8 Commits

Include renames

Author	SHA1	Message	Date
3 people	8a26cfae73	fix(mcp): open MCP OAuth in same browser as gateway (#951) ... * fix(mcp): use gateway callback for MCP OAuth so auth opens in same browser When MCP OAuth is triggered from the web gateway, the auth URL was being opened via `open::that()` which launches the OS default browser instead of the browser already running the gateway UI. This changes the MCP OAuth flow to use the same gateway callback pattern as WASM extensions: in gateway mode, the auth URL is returned to the frontend via SSE and opened with `window.open()`, keeping the user in the same browser. Also adds RFC 8707 `resource` parameter support to the gateway token exchange path, scoping issued tokens to the correct MCP server. Closes #299 Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(mcp): persist DCR client_id in gateway OAuth callback for token refresh The gateway callback handler stored access and refresh tokens but not the DCR client_id. When the token expired, refresh failed with "No client ID found" because get_client_id() could not find it in secrets. Adds client_id_secret_name to PendingOAuthFlow so the gateway callback handler persists the client_id alongside the tokens, matching the behavior of the CLI flow in authorize_mcp_server(). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(mcp): return AuthRequired on 401 so activate triggers OAuth flow activate_mcp() returned ActivationFailed for all errors including 401 auth responses, so the activate handler never triggered the OAuth flow. Now 401/auth errors return AuthRequired, which the handler detects and redirects to the OAuth flow — matching the WASM extension pattern. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(mcp): fix gateway OAuth flow, approval cards, and auto-activation - Add explicit gateway_mode flag on ExtensionManager (set at startup by web gateway) so MCP OAuth returns auth URLs to the frontend instead of calling open::that() on the server machine. - Auto-activate extensions after successful OAuth callback so the UI transitions from "Activate" to "Active" without a second click. - Send ApprovalNeeded status (not generic "Awaiting approval") from thread_ops.rs for all three NeedApproval paths so the web UI shows approval cards for deferred tool calls. - Remove duplicate ApprovalNeeded send from agent_loop.rs (thread_ops.rs is now the canonical sender). - Skip approval for tool_auth in gateway mode since it only returns a URL. - Revert fragile active-server detection heuristic from system prompt. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review findings - Use Release/Acquire ordering for gateway_mode AtomicBool instead of Relaxed to ensure visibility across threads. - Report activation failure as error in OAuth callback SSE event instead of silently falling back to the success message. - Fix EnvGuard::drop to remove env var when original was unset. - Replace hardcoded /tmp/ path with std::env::temp_dir() in test helper. Co-Authored-By: Claude Opus 4.6 <[email protected]> * test(mcp): add E2E trace test for MCP extension lifecycle with mock server Add a full MCP extension lifecycle E2E test that exercises: - Turn 1: tool_search → tool_install → text (extension discovery and install) - Token injection + activate (simulating OAuth completion) - Turn 2: MCP tool calls (notion-search → notion-fetch → text) Includes a mock MCP server (tests/support/mock_mcp_server.rs) with OAuth discovery, DCR, token exchange, and JSON-RPC endpoints. The mock server validates Bearer auth and serves pre-configured tool responses. Also adds inject_registry_entry() to ExtensionManager for test use and exposes extension_manager from TestRig. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review findings (round 2) - Only fall back to manual token entry on AuthNotSupported, propagate real errors from auth_mcp_build_url() instead of masking them - Use mcp:-prefixed provider string in PendingOAuthFlow for consistency with CLI MCP auth token storage - Only persist client_id_secret_name for DCR flows (not pre-configured OAuth) - Fix gateway_callback_redirect_uri to use /oauth/callback path - Bypass exchange proxy when flow has RFC 8707 resource parameter - Remove client_id double-prefix in oauth callback handler - Remove weak tests that didn't exercise production logic - Add clarifying comments for exchange_oauth_code delegation Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: keep OAuth success independent of activation, fix wait_for_responses scoping - OAuth success is now reported accurately even when auto-activation fails (tokens are already stored, so auth succeeded) - E2E test waits for turn1_count + 1 responses to ensure turn-2 behavior is actually observed Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-12 11:16:23 -07:00
3 people	f05896fe6a	Migrate GitHub webhook normalization into github tool (#758) ... * Add event-triggered routines and workflow skill templates * Add generic host-verified webhook ingress for tools * Migrate GitHub webhook normalization into github tool * Bump github tool registry version * Stabilize trace E2E test rig and approval behavior * Add reusable gateway workflow harness with mock LLM server (#762) * Add reusable gateway workflow test harness with mock LLM server * Fix clippy issues in workflow harness * Stabilize trace E2E test rig and approval behavior * Address PR review feedback on gateway workflow harness - Extract shared TestChannelHandle into test_channel.rs with name override support, eliminating ~55 lines of duplication between test_rig.rs and gateway_workflow_harness.rs - Remove redundant RoutineEngine creation that was immediately overwritten by Agent::run() - Replace flaky sleep(500ms) with polling loop for routine run count check - Use components.context_manager instead of creating a fresh ContextManager for job tools, ensuring agent and tools share the same instance Co-Authored-By: Claude Opus 4.6 <[email protected]> * Fix import ordering in gateway_workflow_harness Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> * Address PR #758 review feedback - Fix header_value to use fully case-insensitive lookup (iterate with to_ascii_lowercase) instead of checking only exact/lower/upper variants - Change comment_id from u32 to u64 to handle GitHub's billion-range IDs - Remove handle_webhook from LLM-facing JSON schema to prevent direct invocation bypassing HMAC verification - Rename enrichment keys from repository/sender to repository_name/ sender_login to preserve original JSON objects in webhook payloads - Remove put_string_normalized helper (no longer needed) - Replace no-op tests (test_validate_event_in_create_pr_review, test_validate_merge_method) with test_header_value_case_insensitive - Add README docs for 6 undocumented actions (list_issue_comments, create_issue_comment, list_pull_request_comments, reply_pull_request_comment, get_pull_request_reviews, get_combined_status) - Add comment explaining max_tool_calls <= 8 bound in e2e test - Fix gateway workflow harness: add webhook_capability with secret auth to MockGithubWebhookTool, matching staging's hardened webhook security - Fix merge artifacts: remove duplicate test function, orphaned code fragment in e2e_routine_heartbeat [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * Fix formatting in gateway workflow harness Co-Authored-By: Claude Opus 4.6 <[email protected]> * Address Copilot review: filter keys, pr_number fallback, feature gate, version alignment - Update SKILL.md and workflow-routines.md templates to use `repository_name` and `sender_login` (matching enriched payload field names) - Mark webhook HMAC secret as required in SKILL.md prerequisites - Fall back to `/issue/number` for `pr_number` on issue_comment PR webhooks - Gate `gateway_workflow_harness` module behind `#[cfg(feature = "libsql")]` - Align tool version to 0.2.1 in Cargo.toml and capabilities.json Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-12 01:52:47 +00:00
3 people	369741fc60	Add generic host-verified /webhook/tools/{tool} ingress (#757) ... * Add generic host-verified webhook ingress for tools * Stabilize trace E2E test rig and approval behavior * Fix webhook security issues from review feedback - Reject tools without webhook_capability() (was unauthenticated RCE) - Remove secret-in-query-string fallback (leak via logs/referrers) - Require approval for event_emit tool (escalation via routine triggers) - Simplify header_value() (HeaderMap already case-insensitive) - Redact internal errors from webhook HTTP responses - Remove unused hmac_timestamp_tolerance_secs field - Add regression test for tool without webhook capability [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * Harden webhook ingress: require auth mechanism, body limit layer, health check - Reject webhook capabilities that declare no auth mechanism (empty WebhookCapability would previously allow unauthenticated access) - Add DefaultBodyLimit layer to reject oversized payloads before buffering - Health check (GET) now verifies tool has webhook_capability(), not just existence - Add regression tests for all three fixes [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * Fix auto_approve_tools inconsistency between dispatcher and thread_ops dispatcher.rs skips all approval checks (including Always) when auto_approve_tools is true, but thread_ops.rs still required approval for Always tools. This caused deferred tool calls to unexpectedly halt in test rigs and auto-approve configurations. Match dispatcher behavior: short-circuit all approval when auto_approve_tools is enabled. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-11 03:36:25 +00:00
4 people	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]>	2026-03-07 09:15:00 +00:00
3 people	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]>	2026-03-07 08:24:24 +00:00
3 people	8fbb782090	fix(llm): nudge LLM when it expresses tool intent without calling tools (#653) ... * fix(llm): nudge LLM when it expresses tool intent without calling tools Non-Anthropic models (especially GLM-5 via NEAR AI) frequently output text like "Let me search for X" without including tool_calls, creating a frustrating loop where the user waits but nothing happens. Add llm_signals_tool_intent() detection that matches intent phrases ("let me search", "I'll fetch") while excluding conversational phrases ("let me explain", "let me know") and content inside code blocks. When detected, inject a nudge message telling the model to actually call the tool. Cap at 2 consecutive nudges to avoid infinite loops. Applied to all three agentic loops: dispatcher (interactive chat), agent/worker (background jobs), and worker/runtime (sandbox containers). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(nudge): address PR #653 review comments 1. Update doc comment to match implementation (code blocks only, not quotes) 2. Use match_indices() instead of find() to check all prefix occurrences 3. Add !available_tools.is_empty() guard in dispatcher nudge check 4. Reset consecutive_tool_intent_nudges on non-intent text responses 5. Add regression test for shadowed prefix detection Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(nudge): address second round of PR #653 review comments 1. Strip double-quoted strings in tool-intent detection to avoid false positives on quoted prose like `"Let me search the database"`. 2. Only reset consecutive_tool_intent_nudges when text does NOT signal intent — preserves the 2-nudge cap when intent is detected but cap is already reached. 3. Fix assertion message in nudge_cap test to report correct call index. 4. Add regression test for quoted strings outside code blocks. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-07 08:05:55 +00:00
3 people	ae89a52ac2	feat(routines): approval context for autonomous job execution (#577) ... * feat(routines): add approval context for autonomous job execution Routines and background jobs were unable to use any tools that required approval (file ops, shell, message, http), making them effectively useless. This adds an ApprovalContext system that lets autonomous jobs pre-authorize tools at dispatch time. - Add ApprovalContext enum with Autonomous variant that auto-approves UnlessAutoApproved tools and optionally pre-authorizes Always tools - Add tool_permissions field to RoutineAction::FullJob for pre-authorizing Always-gated tools (e.g. destructive shell, cross-channel messaging) - Add Scheduler::dispatch_job_with_context() to thread approval context through to workers - Set message tool default channel/target from routine NotifyConfig so routines can send results without cross-channel approval - Fix Completed→Completed state transition error in worker (plan marks job completed, then direct loop or outer run() tries again) Co-Authored-By: Claude Opus 4.6 <[email protected]> * test(routines): add E2E trace for routine news digest workflow Add a 3-turn trace fixture and test that exercises: - Turn 1: routine_create with full_job mode and tool_permissions - Turn 2: Simulated digest workflow with echo + memory_write - Turn 3: Verification via memory_search [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(test): wire RoutineEngine into test rig for routine_create E2E - Add `with_routines()` to TestRigBuilder that passes a RoutineConfig to Agent::new, enabling routine tool registration during agent startup - Add Turn 2 (routine_list) to the trace to verify routine persistence in the database after routine_create - Fix formatting issues flagged by CI (cargo fmt) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(scheduler): deduplicate dispatch_job and dispatch_job_with_context Extract shared logic into private `dispatch_job_inner` to prevent divergence when dispatch behavior changes in the future. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(routines): add routine_fire tool and real E2E routine execution test - Add `routine_fire` tool that calls `RoutineEngine::fire_manual` to trigger a routine on demand. Registered alongside the other 5 routine tools (now 6 total). - Rewrite the routine_news_digest E2E trace to exercise the full execution stack end-to-end: 1. routine_create (manual trigger, full_job, tool_permissions: [message]) 2. routine_fire → RoutineEngine → Scheduler::dispatch_job_with_context → autonomous Worker consuming TraceLlm steps 3. Worker calls echo → memory_write → message (broadcast to test channel) 4. Test verifies the message broadcast arrived, proving ApprovalContext correctly allowed the Always-approval message tool - Register message tools in TestRig so routines can send messages to the test channel via channel_manager.broadcast(). [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(routines): wire HttpInterceptor through scheduler for routine worker http calls Propagate http_interceptor from AgentDeps → Scheduler → WorkerDeps → JobContext so that routine workers (and any scheduler-dispatched workers) can use the ReplayingHttpInterceptor for mock HTTP responses during tests. Changes: - Add http_interceptor field to Scheduler and WorkerDeps - Set job_ctx.http_interceptor in Worker before tool execution - Add with_http_exchanges() builder method to TestRigBuilder - Replace echo tool with http tool in routine_news_digest trace - Test now exercises real http tool with mock response → memory_write → message Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review comments from Copilot on PR #577 - Extract `ApprovalContext::is_blocked_or_default()` helper to deduplicate approval check logic in worker.rs and scheduler.rs - Extract `parse_tool_permissions()` helper to deduplicate JSON array parsing in routine.rs and builtin/routine.rs - Fix test name: `test_mark_completed_twice_does_not_error` → `test_mark_completed_twice_returns_error` (matches actual behavior) - Fix ApprovalContext doc comment to clarify it only models autonomous mode - Fix flaky index-based assertion in routine_news_digest test — now uses content-based search instead of fixed position - Fix stale comment: echo → http in routine test header - Add TODO for subtask approval context propagation (latent, not in active code paths) - Add TODO for global message tool context race in routine_engine Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in is_blocked_or_default test Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(test_rig): destructure self in build() to avoid partial-move fragility Destructure TestRigBuilder at the top of build() instead of accessing self.* fields after moving self.http_exchanges. While the prior code compiled (remaining fields are Copy), it was fragile and would break if any non-Copy field were added. Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: clarify that routine_fire bypasses cooldown Manual fires are explicitly user-initiated and intentionally bypass cooldown checks (which only apply to automated cron/event triggers). Updated tool description and fire_manual docstring to make this clear. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(routines): fix message tool approval in routine context Two fixes for message tool failures in autonomous routine jobs: 1. MessageTool::requires_approval() now returns UnlessAutoApproved when the explicit channel param matches the default channel (was Always, causing "requires authentication" errors for routine workers). 2. routine_create tool now accepts notify_channel and notify_user params, wired into NotifyConfig. Without these, routines had channel: None, so set_message_tool_context was never called, causing "No channel specified" errors. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor(message): remove approval requirement from message tool The message tool only sends to user-owned channels via ChannelManager::broadcast (TUI, Telegram, Slack, web gateway, etc.). It cannot reach arbitrary external services, so approval adds friction with no security benefit. This also eliminates the routine context errors entirely since approval is never checked. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review comments — routine_fire approval + test rename - routine_fire now returns UnlessAutoApproved since firing a routine can dispatch a full_job with pre-authorized Always-gated tools - Rename test_approval_context_never_always_passes to test_approval_context_never_is_not_blocked for clarity Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review nits — update stale docs and comments - Remove 'message' from tool_permissions example (no longer Always) - Reword message tool approval comment for accuracy - Clarify with_routines() docstring re: tool registration vs engine wiring Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-07 05:21:58 +00:00
4 people	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]>	2026-03-05 09:13:09 +00:00