Files
optimclaw/src/agent/self_repair.rs
T
a24fd3e8a3 Add automated QA: schema validator, CI matrix, Docker build, and P1 test coverage (#353)
* Add automated QA: tool schema validator, feature-flag CI matrix, Docker build

P0 items from the automated QA plan (#352):

- Add validate_tool_schema() that checks OpenAI strict-mode rules
  (type: object, required keys in properties, nested object/array
  recursion) with 10 unit tests and 6 integration tests covering
  all core built-in tools

- CI test matrix now runs with --all-features, default features, and
  --no-default-features --features libsql to catch dead code behind
  wrong cfg gates

- CI clippy now runs the same 3-feature matrix with --all flags

- Docker build job added to catch missing files in Dockerfile

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add P1 automated QA tests and fix LeakDetector prefix shadowing bug

P1 test coverage: config round-trip (settings + bootstrap), shell tool
arg handling, safety adversarial tests (sanitizer, leak detector,
allowlist), turn persistence (conversations, metadata, pagination, jobs),
and a clippy fix for libsql-only builds.

Fixed a real bug where AhoCorasick non-overlapping prefix iteration
caused shorter prefixes (e.g. "sk-") to shadow longer ones
(e.g. "sk-ant-api"), preventing Anthropic API key and SSH private key
detection.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add P2 automated QA tests: chaos, lifecycle, collision, and recovery

Cover all P2 items from the automated QA plan:
- Circuit breaker chaos tests (hanging provider, rapid cycles, mixed errors)
- Failover chaos tests (hanging failover, all-fail, tools path, single provider)
- Value estimator boundary tests (negative cost, zero price, zero earnings)
- Context length recovery test (ContextLengthExceeded -> compact -> retry)
- WASM channel lifecycle tests (write/commit/read round-trip, namespace isolation)
- Extension registry collision tests (same-name different-kind coexistence)
- Extension filesystem collision tests (separate dirs, detect_kind priority)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add P3 concurrent stress tests for ContextManager and SessionManager

Tests verify thread safety of double-checked locking, TOCTOU
prevention, and RwLock-based concurrent access patterns under load.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add dispatcher loop guard and self-repair stuck job tests

Dispatcher: test force_text mechanism prevents infinite tool call loops,
verify iteration bound arithmetic guarantees termination for all configs.

Self-repair: test stuck job detection, recovery within attempt limits,
manual escalation when limit exceeded, graceful degradation without
store/builder dependencies.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add E2E testing infrastructure design doc

Python + Playwright framework with mock LLM server for deterministic
browser-level testing of the web gateway. Covers connection/auth,
chat round-trip with SSE streaming, and skills lifecycle scenarios.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Add E2E testing infrastructure implementation plan

10-task plan covering: scaffolding, mock LLM server, helpers,
conftest fixtures, connection/chat/skills test scenarios,
CI workflow, README, and integration run.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* scaffold: E2E test project with pyproject.toml

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: E2E helpers with DOM selectors and port discovery

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: mock OpenAI-compat LLM server for E2E tests

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: E2E conftest with session fixtures for mock LLM and ironclaw

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: E2E scenario 1 -- connection and tab navigation tests

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: E2E scenario 2 -- chat message round-trip tests

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* feat: E2E scenario 3 -- skills search, install, remove tests

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* ci: add weekly E2E test workflow with Playwright

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* docs: E2E test README with setup and usage instructions

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: E2E test integration fixes from first run

- Use temp file DB instead of :memory: (libSQL :memory: doesn't persist
  tables across execute_batch)
- Fix installed skills selector: #skills-list not #installed-skills
- Add pytest-timeout to dependencies
- Improve skills install/remove test with wait_for instead of fixed sleeps

8 passed, 1 skipped (skills install depends on ClawHub availability)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add OpenAI strict-mode schema validator for all built-in tools (QA 1.1)

Add src/tools/schema_validator.rs with validate_strict_schema() that checks
tool parameter schemas against OpenAI function calling strict-mode rules:
type object at top level, required keys in properties, enum type consistency,
array items definitions, nested object recursion, and additionalProperties.

17 tests validate all 34+ built-in tool schemas across 5 test groups:
- 9 simple tools (echo, time, json, http, shell, file read/write/list/patch)
- 4 job tools (create, list, status, cancel)
- 4 skill tools (list, search, install, remove)
- 13 inline schemas for extension, routine, and complex job tools
- 4 memory tool schemas

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add E2E scenarios for SSE reconnect, HTML injection, and tool approval (QA 3.3/5/6)

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: E2E test reliability for HTML injection and SSE reconnect

- HTML injection: test sanitization directly via JS injection instead of
  depending on full LLM round-trip (avoids intermittent 404 from mock)
- SSE reconnect: increase wait times for DB persistence and relax
  assertion to check total message count after history reload

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: cargo fmt formatting

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add WASM and MCP tool schema validation tests (QA 1.1)

Extends the schema validator with representative WASM tool schemas
(weather, HTTP client, batch processor, status), MCP tool schemas
(default, file read, SQL query, strict mode), and defect detection
tests for common external schema issues (missing type, typo in
required, array without items, enum type mismatch).

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add auth middleware and compaction module tests

Auth middleware (8 new tests): valid/invalid bearer tokens, query param
fallback, case sensitivity, empty tokens, whitespace handling.

Compaction module (16 new tests): truncation strategy, summarize strategy
with mock LLM, workspace fallback, format_turns helper, sequential
compactions, coherence after compaction, token decrease verification.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add config round-trip integration tests (QA 1.2)

Test the full bootstrap .env lifecycle: write via the same format
as save_bootstrap_env/upsert_bootstrap_var, read back via dotenvy,
and assert values match. Covers LLM backend selection, embedding
disable flag, onboard completion flag, session token keys, multi-key
preservation across upsert, and special characters (spaces, equals,
quotes, backslashes, hashes).

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add value estimator boundary tests and dispatcher loop guard (QA 4.3/4.4)

Value estimator (14 new tests): zero/negative prices, large values,
negative cost, exact margin boundaries, custom margin configuration.

Dispatcher loop guard (2 new tests): verifies the dispatch loop terminates
when all tool calls fail (regression guard for PR #252 infinite loop)
and when max iterations are reached.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test: add failover edge cases and provider chaos tests (QA 2.6/4.1)

Failover edge cases (4 new tests): cooldown at zero nanos, half-open
failure reopens circuit, all providers fail gracefully (no panic),
single failing provider with cooldown.

Provider chaos tests (15 new tests): flakey provider with retries,
hanging provider with timeout, garbage provider, circuit breaker
trip/recover, failover chain cascading, non-transient error stops
chain, full stack integration (retry + failover + circuit breaker).

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review feedback on QA tests

- Fix Bearer auth case-sensitivity per RFC 6750 (auth.rs)
- Refactor bootstrap.rs to expose path-parameterized variants so
  config_round_trip tests call real code instead of reimplementations
- Remove deprecated event_loop fixture, use dynamic ports, minimal env,
  session-scoped browser, and wire HEADED=1 in E2E conftest
- Add cross-referencing doc comments between schema validators
- Simplify array validation logic in tool.rs
- Bump e2e.yml checkout@v4 to @v6

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: cargo fmt and fix clippy warning in signal.rs

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: improve E2E fixture error reporting and prevent stdin blocking

- Add --no-onboard flag to prevent wizard from blocking in CI
- Pipe /dev/null to stdin to prevent any stdin reads from hanging
- Add RUST_BACKTRACE=1 for crash diagnostics
- On server startup timeout, dump stderr to pytest output so CI
  logs show why the server failed to start

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: set session-scoped event loop for E2E async fixtures

pytest-asyncio 1.3.0 defaults asyncio_default_fixture_loop_scope to
None (function scope), causing session-scoped async fixtures to be
re-evaluated per test function with independent event loops. Each test
then independently attempts to start the ironclaw server, times out
at 120s, and wastes ~24 minutes of CI before the job is cancelled.

Setting asyncio_default_fixture_loop_scope = "session" ensures all
session-scoped async fixtures share a single event loop, so the server
starts once and is reused across all tests.

Also adds -x flag to pytest in CI to stop on first failure instead of
running all 19 tests when the fixture is broken.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: set test loop scope to session to match fixture loop scope

With asyncio_default_fixture_loop_scope=session but
asyncio_default_test_loop_scope=function (the default), tests run on
a per-function event loop while fixtures produce objects (Playwright
pages, browser contexts) on the session event loop. This event loop
mismatch causes the test to hang indefinitely awaiting Playwright
operations that are bound to the wrong loop.

Setting both scopes to "session" ensures a single event loop is shared
across all fixtures and tests, eliminating the deadlock.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* ci: add roll-up jobs to match branch protection required checks

Branch protection expects "Code Style (fmt + clippy)" and "Run Tests"
status checks, but only individual job names were reported. Add
roll-up jobs that aggregate results and report the expected names.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
2026-02-27 09:09:45 +04:00

521 lines
17 KiB
Rust

//! Self-repair for stuck jobs and broken tools.
use std::sync::Arc;
use std::time::Duration;
use async_trait::async_trait;
use chrono::{DateTime, Utc};
use uuid::Uuid;
use crate::context::{ContextManager, JobState};
use crate::db::Database;
use crate::error::RepairError;
use crate::tools::{BuildRequirement, Language, SoftwareBuilder, SoftwareType, ToolRegistry};
/// A job that has been detected as stuck.
#[derive(Debug, Clone)]
pub struct StuckJob {
pub job_id: Uuid,
pub last_activity: DateTime<Utc>,
pub stuck_duration: Duration,
pub last_error: Option<String>,
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,
}
/// Result of a repair attempt.
#[derive(Debug)]
pub enum RepairResult {
/// Repair was successful.
Success { message: String },
/// Repair failed but can be retried.
Retry { message: String },
/// Repair failed permanently.
Failed { message: String },
/// Manual intervention required.
ManualRequired { message: String },
}
/// Trait for self-repair implementations.
#[async_trait]
pub trait SelfRepair: Send + Sync {
/// Detect stuck jobs.
async fn detect_stuck_jobs(&self) -> Vec<StuckJob>;
/// Attempt to repair a stuck job.
async fn repair_stuck_job(&self, job: &StuckJob) -> Result<RepairResult, RepairError>;
/// Detect broken tools.
async fn detect_broken_tools(&self) -> Vec<BrokenTool>;
/// Attempt to repair a broken tool.
async fn repair_broken_tool(&self, tool: &BrokenTool) -> Result<RepairResult, RepairError>;
}
/// Default self-repair implementation.
pub struct DefaultSelfRepair {
context_manager: Arc<ContextManager>,
// TODO: use for time-based stuck detection (currently only max_repair_attempts is checked)
#[allow(dead_code)]
stuck_threshold: Duration,
max_repair_attempts: u32,
store: Option<Arc<dyn Database>>,
builder: Option<Arc<dyn SoftwareBuilder>>,
// TODO: use for tool hot-reload after repair
#[allow(dead_code)]
tools: Option<Arc<ToolRegistry>>,
}
impl DefaultSelfRepair {
/// Create a new self-repair instance.
pub fn new(
context_manager: Arc<ContextManager>,
stuck_threshold: Duration,
max_repair_attempts: u32,
) -> Self {
Self {
context_manager,
stuck_threshold,
max_repair_attempts,
store: None,
builder: None,
tools: None,
}
}
/// Add a Store for tool failure tracking.
#[allow(dead_code)] // TODO: wire up in main.rs when persistence is needed
pub(crate) fn with_store(mut self, store: Arc<dyn Database>) -> Self {
self.store = Some(store);
self
}
/// Add a Builder and ToolRegistry for automatic tool repair.
#[allow(dead_code)] // TODO: wire up in main.rs when auto-repair is needed
pub(crate) fn with_builder(
mut self,
builder: Arc<dyn SoftwareBuilder>,
tools: Arc<ToolRegistry>,
) -> Self {
self.builder = Some(builder);
self.tools = Some(tools);
self
}
}
#[async_trait]
impl SelfRepair for DefaultSelfRepair {
async fn detect_stuck_jobs(&self) -> Vec<StuckJob> {
let stuck_ids = self.context_manager.find_stuck_jobs().await;
let mut stuck_jobs = Vec::new();
for job_id in stuck_ids {
if let Ok(ctx) = self.context_manager.get_context(job_id).await
&& ctx.state == JobState::Stuck
{
let stuck_duration = ctx
.started_at
.map(|start| {
let now = Utc::now();
let duration = now.signed_duration_since(start);
Duration::from_secs(duration.num_seconds().max(0) as u64)
})
.unwrap_or_default();
stuck_jobs.push(StuckJob {
job_id,
last_activity: ctx.started_at.unwrap_or(ctx.created_at),
stuck_duration,
last_error: None,
repair_attempts: ctx.repair_attempts,
});
}
}
stuck_jobs
}
async fn repair_stuck_job(&self, job: &StuckJob) -> Result<RepairResult, RepairError> {
// Check if we've exceeded max repair attempts
if job.repair_attempts >= self.max_repair_attempts {
return Ok(RepairResult::ManualRequired {
message: format!(
"Job {} has exceeded maximum repair attempts ({})",
job.job_id, self.max_repair_attempts
),
});
}
// Try to recover the job
let result = self
.context_manager
.update_context(job.job_id, |ctx| ctx.attempt_recovery())
.await;
match result {
Ok(Ok(())) => {
tracing::info!("Successfully recovered job {}", job.job_id);
Ok(RepairResult::Success {
message: format!("Job {} recovered and will be retried", job.job_id),
})
}
Ok(Err(e)) => {
tracing::warn!("Failed to recover job {}: {}", job.job_id, e);
Ok(RepairResult::Retry {
message: format!("Recovery attempt failed: {}", e),
})
}
Err(e) => Err(RepairError::Failed {
target_type: "job".to_string(),
target_id: job.job_id,
reason: e.to_string(),
}),
}
}
async fn detect_broken_tools(&self) -> Vec<BrokenTool> {
let Some(ref store) = self.store else {
return vec![];
};
// Threshold: 5 failures before considering a tool broken
match store.get_broken_tools(5).await {
Ok(tools) => {
if !tools.is_empty() {
tracing::info!("Detected {} broken tools needing repair", tools.len());
}
tools
}
Err(e) => {
tracing::warn!("Failed to detect broken tools: {}", e);
vec![]
}
}
}
async fn repair_broken_tool(&self, tool: &BrokenTool) -> Result<RepairResult, RepairError> {
let Some(ref builder) = self.builder else {
return Ok(RepairResult::ManualRequired {
message: format!("Builder not available for repairing tool '{}'", tool.name),
});
};
let Some(ref store) = self.store else {
return Ok(RepairResult::ManualRequired {
message: "Store not available for tracking repair".to_string(),
});
};
// Check repair attempt limit
if tool.repair_attempts >= self.max_repair_attempts {
return Ok(RepairResult::ManualRequired {
message: format!(
"Tool '{}' exceeded max repair attempts ({})",
tool.name, self.max_repair_attempts
),
});
}
tracing::info!(
"Attempting to repair tool '{}' (attempt {})",
tool.name,
tool.repair_attempts + 1
);
// Increment repair attempts
if let Err(e) = store.increment_repair_attempts(&tool.name).await {
tracing::warn!("Failed to increment repair attempts: {}", e);
}
// Create BuildRequirement for repair
let requirement = BuildRequirement {
name: tool.name.clone(),
description: format!(
"Repair broken WASM tool.\n\n\
Tool name: {}\n\
Previous error: {}\n\
Failure count: {}\n\n\
Analyze the error, fix the implementation, and rebuild.",
tool.name,
tool.last_error.as_deref().unwrap_or("Unknown error"),
tool.failure_count
),
software_type: SoftwareType::WasmTool,
language: Language::Rust,
input_spec: None,
output_spec: None,
dependencies: vec![],
capabilities: vec!["http".to_string(), "workspace".to_string()],
};
// Attempt to build/repair
match builder.build(&requirement).await {
Ok(result) if result.success => {
tracing::info!(
"Successfully rebuilt tool '{}' after {} iterations",
tool.name,
result.iterations
);
// Mark as repaired in database
if let Err(e) = store.mark_tool_repaired(&tool.name).await {
tracing::warn!("Failed to mark tool as repaired: {}", e);
}
// Log if the tool was auto-registered
if result.registered {
tracing::info!("Repaired tool '{}' auto-registered", tool.name);
}
Ok(RepairResult::Success {
message: format!(
"Tool '{}' repaired successfully after {} iterations",
tool.name, result.iterations
),
})
}
Ok(result) => {
// Build completed but failed
tracing::warn!(
"Repair build for '{}' completed but failed: {:?}",
tool.name,
result.error
);
Ok(RepairResult::Retry {
message: format!(
"Repair attempt {} for '{}' failed: {}",
tool.repair_attempts + 1,
tool.name,
result.error.unwrap_or_else(|| "Unknown error".to_string())
),
})
}
Err(e) => {
tracing::error!("Repair build for '{}' errored: {}", tool.name, e);
Ok(RepairResult::Retry {
message: format!("Repair build error: {}", e),
})
}
}
}
}
/// Background repair task that periodically checks for and repairs issues.
pub struct RepairTask {
repair: Arc<dyn SelfRepair>,
check_interval: Duration,
}
impl RepairTask {
/// Create a new repair task.
pub fn new(repair: Arc<dyn SelfRepair>, check_interval: Duration) -> Self {
Self {
repair,
check_interval,
}
}
/// Run the repair task.
pub async fn run(&self) {
loop {
tokio::time::sleep(self.check_interval).await;
// Check for stuck jobs
let stuck_jobs = self.repair.detect_stuck_jobs().await;
for job in stuck_jobs {
tracing::info!("Attempting to repair stuck job {}", job.job_id);
match self.repair.repair_stuck_job(&job).await {
Ok(RepairResult::Success { message }) => {
tracing::info!("Repair succeeded: {}", message);
}
Ok(RepairResult::Retry { message }) => {
tracing::warn!("Repair needs retry: {}", message);
}
Ok(RepairResult::Failed { message }) => {
tracing::error!("Repair failed: {}", message);
}
Ok(RepairResult::ManualRequired { message }) => {
tracing::warn!("Manual intervention needed: {}", message);
}
Err(e) => {
tracing::error!("Repair error: {}", e);
}
}
}
// Check for broken tools
let broken_tools = self.repair.detect_broken_tools().await;
for tool in broken_tools {
tracing::info!("Attempting to repair broken tool: {}", tool.name);
match self.repair.repair_broken_tool(&tool).await {
Ok(result) => {
tracing::info!("Tool repair result: {:?}", result);
}
Err(e) => {
tracing::error!("Tool repair error: {}", e);
}
}
}
}
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_repair_result_variants() {
let success = RepairResult::Success {
message: "OK".to_string(),
};
assert!(matches!(success, RepairResult::Success { .. }));
let manual = RepairResult::ManualRequired {
message: "Help needed".to_string(),
};
assert!(matches!(manual, RepairResult::ManualRequired { .. }));
}
// === QA Plan - Self-repair stuck job tests ===
#[tokio::test]
async fn detect_no_stuck_jobs_when_all_healthy() {
let cm = Arc::new(ContextManager::new(10));
// Create a job and leave it Pending (not stuck).
cm.create_job("Job 1", "desc").await.unwrap();
let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3);
let stuck = repair.detect_stuck_jobs().await;
assert!(stuck.is_empty());
}
#[tokio::test]
async fn detect_stuck_job_finds_stuck_state() {
let cm = Arc::new(ContextManager::new(10));
let job_id = cm.create_job("Stuck job", "desc").await.unwrap();
// Transition to InProgress, then to Stuck.
cm.update_context(job_id, |ctx| ctx.transition_to(JobState::InProgress, None))
.await
.unwrap()
.unwrap();
cm.update_context(job_id, |ctx| {
ctx.transition_to(JobState::Stuck, Some("timed out".to_string()))
})
.await
.unwrap()
.unwrap();
let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3);
let stuck = repair.detect_stuck_jobs().await;
assert_eq!(stuck.len(), 1);
assert_eq!(stuck[0].job_id, job_id);
}
#[tokio::test]
async fn repair_stuck_job_succeeds_within_limit() {
let cm = Arc::new(ContextManager::new(10));
let job_id = cm.create_job("Repairable", "desc").await.unwrap();
// Move to InProgress -> Stuck.
cm.update_context(job_id, |ctx| ctx.transition_to(JobState::InProgress, None))
.await
.unwrap()
.unwrap();
cm.update_context(job_id, |ctx| ctx.transition_to(JobState::Stuck, None))
.await
.unwrap()
.unwrap();
let repair = DefaultSelfRepair::new(Arc::clone(&cm), Duration::from_secs(60), 3);
let stuck_job = StuckJob {
job_id,
last_activity: Utc::now(),
stuck_duration: Duration::from_secs(120),
last_error: None,
repair_attempts: 0,
};
let result = repair.repair_stuck_job(&stuck_job).await.unwrap();
assert!(
matches!(result, RepairResult::Success { .. }),
"Expected Success, got: {:?}",
result
);
// Job should be back to InProgress after recovery.
let ctx = cm.get_context(job_id).await.unwrap();
assert_eq!(ctx.state, JobState::InProgress);
}
#[tokio::test]
async fn repair_stuck_job_returns_manual_when_limit_exceeded() {
let cm = Arc::new(ContextManager::new(10));
let job_id = cm.create_job("Unrepairable", "desc").await.unwrap();
let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 2);
let stuck_job = StuckJob {
job_id,
last_activity: Utc::now(),
stuck_duration: Duration::from_secs(300),
last_error: Some("persistent failure".to_string()),
repair_attempts: 2, // == max
};
let result = repair.repair_stuck_job(&stuck_job).await.unwrap();
assert!(
matches!(result, RepairResult::ManualRequired { .. }),
"Expected ManualRequired, got: {:?}",
result
);
}
#[tokio::test]
async fn detect_broken_tools_returns_empty_without_store() {
let cm = Arc::new(ContextManager::new(10));
let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3);
// No store configured, should return empty.
let broken = repair.detect_broken_tools().await;
assert!(broken.is_empty());
}
#[tokio::test]
async fn repair_broken_tool_returns_manual_without_builder() {
let cm = Arc::new(ContextManager::new(10));
let repair = DefaultSelfRepair::new(cm, Duration::from_secs(60), 3);
let broken = BrokenTool {
name: "test-tool".to_string(),
failure_count: 10,
last_error: Some("crash".to_string()),
first_failure: Utc::now(),
last_failure: Utc::now(),
last_build_result: None,
repair_attempts: 0,
};
let result = repair.repair_broken_tool(&broken).await.unwrap();
assert!(
matches!(result, RepairResult::ManualRequired { .. }),
"Expected ManualRequired without builder, got: {:?}",
result
);
}
}