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
+12 -6
View File
@@ -56,6 +56,7 @@ pub struct AppComponents {
pub session: Arc<SessionManager>,
pub catalog_entries: Vec<crate::extensions::RegistryEntry>,
pub dev_loaded_tool_names: Vec<String>,
pub builder: Option<Arc<dyn crate::tools::SoftwareBuilder>>,
}
/// Options that control optional init phases.
@@ -280,6 +281,7 @@ impl AppBuilder {
Arc<ToolRegistry>,
Option<Arc<dyn EmbeddingProvider>>,
Option<Arc<Workspace>>,
Option<Arc<dyn crate::tools::SoftwareBuilder>>,
),
anyhow::Error,
> {
@@ -367,16 +369,19 @@ impl AppBuilder {
}
// Register builder tool if enabled
if self.config.builder.enabled
let builder = if self.config.builder.enabled
&& (self.config.agent.allow_local_tools || !self.config.sandbox.enabled)
{
tools
let b = tools
.register_builder_tool(llm.clone(), Some(self.config.builder.to_builder_config()))
.await;
tracing::debug!("Builder mode enabled");
}
tracing::info!("Builder mode enabled");
Some(b)
} else {
None
};
Ok((safety, tools, embeddings, workspace))
Ok((safety, tools, embeddings, workspace, builder))
}
/// Phase 5: Load WASM tools, MCP servers, and create extension manager.
@@ -699,7 +704,7 @@ impl AppBuilder {
} else {
self.init_llm().await?
};
let (safety, tools, embeddings, workspace) = self.init_tools(&llm).await?;
let (safety, tools, embeddings, workspace, builder) = self.init_tools(&llm).await?;
// Create hook registry early so runtime extension activation can register hooks.
let hooks = Arc::new(HookRegistry::new());
@@ -819,6 +824,7 @@ impl AppBuilder {
session: self.session,
catalog_entries,
dev_loaded_tool_names,
builder,
})
}
}