeln!(f, r#"{{"auth_mode":"apiKey","OPENAI_API_KEY":""}}"#).unwrap();
assert!(load_codex_credentials(f.path()).is_none());
}
#[test]
fn api_key_mode_missing_key_does_not_fallback_to_chatgpt() {
// Bug: if auth_mode is "apiKey" but key is missing, the old code would
// fall through to check for a ChatGPT token, returning is_chatgpt_mode: true.
let mut f = NamedTempFile::new().unwrap();
writeln!(
f,
r#"{{"auth_mode":"apiKey","OPENAI_API_KEY":"","tokens":{{"id_token":{{}},"access_token":"eyJ-bad","refresh_token":"rt-x"}}}}"#
)
.unwrap();
assert!(load_codex_credentials(f.path()).is_none());
}
}
-932
View File
@@ -1,932 +0,0 @@
//! Codex ChatGPT Responses API provider.
//!
//! Implements `LlmProvider` by speaking the OpenAI Responses API protocol
//! (`POST /responses`) used by the ChatGPT backend at
//! `chatgpt.com/backend-api/codex`. This bypasses `rig-core`'s Chat
//! Completions path, which is incompatible with this endpoint.
//!
//! # Warning
//!
//! The ChatGPT backend endpoint (`chatgpt.com/backend-api/codex`) is a
//! **private, undocumented API**. Using subscriber OAuth tokens from a
//! third-party application may violate the token's intended scope or
//! OpenAI's Terms of Service. This feature is provided as-is for
//! convenience and may break without notice.
use async_trait::async_trait;
use eventsource_stream::Eventsource;
use futures::{Stream, StreamExt};
use reqwest::Client;
use rust_decimal::Decimal;
use secrecy::{ExposeSecret, SecretString};
use serde_json::{Value, json};
use std::path::PathBuf;
use std::time::Duration;
use tokio::sync::{Mutex, RwLock};
use super::codex_auth;
use crate::error::LlmError;
use super::provider::{
ChatMessage, CompletionRequest, CompletionResponse, ContentPart, FinishReason, LlmProvider,
Role, ToolCall, ToolCompletionRequest, ToolCompletionResponse, ToolDefinition,
};
/// Provider that speaks the Responses API protocol against the ChatGPT backend.
pub struct CodexChatGptProvider {
client: Client,
base_url: String,
api_key: RwLock<SecretString>,
/// User-configured model name (or empty/"default" for auto-detect).
configured_model: String,
/// Lazily resolved model name (populated on first LLM call).
resolved_model: tokio::sync::OnceCell<String>,
/// OAuth refresh token for automatic 401 retry.
refresh_token: Option<SecretString>,
/// Path to auth.json for persisting refreshed tokens.
auth_path: Option<PathBuf>,
/// Timeout for actual `/responses` requests.
request_timeout: Duration,
/// Prevent concurrent 401 handlers from racing the same refresh token.
refresh_lock: Mutex<()>,
}
impl CodexChatGptProvider {
#[cfg(test)]
fn new(base_url: &str, api_key: &str, model: &str) -> Self {
Self {
client: Client::new(),
base_url: base_url.trim_end_matches('/').to_string(),
api_key: RwLock::new(SecretString::from(api_key.to_string())),
configured_model: model.to_string(),
resolved_model: tokio::sync::OnceCell::const_new(),
refresh_token: None,
auth_path: None,
request_timeout: Duration::from_secs(120),
refresh_lock: Mutex::new(()),
}
}
/// Create a provider with lazy model detection.
///
/// The model is **not** resolved during construction. Instead, it is
/// resolved on the first LLM call via [`resolve_model`], avoiding the
/// need for `block_in_place` / `block_on` during provider setup.
///
/// **Model selection priority** (applied at resolution time):
/// 1. If `configured_model` is non-empty, validate it against the
/// `/models` endpoint. If it isn't in the supported list, log a
/// warning with available models and fall back to the top model.
/// 2. If `configured_model` is empty (or a generic placeholder like
/// "default"), auto-detect the highest-priority model from the API.
pub fn with_lazy_model(
base_url: &str,
api_key: SecretString,
configured_model: &str,
refresh_token: Option<SecretString>,
auth_path: Option<PathBuf>,
request_timeout_secs: u64,
) -> Self {
tracing::warn!(
"Codex ChatGPT provider uses a private, undocumented API \
(chatgpt.com/backend-api/codex). This may violate OpenAI's \
Terms of Service and could break without notice."
);
Self {
client: Client::new(),
base_url: base_url.trim_end_matches('/').to_string(),
api_key: RwLock::new(api_key),
configured_model: configured_model.to_string(),
resolved_model: tokio::sync::OnceCell::const_new(),
refresh_token,
auth_path,
request_timeout: Duration::from_secs(request_timeout_secs),
refresh_lock: Mutex::new(()),
}
}
/// Resolve the model to use, lazily on first call.
///
/// Uses `OnceCell` so the `/models` fetch happens at most once.
async fn resolve_model(&self) -> &str {
self.resolved_model
.get_or_init(|| async {
let api_key = self.api_key.read().await.clone();
let available = Self::fetch_available_models(&self.client, &self.base_url, &api_key)
.await;
let configured = &self.configured_model;
if !configured.is_empty() && configured != "default" {
// User explicitly configured a model — validate it
if available.is_empty() {
tracing::warn!(
"Could not fetch model list; using configured model '{configured}'"
);
return configured.clone();
}
if available.iter().any(|m| m == configured) {
tracing::info!(model = %configured, "Codex ChatGPT: using configured model");
return configured.clone();
}
tracing::warn!(
configured = %configured,
available = ?available,
"Configured model not found in supported list, falling back to top model"
);
available
.into_iter()
.next()
.unwrap_or_else(|| configured.clone())
} else {
// No user preference — auto-detect
if let Some(top) = available.into_iter().next() {
tracing::info!(model = %top, "Codex ChatGPT: auto-detected model");
top
} else {
tracing::warn!(
"Could not auto-detect model, using fallback '{configured}'"
);
configured.clone()
}
}
})
.await
}
/// Query `/models?client_version=0.111.0` and return the list of available
/// model slugs, ordered by priority (highest first).
async fn fetch_available_models(
client: &Client,
base_url: &str,
api_key: &SecretString,
) -> Vec<String> {
let url = format!("{base_url}/models?client_version=0.111.0");
let resp = match client
.get(&url)
.bearer_auth(api_key.expose_secret())
.timeout(Duration::from_secs(10))
.send()
.await
{
Ok(r) => r,
Err(e) => {
tracing::warn!("Failed to fetch Codex models: {e}");
return Vec::new();
}
};
if !resp.status().is_success() {
tracing::warn!(status = %resp.status(), "Failed to fetch Codex models");
return Vec::new();
}
let body: Value = match resp.json().await {
Ok(v) => v,
Err(_) => return Vec::new(),
};
// The response has { "models": [ { "slug": "...", ... }, ... ] }
body.get("models")
.and_then(|m| m.as_array())
.map(|models| {
models
.iter()
.filter_map(|m| {
m.get("slug")
.and_then(|s| s.as_str())
.map(|s| s.to_string())
})
.collect()
})
.unwrap_or_default()
}
/// Convert IronClaw messages to Responses API request JSON.
fn build_request_body(
&self,
model: &str,
messages: &[ChatMessage],
tools: &[ToolDefinition],
tool_choice: Option<&str>,
) -> Value {
// Extract system instructions
let instructions: String = messages
.iter()
.filter(|m| m.role == Role::System)
.map(|m| m.content.as_str())
.collect::<Vec<_>>()
.join("\n\n");
// Convert non-system messages to Responses API input items
let input: Vec<Value> = messages
.iter()
.filter(|m| m.role != Role::System)
.flat_map(Self::message_to_input_items)
.collect();
// Convert tool definitions
let api_tools: Vec<Value> = tools
.iter()
.map(|t| {
json!({
"type": "function",
"name": t.name,
"description": t.description,
"parameters": t.parameters,
})
})
.collect();
let mut body = json!({
"model": model,
"instructions": instructions,
"input": input,
"stream": true,
"store": false,
});
if !api_tools.is_empty() {
body["tools"] = json!(api_tools);
body["tool_choice"] = json!(tool_choice.unwrap_or("auto"));
}
body
}
/// Convert a single ChatMessage to one or more Responses API input items.
fn message_to_input_items(msg: &ChatMessage) -> Vec<Value> {
let mut items = Vec::new();
match msg.role {
Role::User => {
// Build content array: if content_parts is populated, use it
// to include multimodal content (images). Otherwise fall back
// to the plain text content field.
let content = if !msg.content_parts.is_empty() {
msg.content_parts
.iter()
.map(|part| match part {
ContentPart::Text { text } => json!({
"type": "input_text",
"text": text,
}),
ContentPart::ImageUrl { image_url } => json!({
"type": "input_image",
"image_url": image_url.url,
}),
})
.collect::<Vec<_>>()
} else {
vec![json!({
"type": "input_text",
"text": msg.content,
})]
};
items.push(json!({
"type": "message",
"role": "user",
"content": content,
}));
}
Role::Assistant => {
// If the assistant message has tool calls, emit function_call items
if let Some(ref tool_calls) = msg.tool_calls {
// Emit the assistant text as a message if non-empty
if !msg.content.is_empty() {
items.push(json!({
"type": "message",
"role": "assistant",
"content": [{
"type": "output_text",
"text": msg.content,
}],
}));
}
for tc in tool_calls {
let args = if tc.arguments.is_string() {
tc.arguments.as_str().unwrap_or("{}").to_string()
} else {
serde_json::to_string(&tc.arguments).unwrap_or_default()
};
items.push(json!({
"type": "function_call",
"name": tc.name,
"arguments": args,
"call_id": tc.id,
}));
}
} else {
items.push(json!({
"type": "message",
"role": "assistant",
"content": [{
"type": "output_text",
"text": msg.content,
}],
}));
}
}
Role::Tool => {
items.push(json!({
"type": "function_call_output",
"call_id": msg.tool_call_id.as_deref().unwrap_or(""),
"output": msg.content,
}));
}
Role::System => {
// System messages are handled via `instructions` field
}
}
items
}
/// Send a request and parse the SSE response.
///
/// On HTTP 401, if a refresh token is available, attempts to refresh
/// the access token and retry the request once.
async fn send_request(&self, body: Value) -> Result<ResponsesResult, LlmError> {
let url = format!("{}/responses", self.base_url);
tracing::debug!(
url = %url,
model = %body.get("model").and_then(|m| m.as_str()).unwrap_or("?"),
"Codex ChatGPT: sending request"
);
let api_key = self.api_key.read().await.clone();
let resp =
Self::send_http_request(&self.client, &url, &api_key, &body, self.request_timeout)
.await?;
let status = resp.status();
if status.as_u16() == 401 {
// Attempt token refresh if we have a refresh token
if let Some(ref rt) = self.refresh_token {
let _refresh_guard = self.refresh_lock.lock().await;
let current_token = self.api_key.read().await.clone();
if current_token.expose_secret() != api_key.expose_secret() {
tracing::info!("Received 401, but another request already refreshed the token");
let retry_resp = Self::send_http_request(
&self.client,
&url,
&current_token,
&body,
self.request_timeout,
)
.await?;
let retry_status = retry_resp.status();
if !retry_status.is_success() {
let body_text =
tokio::time::timeout(Duration::from_secs(5), retry_resp.text())
.await
.unwrap_or(Ok(String::new()))
.unwrap_or_default();
return Err(LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!(
"HTTP {retry_status} from {url} (after concurrent token refresh): {body_text}"
),
});
}
return Self::parse_sse_response_stream(retry_resp, self.request_timeout).await;
}
tracing::info!("Received 401, attempting token refresh");
if let Some(new_token) =
codex_auth::refresh_access_token(&self.client, rt, self.auth_path.as_deref())
.await
{
// Update stored api_key
*self.api_key.write().await = new_token.clone();
tracing::info!("Token refreshed, retrying request");
// Retry the request with the new token
let retry_resp = Self::send_http_request(
&self.client,
&url,
&new_token,
&body,
self.request_timeout,
)
.await?;
let retry_status = retry_resp.status();
if !retry_status.is_success() {
let body_text =
tokio::time::timeout(Duration::from_secs(5), retry_resp.text())
.await
.unwrap_or(Ok(String::new()))
.unwrap_or_default();
return Err(LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!(
"HTTP {retry_status} from {url} (after token refresh): {body_text}"
),
});
}
return Self::parse_sse_response_stream(retry_resp, self.request_timeout).await;
} else {
tracing::warn!(
"Token refresh failed. Please re-authenticate with: codex --login"
);
}
}
// No refresh token or refresh failed — return the 401 error
// Drain the response body to release the connection
let _ = resp.text().await;
return Err(LlmError::AuthFailed {
provider: "codex_chatgpt".to_string(),
});
}
if !status.is_success() {
// Read the error body with a timeout to avoid hanging
let body_text = tokio::time::timeout(Duration::from_secs(5), resp.text())
.await
.unwrap_or(Ok(String::new()))
.unwrap_or_default();
return Err(LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!("HTTP {status} from {url}: {body_text}",),
});
}
Self::parse_sse_response_stream(resp, self.request_timeout).await
}
/// Low-level HTTP POST to the /responses endpoint.
async fn send_http_request(
client: &Client,
url: &str,
api_key: &SecretString,
body: &Value,
timeout: Duration,
) -> Result<reqwest::Response, LlmError> {
client
.post(url)
.bearer_auth(api_key.expose_secret())
.header("Content-Type", "application/json")
.header("Accept", "text/event-stream")
.json(body)
.timeout(timeout)
.send()
.await
.map_err(|e| LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!("HTTP request failed: {e}"),
})
}
async fn parse_sse_response_stream(
resp: reqwest::Response,
idle_timeout: Duration,
) -> Result<ResponsesResult, LlmError> {
let stream = resp
.bytes_stream()
.map(|chunk| chunk.map_err(|e| e.to_string()));
Self::parse_sse_stream(stream, idle_timeout).await
}
async fn parse_sse_stream<S>(
stream: S,
idle_timeout: Duration,
) -> Result<ResponsesResult, LlmError>
where
S: Stream<Item = Result<bytes::Bytes, String>> + Unpin,
{
let mut result = ResponsesResult::default();
let mut stream = stream.eventsource();
loop {
match tokio::time::timeout(idle_timeout, stream.next()).await {
Ok(Some(Ok(event))) => {
let data = event.data.trim();
if data.is_empty() {
continue;
}
let parsed: Value = match serde_json::from_str(data) {
Ok(v) => v,
Err(_) => continue,
};
if Self::handle_sse_event(&mut result, event.event.as_str(), &parsed) {
return Ok(result);
}
}
Ok(Some(Err(e))) => {
return Err(LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!("Failed to read SSE stream: {e}"),
});
}
Ok(None) => return Ok(result),
Err(_) => {
return Err(LlmError::RequestFailed {
provider: "codex_chatgpt".to_string(),
reason: format!(
"Timed out waiting for SSE event after {}s",
idle_timeout.as_secs()
),
});
}
}
}
}
/// Parse SSE events from the response text.
#[cfg(test)]
fn parse_sse_response(sse_text: &str) -> Result<ResponsesResult, LlmError> {
let mut result = ResponsesResult::default();
let mut current_event_type = String::new();
for line in sse_text.lines() {
if let Some(event) = line.strip_prefix("event: ") {
current_event_type = event.trim().to_string();
continue;
}
if let Some(data) = line.strip_prefix("data: ") {
let data = data.trim();
if data.is_empty() {
continue;
}
let parsed: Value = match serde_json::from_str(data) {
Ok(v) => v,
Err(_) => continue,
};
if Self::handle_sse_event(&mut result, current_event_type.as_str(), &parsed) {
return Ok(result);
}
}
}
Ok(result)
}
fn handle_sse_event(result: &mut ResponsesResult, event_type: &str, parsed: &Value) -> bool {
match event_type {
"response.output_text.delta" => {
if let Some(delta) = parsed.get("delta").and_then(|d| d.as_str()) {
result.text.push_str(delta);
}
}
"response.output_item.added" => {
// Capture function call metadata when the item is first added.
// The item has: id (item_id), call_id, name, type.
let item = parsed.get("item").unwrap_or(parsed);
if item.get("type").and_then(|t| t.as_str()) == Some("function_call") {
let item_id = item
.get("id")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
let call_id = item
.get("call_id")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
let name = item
.get("name")
.and_then(|v| v.as_str())
.unwrap_or("")
.to_string();
result
.pending_tool_calls
.entry(item_id)
.or_insert_with(|| PendingToolCall {
call_id,
name,
arguments: String::new(),
});
}
}
"response.function_call_arguments.delta" => {
// Delta events use `item_id` (not `call_id`)
if let Some(item_id) = parsed.get("item_id").and_then(|v| v.as_str())
&& let Some(entry) = result.pending_tool_calls.get_mut(item_id)
&& let Some(delta) = parsed.get("delta").and_then(|d| d.as_str())
{
entry.arguments.push_str(delta);
}
}
"response.completed" => {
if let Some(response) = parsed.get("response")
&& let Some(usage) = response.get("usage")
{
result.input_tokens = usage
.get("input_tokens")
.and_then(|v| v.as_u64())
.unwrap_or(0) as u32;
result.output_tokens = usage
.get("output_tokens")
.and_then(|v| v.as_u64())
.unwrap_or(0) as u32;
}
return true;
}
_ => {}
}
false
}
/// Remove keys with empty-string values from a JSON object.
///
/// gpt-5.2-codex fills optional tool parameters with `""` (e.g.
/// `"timestamp": ""`). IronClaw's tool validation treats these as
/// invalid "non-empty input expected". Stripping them makes the
/// tool see only the actually-provided values.
fn strip_empty_string_values(value: Value) -> Value {
match value {
Value::Object(map) => {
let cleaned: serde_json::Map<String, Value> = map
.into_iter()
.filter(|(_, v)| !matches!(v, Value::String(s) if s.is_empty()))
.map(|(k, v)| (k, Self::strip_empty_string_values(v)))
.collect();
Value::Object(cleaned)
}
other => other,
}
}
}
#[derive(Debug, Default)]
struct ResponsesResult {
text: String,
/// Keyed by item_id (the SSE item identifier, e.g. "fc_...").
pending_tool_calls: std::collections::HashMap<String, PendingToolCall>,
input_tokens: u32,
output_tokens: u32,
}
#[derive(Debug)]
struct PendingToolCall {
/// The call_id from the API (e.g. "call_..."), used to match results.
call_id: String,
name: String,
arguments: String,
}
#[async_trait]
impl LlmProvider for CodexChatGptProvider {
fn model_name(&self) -> &str {
// Return resolved model if available, otherwise the configured name.
self.resolved_model
.get()
.map(|s| s.as_str())
.unwrap_or(&self.configured_model)
}
fn cost_per_token(&self) -> (Decimal, Decimal) {
// ChatGPT backend doesn't expose per-token pricing
(Decimal::ZERO, Decimal::ZERO)
}
async fn complete(&self, request: CompletionRequest) -> Result<CompletionResponse, LlmError> {
let model = self.resolve_model().await;
let body = self.build_request_body(model, &request.messages, &[], None);
let result = self.send_request(body).await?;
Ok(CompletionResponse {
content: result.text,
input_tokens: result.input_tokens,
output_tokens: result.output_tokens,
finish_reason: FinishReason::Stop,
cache_read_input_tokens: 0,
cache_creation_input_tokens: 0,
})
}
async fn complete_with_tools(
&self,
request: ToolCompletionRequest,
) -> Result<ToolCompletionResponse, LlmError> {
let model = self.resolve_model().await;
let body = self.build_request_body(
model,
&request.messages,
&request.tools,
request.tool_choice.as_deref(),
);
let result = self.send_request(body).await?;
let tool_calls: Vec<ToolCall> = result
.pending_tool_calls
.into_values()
.map(|tc| {
let args: Value =
serde_json::from_str(&tc.arguments).unwrap_or_else(|_| json!(tc.arguments));
// gpt-5.2-codex fills optional parameters with empty strings (e.g.
// `"timestamp": ""`), which IronClaw's tool validation rejects.
// Strip them so only actually-provided values reach the tool.
let args = Self::strip_empty_string_values(args);
ToolCall {
id: tc.call_id,
name: tc.name,
arguments: args,
}
})
.collect();
let finish_reason = if tool_calls.is_empty() {
FinishReason::Stop
} else {
FinishReason::ToolUse
};
Ok(ToolCompletionResponse {
content: if result.text.is_empty() {
None
} else {
Some(result.text)
},
tool_calls,
input_tokens: result.input_tokens,
output_tokens: result.output_tokens,
finish_reason,
cache_read_input_tokens: 0,
cache_creation_input_tokens: 0,
})
}
}
#[cfg(test)]
mod tests {
use super::*;
use bytes::Bytes;
use futures::stream;
#[test]
fn test_message_conversion_user() {
let items = CodexChatGptProvider::message_to_input_items(&ChatMessage::user("hello"));
assert_eq!(items.len(), 1);
assert_eq!(items[0]["type"], "message");
assert_eq!(items[0]["role"], "user");
assert_eq!(items[0]["content"][0]["type"], "input_text");
assert_eq!(items[0]["content"][0]["text"], "hello");
}
#[test]
fn test_message_conversion_user_with_image() {
use super::super::provider::ImageUrl;
let parts = vec![
ContentPart::Text {
text: "What's in this image?".to_string(),
},
ContentPart::ImageUrl {
image_url: ImageUrl {
url: "data:image/png;base64,iVBOR...".to_string(),
detail: None,
},
},
];
let msg = ChatMessage::user_with_parts("", parts);
let items = CodexChatGptProvider::message_to_input_items(&msg);
assert_eq!(items.len(), 1);
assert_eq!(items[0]["type"], "message");
assert_eq!(items[0]["role"], "user");
let content = items[0]["content"].as_array().unwrap();
assert_eq!(content.len(), 2);
assert_eq!(content[0]["type"], "input_text");
assert_eq!(content[0]["text"], "What's in this image?");
assert_eq!(content[1]["type"], "input_image");
assert_eq!(content[1]["image_url"], "data:image/png;base64,iVBOR...");
}
#[test]
fn test_message_conversion_assistant() {
let items = CodexChatGptProvider::message_to_input_items(&ChatMessage::assistant("hi"));
assert_eq!(items.len(), 1);
assert_eq!(items[0]["type"], "message");
assert_eq!(items[0]["role"], "assistant");
assert_eq!(items[0]["content"][0]["type"], "output_text");
}
#[test]
fn test_message_conversion_tool_result() {
let msg = ChatMessage::tool_result("call_1", "search", "result text");
let items = CodexChatGptProvider::message_to_input_items(&msg);
assert_eq!(items.len(), 1);
assert_eq!(items[0]["type"], "function_call_output");
assert_eq!(items[0]["call_id"], "call_1");
assert_eq!(items[0]["output"], "result text");
}
#[test]
fn test_message_conversion_assistant_with_tool_calls() {
let tc = ToolCall {
id: "call_1".to_string(),
name: "search".to_string(),
arguments: json!({"query": "rust"}),
};
let msg = ChatMessage::assistant_with_tool_calls(Some("thinking...".into()), vec![tc]);
let items = CodexChatGptProvider::message_to_input_items(&msg);
// Should produce: 1 text message + 1 function_call
assert_eq!(items.len(), 2);
assert_eq!(items[0]["type"], "message");
assert_eq!(items[1]["type"], "function_call");
assert_eq!(items[1]["name"], "search");
assert_eq!(items[1]["call_id"], "call_1");
}
#[test]
fn test_build_request_extracts_system_as_instructions() {
let provider = CodexChatGptProvider::new("https://example.com", "key", "gpt-4o");
let messages = vec![
ChatMessage::system("You are helpful."),
ChatMessage::user("hello"),
];
let body = provider.build_request_body("gpt-4o", &messages, &[], None);
assert_eq!(body["instructions"], "You are helpful.");
// input should only contain the user message, not the system message
assert_eq!(body["input"].as_array().unwrap().len(), 1);
// store must be false for ChatGPT backend
assert_eq!(body["store"], false);
}
#[test]
fn test_parse_sse_text_response() {
let sse = r#"event: response.output_text.delta
data: {"delta":"Hello"}
event: response.output_text.delta
data: {"delta":" world!"}
event: response.completed
data: {"response":{"usage":{"input_tokens":10,"output_tokens":5}}}
"#;
let result = CodexChatGptProvider::parse_sse_response(sse).unwrap();
assert_eq!(result.text, "Hello world!");
assert_eq!(result.input_tokens, 10);
assert_eq!(result.output_tokens, 5);
assert!(result.pending_tool_calls.is_empty());
}
#[test]
fn test_parse_sse_tool_call() {
// Real API format: output_item.added has item.id (item_id) + item.call_id,
// delta events use item_id (not call_id)
let sse = r#"event: response.output_item.added
data: {"item":{"id":"fc_1","type":"function_call","call_id":"call_1","name":"search"}}
event: response.function_call_arguments.delta
data: {"item_id":"fc_1","delta":"{\"query\":"}
event: response.function_call_arguments.delta
data: {"item_id":"fc_1","delta":"\"rust\"}"}
event: response.completed
data: {"response":{"usage":{"input_tokens":20,"output_tokens":15}}}
"#;
let result = CodexChatGptProvider::parse_sse_response(sse).unwrap();
assert!(result.text.is_empty());
assert_eq!(result.pending_tool_calls.len(), 1);
let tc = result.pending_tool_calls.get("fc_1").unwrap();
assert_eq!(tc.call_id, "call_1");
assert_eq!(tc.name, "search");
assert_eq!(tc.arguments, "{\"query\":\"rust\"}");
}
#[tokio::test]
async fn test_parse_sse_stream_response() {
let stream = stream::iter(vec![
Ok(Bytes::from_static(
b"event: response.output_text.delta\ndata: {\"delta\":\"Hello\"}\n\n",
)),
Ok(Bytes::from_static(
b"event: response.output_text.delta\ndata: {\"delta\":\" world\"}\n\n",
)),
Ok(Bytes::from_static(
b"event: response.completed\ndata: {\"response\":{\"usage\":{\"input_tokens\":3,\"output_tokens\":2}}}\n\n",
)),
]);
let result = CodexChatGptProvider::parse_sse_stream(stream, Duration::from_secs(1))
.await
.unwrap();
assert_eq!(result.text, "Hello world");
assert_eq!(result.input_tokens, 3);
assert_eq!(result.output_tokens, 2);
}
#[test]
fn test_strip_empty_string_values() {
let input = json!({
"format": "%Y-%m-%d",
"operation": "now",
"timestamp": "",
"timestamp2": "",
});
let cleaned = CodexChatGptProvider::strip_empty_string_values(input);
assert_eq!(cleaned, json!({"format": "%Y-%m-%d", "operation": "now"}));
}
}
-33
View File
@@ -5,8 +5,6 @@
//! extracted into a standalone crate. Resolution logic (reading env vars,
//! settings) lives in `crate::config::llm`.
use std::path::PathBuf;
use secrecy::SecretString;
use crate::llm::registry::ProviderProtocol;
@@ -87,13 +85,6 @@ pub struct RegistryProviderConfig {
/// OAuth token for providers that support Bearer auth (e.g. Anthropic via `claude login`).
/// When set, the provider factory routes to the OAuth-specific provider implementation.
pub oauth_token: Option<SecretString>,
/// When true, route OpenAI-compatible traffic to the Codex ChatGPT
/// Responses API provider instead of rig-core's Chat Completions path.
pub is_codex_chatgpt: bool,
/// OAuth refresh token for Codex ChatGPT token refresh.
pub refresh_token: Option<SecretString>,
/// Path to Codex auth.json for persisting refreshed tokens.
pub auth_path: Option<PathBuf>,
/// Prompt cache retention (Anthropic-specific).
pub cache_retention: CacheRetention,
/// Parameter names that this provider does not support (e.g., `["temperature"]`).
@@ -138,30 +129,6 @@ pub struct LlmConfig {
/// Default: 120. Increase for local LLMs (Ollama, vLLM, LM Studio) that
/// need more time for prompt evaluation on consumer hardware.
pub request_timeout_secs: u64,
/// Generic cheap/fast model for lightweight tasks (heartbeat, routing, evaluation).
/// Works with any backend. Set via `LLM_CHEAP_MODEL` env var.
/// When set, takes priority over the NearAI-specific `NEARAI_CHEAP_MODEL`.
pub cheap_model: Option<String>,
/// Enable cascade mode for smart routing (retry with primary if cheap model
/// response seems uncertain). Default: true. Set via `SMART_ROUTING_CASCADE`.
pub smart_routing_cascade: bool,
}
impl LlmConfig {
/// Resolve the effective cheap model name.
///
/// Resolution order:
/// 1. `LLM_CHEAP_MODEL` (generic, works with any backend)
/// 2. `NEARAI_CHEAP_MODEL` (NearAI-only, backward compatibility)
pub fn cheap_model_name(&self) -> Option<&str> {
self.cheap_model.as_deref().or_else(|| {
if self.backend == "nearai" {
self.nearai.cheap_model.as_deref()
} else {
None
}
})
}
}
/// NEAR AI configuration.
+30 -162
View File
@@ -12,8 +12,6 @@ mod anthropic_oauth;
#[cfg(feature = "bedrock")]
mod bedrock;
pub mod circuit_breaker;
pub(crate) mod codex_auth;
mod codex_chatgpt;
pub mod config;
pub mod costs;
pub mod error;
@@ -104,7 +102,7 @@ pub async fn create_llm_provider(
provider: config.backend.clone(),
})?;
create_registry_provider(reg_config, timeout)
create_registry_provider(reg_config)
}
/// Create an LLM provider from a `NearAiConfig` directly.
@@ -142,13 +140,7 @@ pub fn create_llm_provider_with_config(
/// `create_*_provider` functions.
fn create_registry_provider(
config: &RegistryProviderConfig,
request_timeout_secs: u64,
) -> Result<Arc<dyn LlmProvider>, LlmError> {
// Codex ChatGPT mode: use the Responses API provider
if config.is_codex_chatgpt {
return create_codex_chatgpt_from_registry(config, request_timeout_secs);
}
match config.protocol {
ProviderProtocol::OpenAiCompletions => create_openai_compat_from_registry(config),
ProviderProtocol::Anthropic => create_anthropic_from_registry(config),
@@ -156,36 +148,6 @@ fn create_registry_provider(
}
}
fn create_codex_chatgpt_from_registry(
config: &RegistryProviderConfig,
request_timeout_secs: u64,
) -> Result<Arc<dyn LlmProvider>, LlmError> {
let api_key = config
.api_key
.as_ref()
.cloned()
.ok_or_else(|| LlmError::AuthFailed {
provider: "codex_chatgpt".to_string(),
})?;
tracing::info!(
configured_model = %config.model,
base_url = %config.base_url,
"Using Codex ChatGPT provider (Responses API) — model detection deferred to first call"
);
let provider = codex_chatgpt::CodexChatGptProvider::with_lazy_model(
&config.base_url,
api_key,
&config.model,
config.refresh_token.clone(),
config.auth_path.clone(),
request_timeout_secs,
);
Ok(Arc::new(provider))
}
#[cfg(feature = "bedrock")]
async fn create_bedrock_provider(config: &LlmConfig) -> Result<Arc<dyn LlmProvider>, LlmError> {
let br = config
@@ -201,7 +163,6 @@ async fn create_bedrock_provider(config: &LlmConfig) -> Result<Arc<dyn LlmProvid
br.region,
provider.active_model_name(),
);
Ok(Arc::new(provider))
}
@@ -376,61 +337,32 @@ fn create_ollama_from_registry(
/// Create a cheap/fast LLM provider for lightweight tasks (heartbeat, routing, evaluation).
///
/// Resolution order:
/// 1. `LLM_CHEAP_MODEL` (generic, works with any backend)
/// 2. `NEARAI_CHEAP_MODEL` (NearAI-only, backward compatibility)
///
/// Returns `None` if no cheap model is configured.
/// Uses `NEARAI_CHEAP_MODEL` if set, otherwise falls back to the main provider.
/// Currently only supports NEAR AI backend.
pub fn create_cheap_llm_provider(
config: &LlmConfig,
session: Arc<SessionManager>,
) -> Result<Option<Arc<dyn LlmProvider>>, LlmError> {
let Some(cheap_model) = config.cheap_model_name() else {
let Some(ref cheap_model) = config.nearai.cheap_model else {
return Ok(None);
};
create_cheap_provider_for_backend(config, session, cheap_model)
}
/// Create a cheap provider for a specific backend.
///
/// Handles backend-specific provider construction:
/// - `nearai` — clones NearAiConfig, swaps model, uses `create_llm_provider_with_config`
/// - `bedrock` — returns error (smart routing not yet supported)
/// - All others — clones `RegistryProviderConfig`, swaps model, uses `create_registry_provider`
fn create_cheap_provider_for_backend(
config: &LlmConfig,
session: Arc<SessionManager>,
cheap_model: &str,
) -> Result<Option<Arc<dyn LlmProvider>>, LlmError> {
if config.backend == "nearai" {
let mut cheap_config = config.nearai.clone();
cheap_config.model = cheap_model.to_string();
let provider =
create_llm_provider_with_config(&cheap_config, session, config.request_timeout_secs)?;
return Ok(Some(provider));
}
if config.backend == "bedrock" {
return Err(LlmError::RequestFailed {
provider: "bedrock".to_string(),
reason: "Smart routing with cheap model is not supported for Bedrock yet".to_string(),
});
}
// Registry-based provider: clone config and swap model
let reg_config = config.provider.as_ref().ok_or_else(|| LlmError::RequestFailed {
provider: config.backend.clone(),
reason: format!(
"Cannot create cheap provider for backend '{}': no registry provider config available",
if config.backend != "nearai" {
tracing::warn!(
"NEARAI_CHEAP_MODEL is set but LLM_BACKEND is '{}', not nearai. \
Cheap model setting will be ignored.",
config.backend
),
})?;
);
return Ok(None);
}
let mut cheap_reg_config = reg_config.clone();
cheap_reg_config.model = cheap_model.to_string();
let provider = create_registry_provider(&cheap_reg_config, config.request_timeout_secs)?;
Ok(Some(provider))
let mut cheap_config = config.nearai.clone();
cheap_config.model = cheap_model.clone();
Ok(Some(Arc::new(NearAiChatProvider::new(
cheap_config,
session,
)?)))
}
/// Build the full LLM provider chain with all configured wrappers.
@@ -478,15 +410,14 @@ pub async fn build_provider_chain(
};
// 2. Smart routing (cheap/primary split)
let llm: Arc<dyn LlmProvider> = if let Some(cheap_model) = config.cheap_model_name() {
let cheap = create_cheap_provider_for_backend(config, session.clone(), cheap_model)?
.ok_or_else(|| LlmError::RequestFailed {
provider: config.backend.clone(),
reason: format!(
"Failed to create cheap provider for model '{cheap_model}' on backend '{}'",
config.backend
),
})?;
let llm: Arc<dyn LlmProvider> = if let Some(ref cheap_model) = config.nearai.cheap_model {
let mut cheap_config = config.nearai.clone();
cheap_config.model = cheap_model.clone();
let cheap = create_llm_provider_with_config(
&cheap_config,
session.clone(),
config.request_timeout_secs,
)?;
let cheap: Arc<dyn LlmProvider> = if retry_config.max_retries > 0 {
Arc::new(RetryProvider::new(cheap, retry_config.clone()))
} else {
@@ -501,7 +432,7 @@ pub async fn build_provider_chain(
llm,
cheap,
SmartRoutingConfig {
cascade_enabled: config.smart_routing_cascade,
cascade_enabled: config.nearai.smart_routing_cascade,
..SmartRoutingConfig::default()
},
))
@@ -630,8 +561,6 @@ mod tests {
provider: None,
bedrock: None,
request_timeout_secs: 120,
cheap_model: None,
smart_routing_cascade: true,
}
}
@@ -646,7 +575,7 @@ mod tests {
}
#[test]
fn test_create_cheap_llm_provider_creates_provider_with_nearai_cheap_model() {
fn test_create_cheap_llm_provider_creates_provider_when_configured() {
let mut config = test_llm_config();
config.nearai.cheap_model = Some("cheap-test-model".to_string());
@@ -660,26 +589,7 @@ mod tests {
}
#[test]
fn test_create_cheap_llm_provider_generic_overrides_nearai() {
let mut config = test_llm_config();
config.nearai.cheap_model = Some("nearai-cheap".to_string());
config.cheap_model = Some("generic-cheap".to_string());
let session = Arc::new(SessionManager::new(SessionConfig::default()));
let result = create_cheap_llm_provider(&config, session);
assert!(result.is_ok());
let provider = result.unwrap();
assert!(provider.is_some());
assert_eq!(
provider.unwrap().model_name(),
"generic-cheap",
"LLM_CHEAP_MODEL should take priority over NEARAI_CHEAP_MODEL"
);
}
#[test]
fn test_create_cheap_llm_provider_nearai_cheap_ignored_for_non_nearai_backend() {
fn test_create_cheap_llm_provider_ignored_for_non_nearai_backend() {
let mut config = test_llm_config();
config.backend = "openai".to_string();
config.nearai.cheap_model = Some("cheap-test-model".to_string());
@@ -688,48 +598,6 @@ mod tests {
let result = create_cheap_llm_provider(&config, session);
assert!(result.is_ok());
assert!(
result.unwrap().is_none(),
"NEARAI_CHEAP_MODEL should be ignored when backend is not nearai"
);
}
#[test]
fn test_create_cheap_llm_provider_bedrock_returns_error() {
let mut config = test_llm_config();
config.backend = "bedrock".to_string();
config.cheap_model = Some("cheap-model".to_string());
let session = Arc::new(SessionManager::new(SessionConfig::default()));
let result = create_cheap_llm_provider(&config, session);
assert!(
result.is_err(),
"Bedrock should return an error for cheap model"
);
}
#[test]
fn test_cheap_model_name_resolution() {
// Generic takes priority
let mut config = test_llm_config();
config.cheap_model = Some("generic".to_string());
config.nearai.cheap_model = Some("nearai".to_string());
assert_eq!(config.cheap_model_name(), Some("generic"));
// NearAI fallback when backend is nearai
let mut config = test_llm_config();
config.nearai.cheap_model = Some("nearai".to_string());
assert_eq!(config.cheap_model_name(), Some("nearai"));
// NearAI ignored for non-nearai backend
let mut config = test_llm_config();
config.backend = "openai".to_string();
config.nearai.cheap_model = Some("nearai".to_string());
assert_eq!(config.cheap_model_name(), None);
// None when nothing configured
let config = test_llm_config();
assert_eq!(config.cheap_model_name(), None);
assert!(result.unwrap().is_none());
}
}
-2
View File
@@ -345,7 +345,5 @@ pub(crate) fn build_nearai_model_fetch_config() -> crate::config::LlmConfig {
provider: None,
bedrock: None,
request_timeout_secs: 120,
cheap_model: None,
smart_routing_cascade: false,
}
}
+1 -114
View File
@@ -244,7 +244,6 @@ impl NearAiChatProvider {
let status = response.status();
// Extract Retry-After header before consuming the response body.
// Supports both delay-seconds (RFC 7231 §7.1.3) and HTTP-date formats.
// Falls back to 60s if header is missing or unparseable (prevents "retry after None" errors).
let retry_after_header = response
.headers()
.get("retry-after")
@@ -265,8 +264,7 @@ impl NearAiChatProvider {
));
}
None
})
.or(Some(std::time::Duration::from_secs(60)));
});
let response_text = response.text().await.map_err(|e| LlmError::RequestFailed {
provider: "nearai_chat".to_string(),
reason: format!("Failed to read response body: {}", e),
@@ -2218,115 +2216,4 @@ mod tests {
"http://example.com/api/proxy/v1/chat/completions"
);
}
// -- Retry-After header parsing tests (regression for rate limit "None" bug) --
#[test]
fn test_retry_after_parsing_delay_seconds() {
// Verify delay-seconds format (most common) is parsed correctly
let header_value = "30";
let duration = parse_retry_after_for_test(header_value);
assert_eq!(duration, Some(std::time::Duration::from_secs(30)));
}
#[test]
fn test_retry_after_parsing_rfc2822_date() {
// Verify HTTP-date (RFC 2822) format is parsed correctly
// Use a date 60 seconds in the future
let now = chrono::Utc::now();
let future = now + chrono::Duration::seconds(60);
let date_str = future.to_rfc2822();
let duration = parse_retry_after_for_test(&date_str);
assert!(duration.is_some());
let d = duration.unwrap();
// Allow ±5 seconds of drift due to processing time
assert!(
d.as_secs() >= 55 && d.as_secs() <= 65,
"Expected ~60s, got {}s",
d.as_secs()
);
}
#[test]
fn test_retry_after_fallback_missing_header() {
// Regression test: When Retry-After header is missing,
// should fall back to 60s instead of None
let duration = parse_retry_after_for_test("");
assert_eq!(
duration,
Some(std::time::Duration::from_secs(60)),
"Missing header should fallback to 60s"
);
}
#[test]
fn test_retry_after_fallback_invalid_format() {
// Regression test: When Retry-After header is in unexpected format,
// should fall back to 60s instead of None
let invalid_formats = vec![
"invalid",
"not-a-number",
"30.5", // float instead of int
"abc123",
];
for format in invalid_formats {
let duration = parse_retry_after_for_test(format);
assert_eq!(
duration,
Some(std::time::Duration::from_secs(60)),
"Invalid format '{}' should fallback to 60s",
format
);
}
}
#[test]
fn test_retry_after_past_date_returns_zero() {
// When HTTP-date is in the past, should return Duration::ZERO
// (not None, which would trigger immediate retry)
let past = chrono::Utc::now() - chrono::Duration::seconds(60);
let past_date_str = past.to_rfc2822();
let duration = parse_retry_after_for_test(&past_date_str);
assert_eq!(
duration,
Some(std::time::Duration::ZERO),
"Past date should return Duration::ZERO, not None"
);
}
#[test]
fn test_retry_after_zero_seconds_accepted() {
// Verify zero seconds is a valid retry delay
let duration = parse_retry_after_for_test("0");
assert_eq!(duration, Some(std::time::Duration::ZERO));
}
#[test]
fn test_retry_after_large_number() {
// Verify large numbers are accepted
let duration = parse_retry_after_for_test("3600"); // 1 hour
assert_eq!(duration, Some(std::time::Duration::from_secs(3600)));
}
/// Helper function to test Retry-After header parsing logic
/// (simulates the parsing done in send_request without actual HTTP, including fallback)
fn parse_retry_after_for_test(header_value: &str) -> Option<std::time::Duration> {
let trimmed = header_value.trim();
let parsed = if let Ok(secs) = trimmed.parse::<u64>() {
Some(std::time::Duration::from_secs(secs))
} else if let Ok(dt) = chrono::DateTime::parse_from_rfc2822(trimmed) {
let now = chrono::Utc::now();
let delta = dt.signed_duration_since(now);
Some(std::time::Duration::from_secs(
delta.num_seconds().max(0) as u64
))
} else {
None
};
// Apply fallback to 60s if parsing failed (matches actual code behavior)
parsed.or(Some(std::time::Duration::from_secs(60)))
}
}
+5 -43
View File
@@ -51,32 +51,10 @@ pub struct MemorySnapshotEntry {
pub content: String,
}
/// A recorded HTTP request/response pair.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HttpExchange {
pub request: HttpExchangeRequest,
pub response: HttpExchangeResponse,
}
/// The request side of an HTTP exchange.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HttpExchangeRequest {
pub method: String,
pub url: String,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub headers: Vec<(String, String)>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub body: Option<String>,
}
/// The response side of an HTTP exchange.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HttpExchangeResponse {
pub status: u16,
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub headers: Vec<(String, String)>,
pub body: String,
}
// Re-export HTTP exchange types from their canonical location in observability.
pub use crate::observability::http_interceptor::{
HttpExchange, HttpExchangeRequest, HttpExchangeResponse, HttpInterceptor,
};
/// A single step in the trace.
#[derive(Debug, Clone, Serialize, Deserialize)]
@@ -144,23 +122,7 @@ pub struct ExpectedToolResult {
pub content: String,
}
// ── HTTP interceptor ───────────────────────────────────────────────
/// Trait for intercepting HTTP requests from tools.
///
/// During recording, the interceptor captures exchanges after the real
/// request completes. During replay, it short-circuits with a recorded response.
#[async_trait]
pub trait HttpInterceptor: Send + Sync + std::fmt::Debug {
/// Called before making an HTTP request.
///
/// Return `Some(response)` to short-circuit (replay mode).
/// Return `None` to let the real request proceed (recording mode).
async fn before_request(&self, request: &HttpExchangeRequest) -> Option<HttpExchangeResponse>;
/// Called after a real HTTP request completes (recording mode only).
async fn after_response(&self, request: &HttpExchangeRequest, response: &HttpExchangeResponse);
}
// ── HTTP interceptor impls ─────────────────────────────────────────
/// Records HTTP exchanges during a live session.
#[derive(Debug)]

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