mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-09-01 09:09:19 +00:00
fix: persist turns after approval and add agent-level tests (#250)
* fix: persist turns after approval and add agent-level tests Port relevant changes from PR #112 that were not carried over to #237: - Add persist_turn calls in process_approval for the response, error, and auth-required paths. Previously, turns completed after tool approval were never persisted to DB — if the process crashed after approval the entire turn (user message + assistant response) was lost. - Add agent-level unit tests: StaticLlmProvider mock, make_test_agent helper, tests for auto-approval logic, destructive shell command detection, and PendingApproval backward-compatible deserialization (without deferred_tool_calls field). - Remove unused _thread_state binding in process_approval. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address 14 audit findings in src/agent/ Audit of the agent module found 2 High, 7 Medium, 3 Low, and 2 Nit severity issues. This commit fixes all of them: High: - Remove 4 `.expect()` calls in session.rs (entry API, match, direct indexing, if-let) to eliminate panic paths in production - Add typed RoutineError enum replacing Result<_, String> across routine.rs, routine_engine.rs, and callers in history/store.rs and db/libsql/mod.rs Medium: - Sanitize routine names in path construction to prevent directory traversal (routine_engine.rs) - Log warnings for 5 silently-swallowed errors in scheduler.rs, compaction.rs, and worker.rs - Extract shared handle_auth_intercept helper to deduplicate auth interception in thread_ops.rs - Add session count warning threshold in session_manager.rs - Make FullJob stub degradation visible via warn-level log and prepended warning in output Low: - Restrict dead code visibility with #[cfg(test)] on 19 unused items in submission.rs, task.rs, and undo.rs - Narrow pub to pub(crate) on self_repair.rs builder methods - Remove TaskStatus from mod.rs re-exports (test-only type) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments - Reorder persist_turn before persist_response_chain so the conversation row exists before the metadata UPDATE runs - Add persist_response_chain call to handle_auth_intercept so auth-required paths preserve the response chain - Harden sanitize_routine_name to use allowlist (alphanumeric, dash, underscore) instead of denylist replacements - Fix stale active_thread ID in get_or_create_thread: fall back to create_thread() when the stored ID is missing from the map - Persist turn on approval rejection so user messages survive crashes after a tool is rejected Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
co-authored by
Claude Opus 4.6
parent
97a7637f30
commit
3f135bdde9
+47
-24
@@ -505,7 +505,8 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
|
||||
let output_str = serde_json::to_string_pretty(&output.result)
|
||||
.ok()
|
||||
.map(|s| deps.safety.sanitize_tool_output(tool_name, &s).content);
|
||||
deps.context_manager
|
||||
match deps
|
||||
.context_manager
|
||||
.update_memory(job_id, |mem| {
|
||||
let rec = mem.create_action(tool_name, params.clone()).succeed(
|
||||
output_str.clone(),
|
||||
@@ -516,30 +517,52 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
|
||||
rec
|
||||
})
|
||||
.await
|
||||
.ok()
|
||||
{
|
||||
Ok(rec) => Some(rec),
|
||||
Err(e) => {
|
||||
tracing::warn!(job_id = %job_id, tool = tool_name, "Failed to record action in memory: {e}");
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(Err(e)) => {
|
||||
match deps
|
||||
.context_manager
|
||||
.update_memory(job_id, |mem| {
|
||||
let rec = mem
|
||||
.create_action(tool_name, params.clone())
|
||||
.fail(e.to_string(), elapsed);
|
||||
mem.record_action(rec.clone());
|
||||
rec
|
||||
})
|
||||
.await
|
||||
{
|
||||
Ok(rec) => Some(rec),
|
||||
Err(e) => {
|
||||
tracing::warn!(job_id = %job_id, tool = tool_name, "Failed to record action in memory: {e}");
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
Err(_) => {
|
||||
match deps
|
||||
.context_manager
|
||||
.update_memory(job_id, |mem| {
|
||||
let rec = mem
|
||||
.create_action(tool_name, params.clone())
|
||||
.fail("Execution timeout", elapsed);
|
||||
mem.record_action(rec.clone());
|
||||
rec
|
||||
})
|
||||
.await
|
||||
{
|
||||
Ok(rec) => Some(rec),
|
||||
Err(e) => {
|
||||
tracing::warn!(job_id = %job_id, tool = tool_name, "Failed to record action in memory: {e}");
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(Err(e)) => deps
|
||||
.context_manager
|
||||
.update_memory(job_id, |mem| {
|
||||
let rec = mem
|
||||
.create_action(tool_name, params.clone())
|
||||
.fail(e.to_string(), elapsed);
|
||||
mem.record_action(rec.clone());
|
||||
rec
|
||||
})
|
||||
.await
|
||||
.ok(),
|
||||
Err(_) => deps
|
||||
.context_manager
|
||||
.update_memory(job_id, |mem| {
|
||||
let rec = mem
|
||||
.create_action(tool_name, params.clone())
|
||||
.fail("Execution timeout", elapsed);
|
||||
mem.record_action(rec.clone());
|
||||
rec
|
||||
})
|
||||
.await
|
||||
.ok(),
|
||||
};
|
||||
|
||||
// Persist action to database (fire-and-forget)
|
||||
|
||||
Reference in New Issue
Block a user