feat(self-repair): wire stuck_threshold, store, and builder (#712)

* feat(self-repair): wire stuck_threshold, store, and builder (#647)

Wire the previously dead-code fields in DefaultSelfRepair:

- stuck_threshold: detect_stuck_jobs() now filters by duration, only
  reporting jobs stuck longer than the configured threshold
- with_store(): wired in agent_loop.rs from AgentDeps.store for
  tool failure tracking via Database trait
- with_builder(): wired from register_builder_tool() return value
  through AppComponents and AgentDeps for automatic tool rebuilding
- tools: passed alongside builder for hot-reload logging

Remove all #[allow(dead_code)] annotations. Add regression tests for
threshold-based filtering (both above and below threshold).

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

* fix: add missing `builder` field to AgentDeps in gateway workflow harness

After rebase onto staging, AgentDeps gained a `builder` field for
self-repair tool rebuilding. The gateway workflow test harness was
missing this field, causing CI compilation failure.

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

* ci: retrigger CI

* fix: force CI refresh after path_routing_tests dedup

* test: add E2E test for stuck job repair and tool rebuild cycle

Tests the full self-repair flow requested in review:
1. Job transitions Pending -> InProgress -> Stuck
2. detect_stuck_jobs() finds it (zero threshold)
3. repair_stuck_job() recovers it back to InProgress
4. A broken tool is repaired via MockBuilder
5. Verify builder was invoked and repair succeeded

Uses a MockBuilder (impl SoftwareBuilder) that returns successful
BuildResult without requiring an LLM or filesystem. Uses libsql
test database for the store (increment_repair_attempts, mark_tool_repaired).

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(self-repair): measure stuck_duration from Stuck transition, not started_at

- Use ctx.transitions to find the most recent Stuck transition timestamp
  instead of ctx.started_at (which reflects job start, not stuck time)
- Fix StuckJob.last_activity to use stuck transition timestamp
- Remove misleading "hot-reloaded into registry" log
- Remove stray "// ci fix" comment in memory.rs
- Add regression test: backdated started_at must not inflate stuck_duration

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

* ci: re-trigger CI with latest changes

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

* fix: add type annotation to Ok(()) in test to resolve E0282

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

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Zaki Manian
2026-03-18 20:51:21 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent c8ee55ed19
commit 3dcccc1e64
9 changed files with 297 additions and 30 deletions
+8 -5
View File
@@ -13,7 +13,9 @@ use crate::orchestrator::job_manager::ContainerJobManager;
use crate::secrets::SecretsStore;
use crate::skills::catalog::SkillCatalog;
use crate::skills::registry::SkillRegistry;
use crate::tools::builder::{BuildSoftwareTool, BuilderConfig, LlmSoftwareBuilder};
use crate::tools::builder::{
BuildSoftwareTool, BuilderConfig, LlmSoftwareBuilder, SoftwareBuilder,
};
use crate::tools::builtin::{
ApplyPatchTool, CancelJobTool, CreateJobTool, EchoTool, ExtensionInfoTool, HttpTool,
JobEventsTool, JobPromptTool, JobStatusTool, JsonTool, ListDirTool, ListJobsTool,
@@ -576,22 +578,23 @@ impl ToolRegistry {
self: &Arc<Self>,
llm: Arc<dyn LlmProvider>,
config: Option<BuilderConfig>,
) {
) -> Arc<dyn SoftwareBuilder> {
// First register dev tools needed by the builder
self.register_dev_tools();
// Create the builder (arg order: config, llm, tools)
let builder = Arc::new(LlmSoftwareBuilder::new(
let builder: Arc<dyn SoftwareBuilder> = Arc::new(LlmSoftwareBuilder::new(
config.unwrap_or_default(),
llm,
Arc::clone(self),
));
// Register the build_software tool
self.register(Arc::new(BuildSoftwareTool::new(builder)))
self.register(Arc::new(BuildSoftwareTool::new(Arc::clone(&builder))))
.await;
tracing::debug!("Registered software builder tool");
tracing::info!("Registered software builder tool");
builder
}
/// Register a WASM tool from bytes.