mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-29 08:59:31 +00:00
feat/gemini-cli-oauth
7
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
+7 ironclaw-ci[bot]GitHubNick PismenkovClaude Haiku 4.5Henry ParkIllia PolosukhinXing JiNick StebbingsReidUmesh Kumar Singh智方云cubecloud-iolizicanlizican123Zaki Manianreidliu41ironclaw-ci[bot] <266877842+ironclaw-ci[bot]@users.noreply.github.com>Copilot |
a677b20701 |
chore: promote staging to main (2026-03-10 15:19 UTC) (#865)
* fix: Channel HTTP: server doesn't start after config change (no hot-r… (#779)
* fix: Channel HTTP: server doesn't start after config change (no hot-reload)
* review fixes
* review fixes
* fix linter
* fix code style
* fix: prevent session lock contention blocking message processing (#783)
* fix: prevent session lock contention blocking message processing
## Problem
After container restart, POST /api/chat/send returns 202 ACCEPTED but messages
don't appear in conversation_messages and agent never responds. Messages get
stuck in "stale state" after restart.
Root cause: Session lock was held for entire duration of chat_threads_handler
and chat_history_handler, including during slow database queries. This blocked
the agent loop from acquiring the session lock to process incoming messages,
causing them to hang indefinitely.
## Solution
1. **Release session lock early in chat_threads_handler**: Only acquire lock
when reading active_thread at response time, not during DB queries for
thread list. DB operations no longer block message processing.
2. **Release session lock early in chat_history_handler**: Only acquire lock
when accessing in-memory thread state, not during paginated DB queries or
thread ownership checks. DB operations no longer block message processing.
3. **Add comprehensive logging**: Track message flow from receipt through
session resolution, thread hydration, and state transitions. Helps diagnose
future issues:
- Message queued to agent loop (chat_send_handler)
- Processing message from channel (handle_message)
- Hydrating thread from DB (maybe_hydrate_thread)
- Resolving session and thread (resolve_thread)
- Checking thread state (process_user_input)
- Persisting user message (persist_user_message)
## Impact
- Message processing no longer blocks on session lock contention
- API response times for thread list/history queries unaffected (DB queries
still happen, but lock is not held)
- Better diagnostics for future debugging
## Testing
- All 2756 tests pass
- Code compiles with zero clippy warnings
- No changes to user-facing API or behavior, only lock timing
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* security: redact PII from info-level logs
Downgrade user_id and channel logging to debug level to prevent exposing
Personally Identifiable Information (PII) in production logs.
The user_id field can contain sensitive information such as phone numbers
(e.g., for Signal messages). Logging PII in cleartext at the info level
creates a security and privacy risk, as these logs may be stored in
persistent storage, indexed by log management systems, or accessible to
unauthorized personnel.
Changes:
- Info level: logs only message_id (UUID) for tracking
- Debug level: logs user_id, channel, thread_id for troubleshooting
This maintains debugging capability for developers while protecting user
privacy in production logs.
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
---------
Co-authored-by: Claude Haiku 4.5 <[email protected]>
* chore: sync main into staging (#855)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat(llm): per-provider unsupported parameter filtering (#749, #728) (#809)
Add declarative `unsupported_params` field to provider definitions in
providers.json. Parameters listed are stripped from requests before
sending, preventing 400 errors from providers that reject them (e.g.
gpt-5 family and kimi-k2.5 rejecting custom temperature values).
- Add `unsupported_params` to ProviderDefinition and RegistryProviderConfig
- Propagate from registry through config resolution
- Generic strip helpers handle temperature, max_tokens, stop_sequences
- Apply filtering in RigAdapter and AnthropicOAuthProvider
- Mark openai and tinfoil providers as unsupporting temperature
- Update openai default model to gpt-5-mini
Co-authored-by: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
* fix: Chat input is hidden in mobile browser mode (#877)
* fix: stop XML-escaping tool output content (#598) (#874)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat(llm): per-provider unsupported parameter filtering (#749, #728) (#809)
Add declarative `unsupported_params` field to provider definitions in
providers.json. Parameters listed are stripped from requests before
sending, preventing 400 errors from providers that reject them (e.g.
gpt-5 family and kimi-k2.5 rejecting custom temperature values).
- Add `unsupported_params` to ProviderDefinition and RegistryProviderConfig
- Propagate from registry through config resolution
- Generic strip helpers handle temperature, max_tokens, stop_sequences
- Apply filtering in RigAdapter and AnthropicOAuthProvider
- Mark openai and tinfoil providers as unsupporting temperature
- Update openai default model to gpt-5-mini
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix: stop XML-escaping tool output content in wrap_for_llm (#598)
Remove content escaping that corrupted JSON in tool output. The
<tool_output> structural boundary is preserved but content now passes
through raw, fixing downstream parse failures.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(safety): allow empty string tool params (#848)
* fix(safety): allow empty string tool params
* fix(safety): preserve heuristic checks and add path context to tool validation
This follow-up refactor addresses PR review feedback by restoring
heuristic checks (whitespace ratio, character repetition) for tool
parameter validation and improving error reporting.
Changes:
- Restored heuristic warnings in validate_non_empty_input so they apply
to both user input and tool parameters (when non-empty).
- Refactored check_strings to recursively build and pass JSON paths
(e.g., "metadata.tags[1]").
- Updated validation errors to use the specific JSON path as the field
name instead of the generic "input".
- Added regression tests for whitespace/repetition warnings and JSON
path reporting in tool parameters.
This ensures the safety layer remains semantically neutral about empty
strings (fixing the memory_tree path: "" issue) while maintaining
rigorous protection and providing better developer ergonomics.
* style: run cargo fmt
* perf: optimize release and dist build profiles (#843)
* perf: optimize release and dist build profiles
Add [profile.release] with strip=true and panic="abort" for smaller,
faster release binaries. Upgrade [profile.dist] from lto="thin" to
lto="fat" with codegen-units=1 for maximum optimization in CI releases.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove panic=abort from release profile
Reviewers (zmanian, Copilot, Gemini) correctly flagged that panic=abort
in the release profile would kill the entire process on any tokio task
panic, breaking fault isolation for the long-running server. Removed
from release profile entirely.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: add PR template with risk assessment (#837)
* feat: add PR template with risk assessment and review tracks
Add a pull request template that includes summary, change type,
validation checklist, security/database impact sections, blast radius,
and rollback plan. Update CONTRIBUTING.md with review track definitions
(A/B/C) based on change risk level.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: expand CONTRIBUTING.md with setup, workflow, and guidelines
Add getting started, development workflow, code style summary,
database change guidance, and dependency management sections.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: add fuzzing targets for untrusted input parsers (#835)
* feat: add fuzzing targets for untrusted input parsers
Add cargo-fuzz infrastructure with 5 fuzz targets exercising
security-critical code paths:
- fuzz_safety_sanitizer: Aho-Corasick + regex injection detection
- fuzz_safety_validator: Input validation (length, encoding, patterns)
- fuzz_leak_detector: Secret leak scanning (API keys, tokens)
- fuzz_tool_params: Tool parameter JSON validation
- fuzz_config_env: TOML/JSON config parsing
Each target exercises real IronClaw business logic with invariant
assertions. Includes corpus directories and setup documentation.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: improve fuzz targets to exercise real IronClaw code paths
- fuzz_config_env: exercise SafetyLayer end-to-end (sanitize, validate,
policy check) instead of generic TOML/JSON parsing
- fuzz_tool_params: add validate_tool_schema coverage alongside
validate_tool_params
- Add "fuzz" to workspace exclude in root Cargo.toml
- Update README descriptions to match actual target behavior
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: replace redundant detect() call with meaningful invariant assertion
Replace the double sanitize()+detect() call with an assertion that
critical severity warnings always trigger content modification.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: rewrite fuzz_config_env to exercise IronClaw safety code directly
Replace SafetyLayer wrapper usage with direct Sanitizer, Validator, and
LeakDetector instantiation and invocation. Adds meaningful consistency
assertions (non-empty output, valid-means-no-errors, scan/clean agreement).
Removes the config construction that was only exercising struct instantiation.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(wasm): run leak scan before credential injection in tools wrapper (#791)
* fix(wasm): run leak scan before credential injection in tools wrapper
The tools WASM wrapper runs the LeakDetector on HTTP request headers
AFTER inject_host_credentials() has already substituted real secrets
(e.g., xoxb- Slack bot tokens). This causes the leak detector to
flag the tool's own legitimate outbound API calls as secret exfiltration.
Move the scan to run on raw_headers before any credential injection,
matching the fix already applied to the channels wrapper in #421.
Fixes the same class of bug as #421 (which only fixed channels/wasm/wrapper.rs).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* perf: inline leak scan to avoid Vec allocation on every HTTP request
Address review feedback: instead of cloning all header keys/values into
a Vec to pass to scan_http_request(), iterate over raw_headers directly
using scan_and_clean(). This also provides more specific error messages
(URL vs header vs body).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: fix cargo fmt formatting in leak scan loop
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(setup): drain residual terminal events before secret input (#747) (#849)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat(llm): per-provider unsupported parameter filtering (#749, #728) (#809)
Add declarative `unsupported_params` field to provider definitions in
providers.json. Parameters listed are stripped from requests before
sending, preventing 400 errors from providers that reject them (e.g.
gpt-5 family and kimi-k2.5 rejecting custom temperature values).
- Add `unsupported_params` to ProviderDefinition and RegistryProviderConfig
- Propagate from registry through config resolution
- Generic strip helpers handle temperature, max_tokens, stop_sequences
- Apply filtering in RigAdapter and AnthropicOAuthProvider
- Mark openai and tinfoil providers as unsupporting temperature
- Update openai default model to gpt-5-mini
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix: skip the regression check
[skip-regression-check]
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
* feat(agent): add context size logging before LLM prompt (#810)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat(agent): add context size logging before LLM prompt
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
* fix: preserve text before tool-call XML in forced-text responses (#852)
* fix: preserve text before tool-call XML in forced-text responses (#789)
Local models (Qwen3, DeepSeek, GLM) emit <tool_call> XML even when no
tools are available (force_text mode). The existing strip_xml_tag()
discards everything from an unclosed opening tag onward, producing an
empty string that triggers the "I'm not sure how to respond" fallback.
Add truncate_at_tool_tags() — a code-region-aware pre-processing step
that truncates at the first tool-call XML tag BEFORE clean_response()
runs, preserving all useful text before the tag. Protect all 7
clean_response() call sites. Case-insensitive matching handles models
that emit <TOOL_CALL> or <Tool_Call> variants.
Secondary fix: add has_native_thinking() model detection to skip
<think>/<final> system prompt injection for models with built-in
reasoning (Qwen3, QwQ, DeepSeek-R1, GLM-Z1, etc.), preventing
thinking-only responses that clean to empty.
Wire with_model_name(active_model_name()) at all 9 production sites
that construct Reasoning, so the runtime model name (not static config)
drives system prompt generation.
126 new/updated tests covering truncation edge cases, code-block
awareness, Unicode, case-insensitivity, StubLlm integration for
complete/plan/evaluate_success/respond_with_tools paths, model
detection, and conditional system prompt generation.
Closes #789
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address Copilot review — unclosed-only truncation, ASCII case folding
- truncate_at_tool_tags() now only truncates at UNCLOSED tool tags;
properly closed tags (e.g. <tool_call>...</tool_call>) are left intact
for clean_response() to strip normally, preserving any text after them
- Switch from to_lowercase() to to_ascii_lowercase() to prevent byte
offset misalignment with non-ASCII characters whose lowercase form
has different byte length (e.g. Kelvin sign U+212A)
- Add closing_tag_for() helper to derive closing tags from open patterns
- Fix doc comment: "fenced markdown code blocks or inline code spans"
(not "indented", which find_code_regions() doesn't detect)
- Add regression tests: closed vs unclosed for each tag variant,
Unicode + case-insensitive offset safety, and mixed closed/unclosed
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: minor review items — consistent ascii_lowercase, closing_tag_for tests
- Switch has_native_thinking() from to_lowercase() to to_ascii_lowercase()
for consistency with truncate_at_tool_tags() approach
- Add unit tests for closing_tag_for(): standard tags, space-suffixed
patterns, pipe-delimited tags, and exhaustive coverage of all
TOOL_TAG_PATTERNS entries
- Add test for mixed closed+unclosed tags of different types
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* Feat/docker shell edition (#804)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(mcp): strip top-level null params before forwarding to MCP servers (#795)
* feat(llm): per-provider unsupported parameter filtering (#749, #728) (#809)
Add declarative `unsupported_params` field to provider definitions in
providers.json. Parameters listed are stripped from requests before
sending, preventing 400 errors from providers that reject them (e.g.
gpt-5 family and kimi-k2.5 rejecting custom temperature values).
- Add `unsupported_params` to ProviderDefinition and RegistryProviderConfig
- Propagate from registry through config resolution
- Generic strip helpers handle temperature, max_tokens, stop_sequences
- Apply filtering in RigAdapter and AnthropicOAuthProvider
- Mark openai and tinfoil providers as unsupporting temperature
- Update openai default model to gpt-5-mini
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(mcp): strip top-level null params before forwarding to MCP servers
LLMs frequently emit `"field": null` for optional parameters in tool
calls. Many MCP servers reject explicit nulls for fields that should
simply be absent — e.g. Notion returns 400 for `"sort": null` in a
search call, expecting the field to be omitted entirely.
Strip top-level null keys from the params object before calling
`call_tool()`. Only top-level keys are stripped; nested nulls are
preserved since they may be semantically meaningful.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Illia Polosukhin <[email protected]>
Co-authored-by: Claude Opus 4.6 <[email protected]>
* Add event-triggered routines and workflow skill templates (#756)
* Add event-triggered routines and workflow skill templates
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix: address PR review feedback for event_emit security and quality
Security fixes:
- Require approval (UnlessAutoApproved) for event_emit, matching routine_fire
- Enable sanitization on event_emit payload (external JSON reaches LLM)
- Remove user_id parameter from event_emit to prevent IDOR — always use ctx.user_id
Correctness fixes:
- Rename source → event_source in event_emit for consistency with routine_create
- Use json_value_as_filter_string for filter parsing (handles numbers/booleans)
- Case-insensitive matching for event source and event_type
- Add debug logging for missing filter keys in payload
- Fix skill_install_routine_webhook_sim test missing .with_skills()
- Fix schema_validator test for event_emit payload properties
Code quality:
- Move EventEmitTool struct/impl after RoutineHistoryTool (fix split layout)
- Deduplicate routine_to_info into RoutineInfo::from_routine in types.rs
- Add test section headers in e2e_routine_heartbeat.rs
- Clarify event_emit description to specify system_event routines only
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix: make routine_system_event_emit test create routine before emitting
- Add routine_create step to trace fixture so event_emit has a matching
routine to fire
- Assert fired_routines > 0, not just key presence (Copilot review)
- Add .with_auto_approve_tools(true) since event_emit now requires approval
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: renumber test headers after system_event test insertion
Test 4 was duplicated (routine_cooldown and heartbeat_findings).
Renumber heartbeat_findings to Test 5 and heartbeat_empty_skip to Test 6.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: merge staging and add missing RoutineEngine args in test
RoutineEngine::new on staging requires `tools` and `safety` params.
Update system_event_trigger_matches_and_filters test to pass them.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address new Copilot review comments
- Add .with_auto_approve_tools(true) to skill_install_routine_webhook_sim
test so event_emit doesn't block on approval
- Fix module-level doc comment for event_emit to specify system_event trigger
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: deduplicate json_value_as_string helper
Remove private `json_value_as_string` from routine_engine.rs and use
the identical public `json_value_as_filter_string` from routine.rs,
eliminating divergence risk. (Copilot review)
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix: enable WASM credential injection in No-DB environments (#845)
* fix(wasm): enable credential injection in no-DB environments via env var fallback
When a secrets store is unavailable (e.g. no-DB mode), WASM channel
credentials were silently not injected, causing channels to start without
credentials. Fix by:
- Changing `inject_channel_credentials_from_secrets` to accept
`Option<&dyn SecretsStore>` — secrets store is tried first when present
- Adding env var fallback (`inject_env_credentials`) for credentials not
covered by the secrets store
- Enforcing a channel-name prefix security check on env var names to
prevent WASM channels from reading unrelated host credentials
(e.g. `AWS_SECRET_ACCESS_KEY`)
- Extracting pure `resolve_env_credentials` helper for testability
- Adding case-insensitive prefix matching for secrets store lookup
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
* fix(wasm): inject credentials at startup when no secrets store (setup.rs path)
The startup path (setup_wasm_channels -> register_channel) was guarded by
`if let Some(secrets) = secrets_store`, so in No-DB mode credentials were
never injected and the channel started without them.
Fix by:
- Changing inject_channel_credentials to accept Option<&dyn SecretsStore>
- Always calling it (removing the if-let guard) — env var fallback runs
even when secrets_store is None
- Adding channel-name prefix security check to the env var fallback path
(e.g. TELEGRAM_ for channel "telegram"), consistent with manager.rs
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
* fix(test): correct misleading comment on ICTEST1_UNRELATED_OTHER placeholder
* fix(wasm): guard against empty channel name in credential injection
An empty channel_name would produce prefix "_", allowing any env var
starting with "_" to pass the security check and be injected. Add an
early-return guard in resolve_env_credentials, inject_env_credentials,
and inject_channel_credentials. Add a test to cover this path.
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
---------
Co-authored-by: lizican123 <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix: promote to main (#878)
* fix: replace unsafe env::set_var with thread-safe inject_single_var in SIGHUP handler
Fixes race condition where SIGHUP handler modifies global environment variables
while other threads may be reading them via Config::from_env().
Changes:
- Replace unsafe { std::env::set_var() } with ironclaw::config::inject_single_var()
- Uses INJECTED_VARS mutex instead of unsafe global state modification
- All reads via optional_env() check the thread-safe overlay first
- Prevents data races between SIGHUP reload and concurrent config reads
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* fix: spawn webhook restart as background task to avoid blocking I/O across lock
Prevents holding Mutex lock during async I/O operations (TcpListener::bind,
task shutdown). The SIGHUP handler no longer blocks webhook processing during
listener restart.
Changes:
- Read old_addr and drop lock immediately
- Spawn restart_with_addr() as background task via tokio::spawn
- Lock is only held during the actual restart operation, not the signal handler
Benefits:
- SIGHUP handler returns immediately without blocking
- Webhook requests not delayed by listener restart I/O
- Lock contention significantly reduced
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* fix: add graceful shutdown mechanism for SIGHUP handler background task
Prevents unbounded loop without cancellation token. The SIGHUP handler now
listens for a shutdown signal and exits cleanly during graceful termination.
Changes:
- Create broadcast channel for shutdown signaling
- SIGHUP handler uses tokio::select! to wait for shutdown or SIGHUP
- Send shutdown signal to all background tasks after agent.run() completes
- Ensures clean task lifecycle and no orphaned background tasks
Benefits:
- Proper task cancellation during graceful shutdown
- Follows Tokio best practices for background task management
- No background tasks orphaned when runtime shuts down
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* refactor: replace stringly-typed parameter filtering with typed enum and single helper
Fixes DRY violation where unsupported parameter filtering was duplicated across
rig_adapter.rs and anthropic_oauth.rs using string contains checks.
Changes:
- Add UnsupportedParam typed enum in provider.rs (Temperature, MaxTokens, StopSequences)
- Create strip_unsupported_completion_params() helper function
- Create strip_unsupported_tool_params() helper function
- Update rig_adapter.rs to use shared helpers
- Update anthropic_oauth.rs to use shared helpers
- Replace 60+ lines of duplicate stringly-typed logic
Benefits:
- Type safety: parameter names checked at compile time
- Single source of truth: adding a new param updates one place
- Reduced maintenance burden: no duplicate logic to keep in sync
- Better code clarity: named enum variant is self-documenting
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* docs: clarify intentional parameter asymmetry between completion and tool requests
Add documentation explaining why strip_unsupported_tool_params does not handle
StopSequences: the field doesn't exist in ToolCompletionRequest.
Changes:
- Add clarifying comments to strip_unsupported_tool_params()
- Explain why StopSequences is only in CompletionRequest
- Note that ToolCompletionRequest only supports Temperature and MaxTokens
- Inline comment confirms no action needed for StopSequences
This addresses the appearance of incomplete implementation without changing logic,
as the asymmetry is intentional and correct (ToolCompletionRequest lacks the field).
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* perf: isolate webhook_secret to reduce lock contention on hot path
Move webhook_secret from shared HttpChannelState RwLock into its own Arc<RwLock<>>.
This eliminates contention between secret validation and other state operations.
Changes:
- Change webhook_secret field type from RwLock<Option<SecretString>> to Arc<RwLock<Option<SecretString>>>
- Update initialization in HttpChannel::new()
- Update comments to explain isolation rationale
Benefits:
- Reduce lock contention on webhook request hot path (secret validation)
- Rarely-changing field (SIGHUP only) isolated from frequent state accesses
- Other state operations (tx, pending_responses) no longer wait behind secret reads
- Minimal code change: only field declaration and initialization
The Arc wrapper allows cloning the RwLock handle to separate concerns. With this
change, every webhook request acquires its own isolated lock for secret validation,
not the shared HttpChannelState lock. This scales better under high request volume.
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* fix: prevent partial state corruption on SIGHUP restart failure
Ensure atomicity of configuration reload: if webhook listener restart fails,
secret update is skipped to prevent inconsistent state.
Changes:
- Wait for restart_with_addr() to complete (don't spawn background task)
- Track restart result with restart_failed flag
- Only update secret if restart succeeded or wasn't needed
- Ensure listener and secret stay synchronized
Problem addressed:
- Before: restart spawned as background task, secret updated immediately
- If restart failed, secret was changed but listener still on old address
- This left system in inconsistent state (partial corruption)
Solution:
- Make restart blocking (SIGHUP handler can wait, it's not on request hot path)
- Atomically update secret only after successful restart
- Flag prevents race between restart and secret update
Benefits:
- Configuration changes are atomic (both succeed or both fail together)
- No partial state corruption on restart failure
- Failed restarts don't silently leave inconsistent state
- Secret and listener address stay in sync
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* refactor: generalize hot-secret-swapping with ChannelSecretUpdater trait
Decouple SIGHUP handler from HTTP channel internals by introducing a trait
for channels that support zero-downtime secret updates.
Changes:
- Add ChannelSecretUpdater trait in channels/channel.rs
- Implement ChannelSecretUpdater for HttpChannelState
- Export trait from channels module
- Update SIGHUP handler to use trait-based secret updater collection
- Replace explicit HTTP channel knowledge with generic updater loop
Benefits:
- SIGHUP handler no longer depends on HttpChannelState details
- Tight coupling removed: main.rs doesn't need HTTP channel imports
- Extensible: new channels can opt-in by implementing the trait
- Scalable: multiple channels supported without main.rs changes
- Maintainable: adding channels requires only trait implementation, not SIGHUP handler edits
Pattern:
- ChannelSecretUpdater trait defines the interface for all updaters
- Channels that support hot-secret-swapping implement the trait
- SIGHUP handler loops through all registered updaters generically
Verification:
- All 2,787 tests pass
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
* feat: validate parameter names at deserialization time, not just tests
Add custom serde deserializer for unsupported_params that validates parameter
names at runtime when loading providers.json (or user overrides).
Changes:
- Add unsupported_params_de module with custom deserializer
- Only allows: "temperature", "max_tokens", "stop_sequences"
- Invalid parameter names cause immediate deserialization error
- Update ProviderDefinition to use custom deserializer
- Enhanced test with explicit parameter name validation
- Add new test that verifies invalid parameters are rejected
Problem solved:
- Before: Invalid param names (e.g., "temperrature") silently ignored
- Now: Rejected at deserialization time with clear error message
- Prevents runtime failures caused by typos in configuration
Example error:
unsupported parameter name 'temperrature': must be one of: temperature, max_tokens, stop_sequences
Benefits:
- Fail-fast: errors caught when loading config, not at runtime
- Clear feedback: error message lists valid parameter names
- Type safety: validators run during deserialization
- Configuration errors detected immediately, not silently ignored
Verification:
- All 2,788 tests pass (including new validation test)
- Zero clippy warnings
- Code compiles successfully
Co-Authored-By: Claude Haiku 4.5 <[email protected]>
---------
Co-authored-by: Claude Haiku 4.5 <[email protected]>
* merge: resolve conflicts for PR #800 and #822 into staging (#881)
* fix(ci): secrets can't be used in step if conditions [skip-regression-check] (#787)
GitHub Actions step-level `if:` doesn't have access to `secrets` context.
Replace `if: secrets.X != ''` with `continue-on-error: true` and let
the Set token step handle the fallback.
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
* fix(ci): clean up staging pipeline — remove hacks, skip redundant checks [skip-regression-check] (#794)
- Remove continue-on-error from staging-ci.yml app token steps (secrets are configured)
- Skip test.yml and code_style.yml on PRs targeting staging (staging-ci.yml
already runs tests before promoting, promotion PR gets full CI on main)
- Allow ironclaw-ci[bot] in Claude Code review for bot-created promotion PRs
Co-authored-by: Claude Opus 4.6 <[email protected]>
* fix(ci): run fmt + clippy on staging PRs, skip Windows clippy [skip-regression-check] (#802)
- Remove branches:[main] filter from code_style.yml so it runs on all PRs
- Gate clippy-windows with `if: github.base_ref == 'main'` (skip on staging PRs)
- Update rollup job to allow skipped clippy-windows
- Simplify claude-review.yml to only trigger on labeled event (avoids duplicate runs)
Co-authored-by: Claude Opus 4.6 <[email protected]>
* feat: persist user_id in save_job and expose job_id on routine runs (#709)
* feat: persist worker events to DB and fix activity tab rendering
In-process Worker (used by Scheduler::dispatch_job) now persists events
via save_job_event at key execution points: plan creation, LLM
responses, tool_use, tool_result, and job completion/failure/stuck.
Event data shapes match the container worker format so the gateway
activity tab renders them correctly.
Frontend: tool_result errors now show a red X icon with danger styling
instead of a silent empty output. The result event falls back to the
error field when message is absent.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat: wire RoutineEngine into gateway for direct manual trigger firing
Replace the message-channel hack in routines_trigger_handler with a
direct call to RoutineEngine::fire_manual(), ensuring FullJob routines
dispatch correctly when triggered from the web UI. Inject the engine
into GatewayState from Agent::run after construction.
Also persists user_id in save_job for both PG and libSQL backends,
removes the source='sandbox' filter so all jobs are visible, and
exposes job_id on RoutineRunInfo for the frontend job link.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: remove stale gateway_state argument from Agent::new test call sites
The gateway_state parameter was removed from Agent::new during rebase
(replaced by post-construction set_routine_engine_slot), but three test
call sites still passed the extra None argument.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address PR review — restore sandbox source filter, remove blank lines
- Revert removal of `source = 'sandbox'` filter in all SandboxStore
queries (8 sites across PG and libSQL). Sandbox-specific APIs should
stay scoped to sandbox jobs; unified job listing for the Jobs tab
should use a separate query path.
- Remove extra blank lines in agent_loop.rs and worker.rs that caused
formatting CI failure.
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review — regenerate Cargo.lock, add user_id regression test
- Regenerate Cargo.lock from main's lockfile to eliminate dependency
version downgrades (anyhow, syn, etc.) that were churn from rebase.
- Add regression test verifying user_id round-trips through save_job
and get_job in the libSQL backend.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: remove trailing blank line in libsql jobs.rs
[skip-regression-check]
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* test: add Postgres-side regression test for user_id persistence in save_job
Mirrors the existing libSQL test (test_save_job_persists_user_id) for the
Postgres backend. Gated behind #[cfg(feature = "postgres")] + #[ignore]
since it requires a running PostgreSQL instance (integration tier).
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
* refactor: unify three agentic loops into single AgenticLoop engine (#654)
Replace three independent copy-pasted agentic loops (dispatcher, worker,
container runtime) with a single shared engine in `agentic_loop.rs` that
all consumers customize via the `LoopDelegate` trait.
Phase 1 — Shared engine (`src/agent/agentic_loop.rs`, 205 lines):
- `run_agentic_loop()` owns the core LLM → tool exec → repeat cycle
- `LoopDelegate` trait (Send + Sync, &dyn dispatch) with 6 hook points
- Tool intent nudge logic consolidated (was duplicated in 3 files)
- Iteration limit + force-text behavior preserved
Phase 2 — Three delegate implementations:
- `ChatDelegate` (dispatcher.rs): 3-phase approval flow, hooks, cost
guard, context compaction, skill attenuation, interruption
- `JobDelegate` (worker/job.rs): planning pre-loop phase, parallel
JoinSet exec, mark_completed/stuck/failed, SSE streaming, self-repair
- `ContainerDelegate` (worker/container.rs): sequential tool exec,
HTTP-proxied LLM, container-safe tools, credential injection
Phase 3 — File moves and cleanup:
- Delete `src/agent/worker.rs` — job logic moved to `src/worker/job.rs`
- Rename `src/worker/runtime.rs` → `src/worker/container.rs`
- Re-export `Worker`/`WorkerDeps` from `crate::worker` in `agent/mod.rs`
- Update `scheduler.rs` imports to new worker location
Shared helpers (`src/tools/execute.rs`):
- `execute_tool_with_safety()` replaces 4 copies of validate → timeout
→ execute → serialize
- `process_tool_result()` replaces 3 copies of sanitize → wrap →
ChatMessage (also used by thread_ops.rs approval resume paths)
Net result: -2,408 lines, zero duplicated loop logic, single code path
for tool intent nudge and completion detection.
Closes #654
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address review feedback from Copilot
1. scheduler.rs: Replace `unwrap_or` fallback with proper error
propagation when parsing tool output JSON — surfaces bugs instead
of silently changing the output type.
2. worker/job.rs: Drop MutexGuard before the cancellation `.await` in
`check_signals()` to avoid holding a lock across an async I/O call
(prevents `await_holding_lock` lint).
3. worker/job.rs: Restore consecutive rate-limit counter
(MAX_CONSECUTIVE_RATE_LIMITS = 10) so sustained rate limiting marks
the job stuck with "Persistent rate limiting" instead of silently
burning through max_iterations.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: incorporate staging changes — token budget tracking + mark_failed
Merge staging's changes into the refactored JobDelegate:
- Add token budget tracking in call_llm (update_context/add_tokens)
- mark_stuck → mark_failed for iteration cap and rate-limit exhaustion
(aligns with staging's #788 fix)
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address zmanian's PR review — eliminate type erasure, clean up
Address all 6 review points from zmanian on PR #800:
1. Replace LoopOutcome::Custom(Box<dyn Any>) with typed
LoopOutcome::NeedApproval(Box<PendingApproval>) — eliminates
type erasure and downcast, resolves clippy large_enum_variant.
2. Remove dead max_tool_iterations field from ChatDelegate struct.
3. Add on_tool_intent_nudge() hook to LoopDelegate trait with
implementations in Job and Container delegates for observability.
4. Fix SSE events in job worker to emit raw sanitized content
instead of XML-wrapped <tool_output> tags.
5. Remove 4 duplicate completion tests from job.rs that were
already covered by the shared util module.
6. Avoid logging full tool results — use result_size_bytes in
debug logs (execute.rs, job.rs).
Also updates path references in CLAUDE.md, COVERAGE_PLAN.md,
and add-sse-event.md command.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* feat(doctor): expand diagnostics from 7 to 16 health checks
* test: add unit tests for agentic_loop and execute shared modules
Add 16 tests covering the two new critical shared modules:
agentic_loop.rs (10 tests):
- Text response exits loop immediately
- Tool call → text response continuation
- LoopSignal::Stop exits before LLM call
- LoopSignal::InjectMessage adds user message to context
- Max iterations terminates with LoopOutcome::MaxIterations
- Tool intent nudge fires twice then caps
- before_llm_call early exit bypasses LLM
- truncate_for_preview: short string, long string, multibyte safety
execute.rs (6 tests):
- execute_tool_with_safety success path
- Missing tool returns ToolError::NotFound
- Tool execution failure propagates
- Per-tool timeout enforcement (50ms)
- process_tool_result XML wrapping on success
- process_tool_result error formatting
All 2,777 unit tests pass, 0 clippy warnings.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: cargo fmt
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* fix: address code review — 9 issues across agentic loop, job worker, container
CRITICAL fixes:
- Rate-limit exhaustion now returns Err(LlmError::RateLimited) instead of
Ok(Text("")), stopping the loop immediately with no ghost iteration.
Below-threshold retries still use Text("") with an explicit empty-string
guard in handle_text_response to skip injection.
- check_signals drains the entire message channel before returning,
prioritizing Stop over UserMessage. Previously returned early on first
UserMessage, silently dropping any queued Stop or additional messages.
- check_signals now detects all non-progressing job states (Cancelled,
Failed, Stuck, Completed, Submitted, Accepted) instead of only
Cancelled and Failed.
HIGH fixes:
- Error path in process_tool_result_job applies truncate_for_preview to
bound error strings in SSE/DB events (was unbounded).
- Document Send+Sync lifetime constraint on LoopDelegate trait.
- Test mock before_llm_call refactored from double-lock to single lock
acquisition, eliminating deadlock risk on refactor.
MEDIUM fixes:
- CompletionReport includes actual iteration count via shared
Arc<Mutex<u32>> tracker (was hardcoded 0).
- process_tool_result_job return type changed from Result<bool> to
Result<()> — the bool was always false (dead API).
- Deduplicate truncate in container.rs; now uses truncate_for_preview
from agentic_loop.
Verified: 0 clippy warnings, 2781 tests pass, cargo fmt clean.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
---------
Co-authored-by: Henry Park <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Illia Polosukhin <[email protected]>
Co-authored-by: Umesh Kumar Singh <[email protected]>
Co-authored-by: reidliu41 <[email protected]>
* Revert "Feat/docker shell edition" + fix fmt/clippy (#886)
* Revert "Feat/docker shell edition (#804)"
This reverts commit
|
||
|
|
461d7712e8 |
fix(config): init_secrets no longer overwrites entire config (#726)
* fix(config): init_secrets no longer overwrites entire config init_secrets() was calling Config::from_db_with_toml() to re-resolve config after injecting credentials. This rebuilt the entire config from env/DB/defaults, nuking all other config fields (agent, safety, tools, etc.) even though only LlmConfig depends on injected credentials. This caused 5 CI test failures: the test rig's carefully chosen config values (max_tool_iterations, allow_local_tools, etc.) were silently overwritten with production defaults after secret injection. Fix: add Config::re_resolve_llm() that re-resolves only the LLM config after credential injection, leaving all other config fields untouched. Also fix TraceLlm::complete() to skip ToolCalls steps when called in force_text mode (iteration limit). [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): update test to match TraceLlm::complete() skip-tool-calls behavior [skip-regression-check] TraceLlm::complete() now skips ToolCalls steps (force_text mode) instead of erroring. Update the test to verify it skips past a ToolCalls step and returns the subsequent Text step. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: Zaki <[email protected]> |
||
|
|
30790439ee |
perf: build system prompt once per turn, skip tools on force-text (#583)
* perf: build system prompt once per turn, skip tools on force-text, fix nudge role (#565) Three fixes to agentic loop prompt handling: 1. Build system prompt once per turn instead of every tool iteration. `build_system_prompt_with_tools` is now pub; callers pass the result via `ReasoningContext::system_prompt` to avoid rebuilding ~1,500 tokens per iteration. 2. Skip `## Available Tools` section when `force_text = true`. The dispatcher passes a no-tools prompt variant on the final iteration, saving ~460 tokens and removing misleading instructions. 3. Change nudge message from `Role::System` to `Role::User`. A second system message mid-conversation is unsupported by most providers. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: revert nudge role change to keep ChatMessage::system Copilot review correctly identified that using Role::User for the nudge breaks compact_messages_for_retry, which uses rposition for Role::User to find the last real user message. Role::Assistant would cause back-to-back assistant messages. Since no production issues were reported with the original system role, revert to ChatMessage::system. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — omit tool guidance when tools empty, rename shadowed var - Conditionalize "Call tools…" guidelines and "## Tool Call Style" section in the system prompt so they are only included when tools are non-empty. Previously the force-text (no-tools) prompt still contained misleading tool-calling instructions. (Copilot review comment) - Rename `system_prompt` → `cached_prompt` in dispatcher to avoid shadowing the earlier workspace identity `system_prompt` variable. (Copilot review) - Add regression tests: `test_system_prompt_with_tools_contains_tool_guidance` and extended assertions in `test_system_prompt_without_tools_omits_tools_section`. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: [email protected] <[email protected]> |
||
|
|
424a0366a9 |
feat: enable Anthropic prompt caching via automatic cache_control injection (#660)
* feat(llm): add Anthropic prompt caching and cache token tracking - Inject cache_control via additional_params for Claude models in rig_adapter - Add cache_read_input_tokens and cache_creation_input_tokens to CompletionResponse and ToolCompletionResponse - Extract cached_input_tokens from rig-core unified Usage - Add is_anthropic_model() detection helper with provider prefix support - Log prompt cache hits at debug level (consistent with response_cache) - Add 7 unit tests for cache injection and model detection - Update all mock providers and test fixtures with new fields * feat(cost): apply 90% cache discount to prompt-cached tokens in CostGuard - Add cache_read_input_tokens to TokenUsage so cache counts flow from CompletionResponse through the reasoning layer to the dispatcher - Update CostGuard::record_llm_call() to accept cache_read_input_tokens: cached tokens are billed at 10% of the normal input rate - Thread cache_read_input_tokens from dispatcher into CostGuard - Add test_cache_discount_reduces_cost verifying exact savings match 90% of input cost for fully-cached requests - Update all existing test callers with zero-cache parameter * refactor(cache): scope cache_control to Anthropic backend and validate model support - Replace model-name-based is_anthropic_model() with explicit enable_prompt_cache flag on RigAdapter, set only for the direct Anthropic backend via with_prompt_cache(true) - Add supports_prompt_cache() to validate model names per Anthropic docs: only Claude 3+ models support caching; claude-2 and claude-instant are excluded to prevent 400 errors - Warn when caching is enabled but model does not support it - Replace is_anthropic_model tests with flag-based and model validation tests * fix(cache): validate model at construction and propagate cache metrics through proxy - Move supports_prompt_cache() check into with_prompt_cache() so unsupported models are detected once at construction, not per request - Add cache_read_input_tokens and cache_creation_input_tokens to ProxyCompletionResponse and ProxyToolCompletionResponse with serde(default) for backward compatibility - Pass cache metrics through orchestrator proxy instead of zeroing - Use claude-opus-4-6 in cache discount test to match Anthropic semantics * feat(llm): add configurable cache retention with write surcharge - Add CacheRetention enum (none/short/long) to AnthropicDirectConfig - Parse ANTHROPIC_CACHE_RETENTION env var (default: short) - Inject TTL-aware cache_control (short=5m ephemeral, long=1h) - Extract cache_creation_input_tokens from raw Anthropic response - Add cache_write_multiplier() to LlmProvider trait (1.25x short, 2.0x long) - Pipe dynamic write multiplier through dispatcher to CostGuard - Add TokenUsage.cache_creation_input_tokens field - Add tests for Long TTL injection, 5m and 1h write surcharges - Document ANTHROPIC_CACHE_RETENTION in .env.example * docs: fix stale cache_retention field comment * fix: resolve CI failures after upstream merge - Add missing cost_per_token arg to cache test callsites - Apply cargo fmt to long lines in tests and tracing macros * fix: address Copilot review feedback - Use saturating_add for cache token sum to prevent u32 overflow - Tighten supports_prompt_cache to explicitly match claude-3+/claude-4+ and named families (claude-sonnet/claude-opus/claude-haiku) * fix: adapt prompt caching to registry architecture and add missing cache fields - Resolve merge conflicts: adapt CacheRetention and cache injection to the declarative provider registry (RegistryProviderConfig replaces AnthropicDirectConfig) - Parse ANTHROPIC_CACHE_RETENTION env var in create_anthropic_from_registry() - Use Anthropic automatic caching via top-level cache_control in additional_params (rig-core #[serde(flatten)] places it at request root) - Add cache_read/creation_input_tokens fields to all mock LlmProviders added on main after PR #291 branched (response_cache, dispatcher, provider_chaos, trace_llm) - Suppress clippy::too_many_arguments on record_llm_call and build_rig_request - Add regression tests for cache injection (short/long/none) and cache_write_multiplier values Co-Authored-By: Canvinus <[email protected]> * fix: delegate cache_write_multiplier through provider wrappers and make cache_read_discount configurable The 6 decorator providers (Retry, CircuitBreaker, Failover, SmartRouting, CachedProvider, RecordingLlm) did not delegate cache_write_multiplier() to their inner provider, causing it to always return 1.0 instead of the actual 1.25x/2.0x from RigAdapter. This fix adds delegation for both cache_write_multiplier() and the new cache_read_discount() method. Also makes the cache read discount per-provider instead of hardcoding Anthropic's 90% discount (÷10). OpenAI uses 50% (÷2), so the discount is now returned by each provider via the LlmProvider trait. Addresses review feedback on PR #660. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add CacheRetention FromStr/Display unit tests Tests cover primary values, aliases (off/disabled/5m/ephemeral/1h), case-insensitivity, invalid input error, and Display round-trip. Addresses Copilot review feedback on PR #660. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Andrey <[email protected]> Co-authored-by: Andrey Gruzdev <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
cf96a3253c |
fix(tests): replace hardcoded /tmp paths with tempdir + add 300 unit tests (#659)
* test: add unit tests across 20 modules for coverage push Add 300+ unit tests covering config, context, evaluation, extensions, LLM, secrets, tools/builder, and tools/mcp modules. All tests are pure unit tests (no mocks) exercising serde roundtrips, edge cases, error paths, and business logic. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(tests): replace hardcoded /tmp paths with tempfile::tempdir The e2e_metrics_test::test_metrics_collected_from_tool_trace test was failing because setup_test_dir() created /tmp/ironclaw_metrics_test but the fixture referenced /tmp/ironclaw_e2e_test/hello.txt (path mismatch). Added LlmTrace::replace_paths() to substitute fixture paths at runtime, then converted all 12 test files from hardcoded /tmp/ironclaw_* paths to tempfile::tempdir(). Tests are now isolated, parallel-safe, and leave no debris on disk. Regression test: test_metrics_collected_from_tool_trace now passes consistently regardless of prior /tmp state. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
37bba72397 |
test: add 29 E2E trace tests for issues #571-575 (#593)
* test: add 29 E2E trace tests for worker, threading, tools, workspace, and routines (#571-575) Add comprehensive E2E test coverage across five test files: - e2e_worker_coverage (7 tests): parallel tool calls, error feedback, unknown tools, invalid params, rate limiting, iteration limits, planning mode - e2e_thread_scheduling (3 tests + 2 deferred): multi-turn state, undo/redo, concurrent dispatch - e2e_builtin_tool_coverage (8 tests): time parse/diff/invalid, routine CRUD/history, job create/status/list/cancel, HTTP replay - e2e_workspace_coverage (6 tests): chunked search, multi-doc search, hybrid search, directory tree, document lifecycle, identity in system prompt - e2e_routine_heartbeat (5 tests): cron triggers, event matching, cooldown enforcement, heartbeat findings, empty checklist skip Infrastructure: extend TestRig with database/workspace/trace_llm accessors, register job and routine tools by default, add with_extra_tools() for custom stub tools. Includes 24 JSON trace fixtures across worker/, threading/, tools/, and workspace/. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use 6-field cron format in routine_create_list fixture The cron 0.13 crate accepts both 6 and 7 fields, but the routine_create tool documents 6-field format. Align the fixture to match. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: eliminate vacuous passes and silently-skipped assertions in E2E tests - job_create_status: replace job_status (needs dynamic UUID) with list_jobs, assert both succeed via completed() not just started() - job_list_cancel: keep cancel_job but explicitly assert it fails with invalid canned job_id "latest", verify create_job + list_jobs succeed - unknown_tool_name: add !is_empty() guard before .all() to prevent vacuous pass on empty iterator - workspace tests: change `if let Some(ws)` to `.expect()` so assertions are never silently skipped when workspace/trace_llm is available [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add template substitution to TraceLlm for dynamic tool result forwarding Add {{call_id.json_path}} template syntax to trace fixtures, enabling tool results from one step to flow into subsequent steps' arguments. TraceLlm extracts variables from Role::Tool messages (stripping the safety layer's <tool_output> XML wrapper and unescaping entities) and substitutes them in canned tool_call arguments before returning. This fixes job_create_status and job_list_cancel tests to properly test job_status and cancel_job with real dynamic UUIDs from create_job, instead of using invalid canned IDs that silently failed. Also adds tool result content assertions to job_create_status to verify the actual tool output contains expected data (job_id, title). [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review feedback on E2E tests - undo_redo_cycle: assert exactly 3 turns instead of >= 2 - tool_error_feedback: use tempfile::tempdir() instead of hardcoded /tmp path, patch fixture path at runtime for CI portability - worker_timeout → iteration_limit: rename to accurately describe what's tested - post_plan_work_remaining → simple_echo_flow: rename, test doesn't exercise planning - identity_in_system_prompt: seed IDENTITY.md before test, assert system prompt contains the seeded content instead of just checking Role::System exists [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: strengthen workspace E2E test assertions per PR review - write_chunk_search: assert memory_search was called and returned payment/architecture-related results - multi_document_search: assert memory_search was called for cross-document search - hybrid_search_with_embeddings: assert both memory_write and memory_search were called to confirm write-then-search pipeline - directory_tree: assert tree output contains expected alpha/beta project paths [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
b4b19738a8 |
Trajectory benchmarks and e2e trace test rig (#553)
* refactor: extract shared assertion helpers to support/assertions.rs Move 5 assertion helpers from e2e_spot_checks.rs to a shared module. Add assert_all_tools_succeeded and assert_tool_succeeded for eliminating false positives in E2E tests. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add tool output capture via tool_results() accessor Extract (name, preview) from ToolResult status events in TestChannel and TestRig, enabling content assertions on tool outputs. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: correct tool parameters in 3 broken trace fixtures - tool_time.json: add missing "operation": "now" for time tool - robust_correct_tool.json: same fix - memory_full_cycle.json: change "path" to "target" for memory_write Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add tool success and output assertions to eliminate false positives Every E2E test that exercises tools now calls assert_all_tools_succeeded. Added tool output content assertions where tool results are predictable (time year, read_file content, memory_read content). Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: capture per-tool timing from ToolStarted/ToolCompleted events Record Instant on ToolStarted and compute elapsed duration on ToolCompleted, wiring real timing data into collect_metrics() instead of hardcoded zeros. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: add RAII CleanupGuard for temp file/dir cleanup in tests Replace manual cleanup_test_dir() calls and inline remove_file() with Drop-based CleanupGuard that ensures cleanup even if a test panics. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add Drop impl and graceful shutdown for TestRig Wrap agent_handle in Option so Drop can abort leaked tasks. Signal the channel shutdown before aborting for future cooperative shutdown. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: replace agent startup sleep with oneshot ready signal Use a oneshot channel fired in Channel::start() instead of a fixed 100ms sleep, eliminating the race condition on slow systems. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: replace fragile string-matching iteration limit with count-based detection Use tool completion count vs max_tool_iterations instead of scanning status messages for "iteration"/"limit" substrings. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use assert_all_tools_succeeded for memory_full_cycle test Remove incorrect comment about memory_tree failing with empty path (it actually succeeds). Omit empty path from fixture and use the standard assert_all_tools_succeeded instead of per-tool assertions. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: promote benchmark metrics types to library code Move TraceMetrics, ScenarioResult, RunResult, MetricDelta, and compare_runs() from tests/support/metrics.rs to src/benchmark/metrics.rs. Existing tests use re-export for backward compatibility. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add Scenario and Criterion types for agent benchmarking Scenario defines a task with input, success criteria, and resource limits. Criterion is an enum of programmatic checks (tool_used, response_contains, etc.) evaluated without LLM judgment. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add initial benchmark scenario suite (12 scenarios across 5 categories) Scenarios cover tool_selection, tool_chaining, error_recovery, efficiency, and memory_operations. All loaded from JSON with deserialization validation test. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add benchmark runner with BenchChannel and InstrumentedLlm BenchChannel is a minimal Channel implementation for benchmarks. InstrumentedLlm wraps any LlmProvider to capture per-call metrics. Runner creates a fresh agent per scenario, evaluates success criteria, and produces RunResult with timing, token, and cost metrics. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add baseline management, reports, and benchmark entry point - baseline.rs: load/save/promote benchmark results - report.rs: format comparison reports with regression detection - benchmark_runner.rs: integration test with real LLM (feature-gated) - Add benchmark feature flag to Cargo.toml Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: apply cargo fmt to benchmark module Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add multi-turn scenario types with setup, judge, ResponseNotContains Add BenchScenario, Turn, TurnAssertions, JudgeConfig, ScenarioSetup, WorkspaceSetup, SeedDocument types for multi-turn benchmark scenarios. Add ResponseNotContains criterion variant. Add TurnAssertions::to_criteria() converter for backward compat with existing evaluation engine. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add JSON scenario loader with recursive discovery and tag filter Add load_bench_scenarios() for the new BenchScenario format with recursive directory traversal and tag-based filtering. Create 4 initial trajectory scenarios across tool-selection, multi-turn, and efficiency categories. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): multi-turn runner with workspace seeding and per-turn metrics Add run_bench_scenario() that loops over BenchScenario turns, seeds workspace documents, collects per-turn metrics (tokens, tool calls, wall time), and evaluates per-turn assertions. Add TurnMetrics to metrics.rs and clear_for_next_turn() to BenchChannel. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add LLM-as-judge scoring with prompt formatting and score parsing Create judge.rs with format_judge_prompt, parse_judge_score, and judge_turn. Wire into run_bench_scenario for turns with judge config -- scores below min_score fail the turn. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add CLI subcommand (ironclaw benchmark) Add BenchmarkCommand with --tags, --scenario, --no-judge, --timeout, --update-baseline flags. Wire into Command enum and main.rs dispatch. Feature-gated behind benchmark flag. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): per-scenario JSON output with full trajectory Add save_scenario_results() that writes per-scenario JSON files alongside the run summary. Each scenario gets its own file with turn_metrics trajectory. Update CLI to use new output format. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add ToolRegistry::retain_only and wire tool filtering in scenarios Add a retain_only() method to ToolRegistry that filters tools down to a given allowlist. Wire this into run_bench_scenario() so that when a scenario specifies a tools list in its setup, only those tools are available during the benchmark run. Includes two tests for the new method: one verifying filtering works and one verifying empty input is a no-op. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): wire identity overrides into workspace before agent start Add seed_identity() helper that writes identity files (IDENTITY.md, USER.md, etc.) into the workspace before the agent starts, so that workspace.system_prompt() picks them up. Wire it into run_bench_scenario() after workspace seeding. Include a test that verifies identity files are written and readable. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add --parallel and --max-cost CLI flags Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(benchmark): use feature-conditional snapshot names for CLI help tests Prevents snapshot conflicts between default (no benchmark) and all-features (with benchmark) builds by using separate snapshot names per feature set. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): parallel execution with JoinSet and budget cap enforcement Replace sequential loop in run_all_bench() with parallel execution using JoinSet + semaphore when config.parallel > 1. Add budget cap enforcement that skips remaining scenarios when max_total_cost_usd is exceeded. Track skipped count in RunResult.skipped_scenarios and display it in format_report(). Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add tool restriction and identity override test scenarios Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: fix formatting for Phase 3 Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add SkillRegistry::retain_only and wire skill filtering in scenarios Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(benchmark): add --json flag for machine-readable output Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: add GitHub Actions benchmark workflow (manual trigger) Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(benchmark): remove in-tree benchmark harness, keep retain_only utilities Move benchmark-specific code out of ironclaw in preparation for the nearai/benchmarks trajectory adapter. This removes: - src/benchmark/ (runner, scenarios, metrics, judge, report, etc.) - src/cli/benchmark.rs and the Benchmark CLI subcommand - benchmarks/ data directory (scenarios + trajectories) - .github/workflows/benchmark.yml - The "benchmark" Cargo feature flag What remains: - ToolRegistry::retain_only() and SkillRegistry::retain_only() - Test support types (TraceMetrics, InstrumentedLlm) inlined into tests/support/ instead of re-exporting from the deleted module Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: add README for LLM trace fixture format Documents the trajectory JSON format, response types, request hints, directory structure, and how to write new traces. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(test): unify trace format around turns, add multi-turn support Introduce TraceTurn type that groups user_input with LLM response steps, making traces self-contained conversation trajectories. Add run_trace() to TestRig for automatic multi-turn replay. Backward-compatible: flat "steps" JSON is deserialized as a single turn transparently. Includes all trace fixtures (spot, coverage, advanced), plan docs, and new e2e tests for steering, error recovery, long chains, memory, and prompt injection resilience. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): fix CI failures after merging main - Fix tool_json fixture: use "data" parameter (not "input") to match JsonTool schema - Fix status_events test: remove assertion for "time" tool that isn't in the fixture (only "echo" calls are used) - Allow dead_code in test support metrics/instrumented_llm modules (utilities for future benchmark tests) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * Working on recording traces and testing them * feat(test): add declarative expects to trace fixtures, split infra tests Add TraceExpects struct with 9 optional assertion fields (response_contains, tools_used, all_tools_succeeded, etc.) that can be declared in fixture JSON instead of hand-written Rust. Add verify_expects() and run_recorded_trace() so recorded trace tests become one-liners. Split trace infra tests (deserialization, backward compat) into tests/trace_format.rs which doesn't require the libsql feature gate. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(test): add expects to all trace fixtures, simplify e2e tests Add declarative expects blocks to all 19 trace fixture JSONs across spot/, coverage/, advanced/, and root directories. Update all 8 e2e test files to use verify_trace_expects() / run_and_verify_trace(), replacing ~270 lines of hand-written assertions with fixture-driven verification. Tests that check things beyond expects (file content on disk, metrics, event ordering) keep those extra assertions alongside the declarative ones. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): adapt tests to AppBuilder refactor, fix formatting Update test files to work with refactored TestRigBuilder that uses AppBuilder::build_all() (removing with_tools/with_workspace methods). Update telegram_check fixture to use tool_list instead of echo. Fix cargo fmt issues in src/llm/mod.rs and src/llm/recording.rs. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(test): deduplicate support unit tests into single binary Support modules (assertions, cleanup, test_channel, test_rig, trace_llm) had #[cfg(test)] mod tests blocks that were compiled and run 12 times — once per e2e test binary that declares `mod support;`. Extracted all 29 support unit tests into a dedicated `tests/support_unit_tests.rs` so they run exactly once. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix trailing newlines in support files Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(test): unify trace types and fix recorded multi-turn replay Import shared types (TraceStep, TraceResponse, TraceToolCall, RequestHint, ExpectedToolResult, MemorySnapshotEntry, HttpExchange*) from ironclaw::llm::recording instead of redefining them in trace_llm.rs. Fix the flat-steps deserializer to split at UserInput boundaries into multiple turns, instead of filtering them out and wrapping everything into a single turn. This enables recorded multi-turn traces to be replayed as proper multi-turn conversations via run_trace(). [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): fix CI failures - unused imports and missing struct fields - Add #[allow(unused_imports)] on pub use re-exports in trace_llm.rs (types are re-exported for downstream test files, not used locally) - Add `..` to ToolCompleted pattern in test_channel.rs to match new `error` and `parameters` fields Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): fix CI failures after merging main - Add missing `error` and `parameters` fields to ToolCompleted constructors in support_unit_tests.rs - Add `..` to ToolCompleted pattern match in support_unit_tests.rs - Add #[allow(dead_code)] to CleanupGuard, LlmTrace impl, and TraceLlm impl (only used behind #[cfg(feature = "libsql")]) Co-Authored-By: Claude Opus 4.6 <[email protected]> * Adding coverage running script * fix(test): address review feedback on E2E test infrastructure - Increase wait_for_responses polling to exponential backoff (50ms-500ms) and raise default timeout from 15s to 30s to reduce CI flakiness (#1) - Strengthen prompt_injection_resilience test with positive safety layer assertion via has_safety_warnings(), enable injection_check (#2) - Add assert_tool_order() helper and tools_order field in TraceExpects for verifying tool execution ordering in multi-step traces (#3) - Document TraceLlm sequential-call assumption for concurrency (#6) - Clean up CleanupGuard with PathKind enum instead of shotgun remove_file + remove_dir_all on every path (#8) - Fix coverage.sh: default to --lib only, fix multi-filter syntax, add COV_ALL_TARGETS option - Add coverage/ to .gitignore - Remove planning docs from PR [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review - use HashSet in retain_only, improve skill test - Use HashSet for O(N+M) lookup in SkillRegistry::retain_only and ToolRegistry::retain_only instead of linear scan - Strengthen test_retain_only_empty_is_noop in SkillRegistry to pre-populate with a skill before asserting the no-op behavior [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): revert incorrect safety layer assertion in injection test The safety layer sanitizes tool output, not user input. The injection test sends a malicious user message with no tools called, so the safety layer never fires. Reverted to the original test which correctly validates the LLM refuses via trace expects. Also fixed case-sensitive request hint ("ignore" -> "Ignore") to suppress noisy warning. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: clean stale profdata before coverage run Adds `cargo llvm-cov clean` before each run to prevent "mismatched data" warnings from stale instrumentation profiles. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in retain_only test [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: Illia Polosukhin <[email protected]> |