mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-30 08:17:53 +00:00
3f92b9cb24ef5fd4298318c7adac61766f3a9028
14
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
df3635d6be |
feat(timezone): add timezone-aware session context (#671)
* feat(timezone): add timezone-aware session context (#661) All timestamps were UTC-only, causing daily logs to split at UTC midnight, cron schedules to fire in UTC, and no quiet hours for heartbeat. This adds timezone as a per-session property flowing from the client. Key changes: - New `src/timezone.rs` module with resolution chain, parsing, and detection - `IncomingMessage` carries optional timezone from client - `JobContext.user_timezone` flows timezone to tools - `next_cron_fire()` accepts timezone for schedule evaluation - `Trigger::Cron` stores optional timezone (backward-compatible) - Workspace gains `_tz` variants for daily logs and system prompt - Heartbeat supports quiet hours (`HEARTBEAT_QUIET_START/END`) - Web frontend sends `Intl.DateTimeFormat().resolvedOptions().timeZone` - REPL auto-detects system timezone - `DEFAULT_TIMEZONE` env var / settings for server-wide default Storage stays UTC. Conversion happens at display boundaries. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(timezone): address review feedback on timezone-aware sessions - Validate quiet hours values (0-23) in HeartbeatConfig::resolve() - Fall back to settings values when env vars are unset for quiet hours - Validate IANA timezone strings in routine_create/update with parse_timezone - Add timezone field to routine_create tool schema - Allow standalone timezone update on cron routines without changing schedule - Return path from append_daily_log_tz to avoid TOCTOU race at midnight - Delegate append_daily_log to append_daily_log_tz(entry, UTC) to avoid drift - Preserve timezone through approval flow via PendingApproval.user_timezone - Improve test_today_in_tz to not depend on hardcoded year - Add 3 regression tests for quiet hours config validation Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in routine.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(timezone): address second round of review feedback - Remove .claude/scheduled_tasks.lock from repo and add to .gitignore - Store resolved timezone (not raw message.timezone) in PendingApproval - Carry forward user_timezone through chained approvals in thread_ops - Wire quiet_hours_start/end from config to HeartbeatRunner - Support X-Timezone header as fallback in chat_send_handler [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(timezone): include user's local time in time tool response The time tool's "now" operation now returns local_iso and timezone fields based on ctx.user_timezone, so the LLM can report time in the user's timezone instead of always UTC. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in time.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(timezone): address Copilot review round 3 — validation, deterministic tests, schema fixes - Validate DEFAULT_TIMEZONE and HEARTBEAT_TIMEZONE at config load time - Add timezone field to HeartbeatSettings and config::HeartbeatConfig - Wire heartbeat timezone from config through agent_loop to HeartbeatRunner - Add timezone to routine_update tool schema (was accepted but not advertised) - Error on schedule/timezone update for non-cron routines - Validate timezone in Trigger::from_db (coerce invalid to None with warning) - Validate timezone in approval path (thread_ops.rs) before overwriting - Time tool always includes timezone/local_iso fields (fallback to UTC) - Make quiet hours tests deterministic using current UTC hour - Add regression tests for config validation [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
9f71bd0d44 |
feat: unified thread model for web gateway (#607)
* feat: unified thread model for web gateway Every piece of activity (user chat, routine run, heartbeat alert, external channel message) now lives in its own thread, properly isolated, with meaningful titles and visual distinction. Key changes: - Add `channel` field to ConversationSummary and ThreadInfo so the gateway can distinguish thread origins (gateway, telegram, routine, heartbeat). - Add `list_conversations_all_channels` to Database trait (both postgres and libsql) so chat_threads_handler shows cross-channel threads. - Routine runs get a persistent conversation per routine via `get_or_create_routine_conversation`; notifications carry thread_id. - Heartbeat gets a persistent conversation via `get_or_create_heartbeat_conversation`; HeartbeatRunner accepts an optional Database store and binds notifications to the thread. - Fix broadcast() in web gateway to propagate response.thread_id instead of hardcoding empty string. - Fix isCurrentThread(null) returning true (the core notification leak bug) — now returns false so events without a thread_id don't leak into the active thread. - Rewrite frontend thread sidebar: meaningful titles with channel-specific fallbacks, relative timestamps instead of turn counts, channel badges for non-gateway threads, unread notification dots, read-only indicator for external channel threads. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review — TOCTOU races, stale comment, debounce, broadcast warning - Fix TOCTOU race in get_or_create_routine_conversation (postgres): use INSERT ON CONFLICT on new uq_conv_routine unique index + SELECT-back. - Fix TOCTOU race in get_or_create_heartbeat_conversation (postgres): use INSERT ON CONFLICT on new uq_conv_heartbeat unique index + SELECT-back. - Fix TOCTOU race in get_or_create_routine_conversation (libsql): use BEGIN IMMEDIATE transaction to serialize concurrent writers. - Fix TOCTOU race in get_or_create_heartbeat_conversation (libsql): use BEGIN IMMEDIATE transaction to serialize concurrent writers. - Add V11 migration with partial unique indexes for postgres. - Add matching unique indexes to libsql schema. - Update stale comment on isCurrentThread (said "always shown" but logic now returns false for missing thread_id). - Debounce loadThreads() on off-thread SSE events to prevent request storms. - Log warning in broadcast() when thread_id is None (clients will drop it). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: sort in-memory thread fallback by updated_at descending The in-memory thread list fallback (when no DB is available) used HashMap::values() which has no guaranteed ordering. Sort by updated_at descending to match the SQL query ordering. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: retry libsql connect() on transient "unable to open database file" The cron ticker's background task occasionally fails with "unable to open database file" when creating a new SQLite connection concurrently with the main thread. Add retry with exponential backoff (50ms, 100ms, 200ms) to handle transient VFS/locking issues in libsql's local mode. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use ON CONFLICT with index expressions instead of named constraints PostgreSQL ON CONFLICT ON CONSTRAINT requires a named table constraint, but V11 migration creates unique indexes. Switch to the expression form (ON CONFLICT (columns) WHERE condition) which works with unique indexes. Also fix dead code in threadTitle() where thread.title was already checked on the previous line. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix rustfmt chain collapse in heartbeat.rs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: skip broadcast when thread_id is None instead of sending empty Clients drop SSE events with empty thread_id anyway, so avoid the unnecessary network traffic by returning early. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add libsql routine/heartbeat conversation idempotency tests Add tests proving get_or_create_routine_conversation returns the same conversation ID across multiple invocations with the same routine_id. Add debug logging to routine engine to track conversation resolution. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: show "New chat" title for empty threads - threadTitle() returns "New chat" when turn_count is 0 - Assistant thread label updates dynamically from API data - Default HTML label changed from "Assistant" to "New chat" - New threads naturally sort to top via last_activity DESC [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: thread sorting, routine isolation, and UI polish - Fix libsql timestamp format mismatch causing broken thread sort order. SQLite defaults used `datetime('now')` (space-separated) while Rust code used RFC3339 (T-separated), breaking string-based ORDER BY. All INSERTs now use RFC3339, and queries use `datetime()` to normalize comparison. - Route manual routine triggers through RoutineEngine.fire_manual() instead of injecting as regular chat messages, so routines always run in their dedicated conversation thread. - Add RoutineEngineSlot to GatewayState for gateway<->engine communication. - Derive routine thread titles from conversation metadata (routine_name) instead of showing truncated UUID hashes. - Make chat_new_thread_handler persist to DB synchronously so loadThreads() sees newly created threads immediately. - Fix enableChatInput() no-op and wrong element ID in disableChatInputReadOnly(). - Fix handlers/chat.rs stale gateway-only query (use list_conversations_all_channels). - Sort in-memory threads by DateTime before converting to RFC3339 strings. - Trigger debouncedLoadThreads() on thinking/status SSE events for non-current threads so routine/heartbeat threads appear in sidebar promptly. - Remove "Threads" text from sidebar header. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: routine history display, orphaned tool_results, duplicate system messages Three independent fixes with regression tests: 1. Routine conversations now display in the web UI. build_turns_from_db_messages() handles standalone assistant messages (no preceding user message) by creating turns with empty user_input. Frontend skips empty user bubbles. 2. Worker select_tools and execute_plan paths now push an assistant_with_tool_calls message before tool execution, preventing sanitize_tool_messages from rewriting tool_results as orphaned user messages. 3. Reasoning::plan() and respond_with_tools() merge system messages from context into a single system prompt instead of creating [system, system, ...] sequences that strict LLM providers (Qwen) reject. Also: sidebar padding/spacing improvements, wider thread panel (240px). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR #607 review — RwLock held across await, missing ownership check, heartbeat config - Clone Arc<RoutineEngine> out of RwLock before .await in trigger handler - Add user_id ownership check to fire_manual() with NotAuthorized error - Wire heartbeat notify_user/notify_channel from config to AgentHeartbeatConfig Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: gitignore trace_*.json files and remove stale traces Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: remove trace JSON files from repo Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: proper HTTP status codes for routine errors, read-only input guard, respond thread_id - Map RoutineError::NotFound → 404, NotAuthorized → 403, Disabled → 409 - Guard enableChatInput() against re-enabling on read-only threads - Skip respond() when thread_id is None (matches broadcast() behavior) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
ce5961b1ec |
fix(libsql): support flexible embedding dimensions (#534)
* fix(libsql): support flexible embedding dimensions (#494) The libSQL schema hardcoded F32_BLOB(1536) for the embedding column, preventing use of models with other dimensions (e.g. 768-dim nomic-embed-text). This adds incremental migration support to the libSQL backend and a V9 migration that rebuilds the memory_chunks table with a plain BLOB column accepting any dimension. - Add incremental migration infrastructure (INCREMENTAL_MIGRATIONS array + run_incremental() runner tracked via _migrations table) - V9 migration rebuilds memory_chunks with BLOB column, drops the vector index (which requires fixed-dimension F32_BLOB) - Update base schema for fresh installs (BLOB, no vector index) - Vector search gracefully falls back to FTS-only when the index is absent (matches PostgreSQL behavior after its V9 migration) - Remove now-incorrect "dimension is not 1536" warnings Existing embeddings are preserved during migration. Users only need to re-embed if they change their embedding model/dimension. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: wrap incremental migrations in transaction for atomicity Address PR review feedback: if the process crashes after executing migration SQL but before recording it in _migrations, the migration would be applied but not marked complete. Wrapping both operations in a transaction ensures they succeed or fail together. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: merge main and fix formatting drift Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
470de5bd2d |
feat: merge http/web_fetch tools, add tool output stash for large responses (#578)
* feat: merge http/web_fetch tools, add tool output stash for large responses Merge `web_fetch` into `http` tool with smart approval: plain GETs (no headers, no body) run without approval and follow redirects with SSRF re-validation per hop; all other requests require approval as before. Add `tool_output_stash` on JobContext so full tool outputs are preserved before safety-layer truncation. The `json` tool gains a `source_tool_call_id` parameter to reference stashed outputs, enabling reliable parsing of large API responses that exceed the 100KB context limit. Other improvements: - Descriptive User-Agent header using CARGO_PKG_VERSION - Truncation now keeps partial data + hint about source_tool_call_id - System prompt reinforces tool_calls over narration - json tool query/stringify handle pre-parsed (non-string) data [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: delete dead web_fetch.rs (merged into http tool) Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix rustfmt formatting Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: rename shadowed data binding for clarity in json tool Address PR review: rename owned `data` to `data_value` before re-binding as `let data = &data_value` to make ownership explicit. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(ci): mark network-dependent trace tests as #[ignore] The weather_sf and baseball_stats tests hit live external APIs (wttr.in, ESPN) which are unreliable in CI. Mark them #[ignore] so they don't block the pipeline. Run locally with `--ignored` to include them. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: replay recorded HTTP exchanges in trace tests instead of hitting live APIs Wire ReplayingHttpInterceptor into TestRig when the trace fixture contains http_exchanges. This replays recorded responses instead of making live network calls, making tests deterministic and CI-stable. Add captured HTTP responses to weather_sf.json (wttr.in) and baseball_stats.json (ESPN API) fixtures. Revert #[ignore] on both tests — they now run offline. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: recover inline bracket-format tool calls from LLM text responses When flatten_tool_messages converts tool calls to text like `[Called tool `http` with arguments: {...}]` for NEAR AI compatibility, the LLM sometimes echoes this format back in its text responses instead of using proper tool_calls. Add recovery for this bracket format in recover_tool_calls_from_content and strip it in clean_response so users don't see raw tool call syntax. 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]> |
||
|
|
d562dc8d90 |
fix(workspace): thread document path through search results (#503)
* fix(workspace): thread document path through search results Memory search results were showing chunk UUIDs instead of source file paths. Thread document_path through RankedResult, SearchResult, and the RRF fusion pipeline so handlers can display the actual file path. Fixes #481 Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: use into_iter to move values instead of cloning Address review feedback: consume results with into_iter() to move String fields directly instead of cloning them. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
f18fb5173b |
feat(web): fix jobs UI parity for non-sandbox mode (#491)
* feat(web): fix jobs UI parity for non-sandbox mode The web gateway Jobs UI was built primarily for sandbox (Docker) jobs. When running without sandbox (common for NEAR AI hosted envs), multiple features were broken. This change fixes all of them: - Agent jobs now broadcast live SSE events to the web UI (Activity tab) - Agent job restart via scheduler.dispatch_job (not chat message) - Follow-up prompts for agent jobs via WorkerMessage injection - Capability flags (can_restart, can_prompt, job_kind) in job detail API - Rate-limit retry with cap (10 consecutive) and Retry-After header parsing - Plan interruption on user message (breaks out of plan, re-evaluates) - Correct SSE status field in mark_completed/mark_failed/mark_stuck - SseManager preserved across rebuild_state calls Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fix formatting in db/mod.rs and nearai_chat.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> |
||
|
|
6481448d50 |
feat(web): DB-backed Jobs tab + scheduler-dispatched local jobs (#436)
* feat(web): DB-backed Jobs tab, scheduler-dispatched local jobs, remove active-jobs-bar - Remove active-jobs-bar UI element (HTML, CSS, JS polling) - Move job handlers from server.rs to handlers/jobs.rs - Remove user_id scoping (single-user gateway) - Add list_agent_jobs() and agent_job_summary() to Database trait (both postgres and libsql backends) for non-sandbox job visibility - Wire SchedulerSlot into CreateJobTool so execute_local dispatches via scheduler (persists to DB + spawns worker) instead of creating phantom ContextManager-only jobs - Update /status and /list slash commands to read from DB for consistency with Jobs tab - Fix worker mark_completed: skip if already terminal or stuck - Add agent job cancel via DB update in both web handler and slash cmd - Add Stuck → Completed guard with tracing in worker completion path Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix: address PR review comments - Log warning when get_context fails in worker completion path - Extract duplicated status-counting logic into AgentJobSummary::add_count() helper, used by both postgres and libsql backends Co-Authored-By: Claude Sonnet 4.6 <[email protected]> --------- Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Nick Pismenkov <[email protected]> |
||
|
|
a65b282066 |
fix: web UI routines tab shows all routines regardless of creating channel (#391)
Routines created via Telegram (or any WASM channel) were invisible in the web UI because the routines list endpoint filtered by GATEWAY_USER_ID, which didn't match the Telegram user's ID stored on the routine. Add list_all_routines() to the RoutineStore trait (both libSQL and PostgreSQL backends) and use it in the web dashboard handlers so all routines are visible regardless of which channel created them. Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> |
||
|
Henry ParkandGitHub
|
ddd01a628c | feat(web): persist tool calls, restore approvals on thread switch, and UI fixes (#382) | ||
|
|
04d3b005b1 |
feat: implement FullJob routine mode with scheduler dispatch (#288)
* feat: implement FullJob routine mode with scheduler dispatch FullJob routines previously fell back to lightweight mode (single LLM call, no tools) with a warning. This wires them to the existing Scheduler/Worker infrastructure so they dispatch real jobs with full tool access. Fire-and-forget model: the routine creates a job via ContextManager, schedules it, links the routine_run to the job_id, and completes immediately. The job runs independently with full tool access. - Add RoutineError::JobDispatchFailed variant - Add RoutineStore::link_routine_run_to_job (PostgreSQL + libSQL) - Add execute_full_job() in routine_engine with context_manager/scheduler - Wire context_manager + scheduler into RoutineEngine from agent_loop - Fix pre-existing clippy warnings in tests/html_to_markdown.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: persist job to DB before scheduling in execute_full_job The worker emits job_actions and llm_calls rows that reference agent_jobs via foreign key. Without persisting the job first, those inserts can fail. Match the pattern from commands.rs: fetch JobContext, save_job(), then schedule. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: consolidate job dispatch into Scheduler::dispatch_job and wire max_iterations Move the create + persist + schedule sequence into a single Scheduler::dispatch_job() method so callers (commands.rs, routine_engine.rs) don't duplicate the logic. FullJob routines now pass max_iterations via job metadata, and the worker reads it (defaulting to 50 if unset). Also removes the context_manager field from RoutineEngine since dispatch_job handles everything internally. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: clamp max_iterations to 500 and log category update failures Address PR review feedback: - worker.rs: clamp max_iterations from metadata to MAX_WORKER_ITERATIONS (500) to prevent unbounded LLM token usage from malicious/buggy configs - commands.rs: log warning on category update failure instead of silently discarding the error Co-Authored-By: Claude Opus 4.6 <[email protected]> * 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]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
250551799b |
style: adopt agent-market design language for web UI (#282)
* fix: move Logs to status bar and fix chat history ordering after restart
Move the Logs tab out of the main tab bar and into the right-side status
area as a compact pill button next to "Connected". Remove it from the
Ctrl+1-N shortcut order (now Ctrl+1-5).
Fix chat message ordering in libSQL backend: datetime('now') has only
second precision, so back-to-back user+assistant inserts got identical
timestamps causing non-deterministic ORDER BY. Now passes explicit
millisecond-precision timestamps and uses rowid as tiebreaker for
existing data.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* refactor: separate WASM extensions from MCP servers on Extensions page
Reorganize the Extensions tab into 5 distinct sections: Installed
Extensions, Available WASM Extensions, Install WASM Extension (by
tar.gz URL), MCP Servers (with Add Custom form), and Registered Tools.
Registry entries are now filtered client-side by kind so WASM tools/
channels and MCP servers each have dedicated UI sections.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* style: adopt agent-market design language for web UI
Refresh the web gateway visual identity with a cleaner, modern aesthetic:
deeper blacks, green accent palette, DM Sans + IBM Plex Mono typography,
larger border-radii, glassmorphic navigation, refined hover effects,
pill badges, and green focus rings. CSS-only change plus Google Fonts.
Co-Authored-By: Claude Opus 4.6 <[email protected]>
* Update src/channels/web/static/style.css
Co-authored-by: Copilot <[email protected]>
* Update src/channels/web/static/style.css
Co-authored-by: Copilot <[email protected]>
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Copilot <[email protected]>
|
||
|
|
3f135bdde9 |
fix: persist turns after approval and add agent-level tests (#250)
* fix: persist turns after approval and add agent-level tests Port relevant changes from PR #112 that were not carried over to #237: - Add persist_turn calls in process_approval for the response, error, and auth-required paths. Previously, turns completed after tool approval were never persisted to DB — if the process crashed after approval the entire turn (user message + assistant response) was lost. - Add agent-level unit tests: StaticLlmProvider mock, make_test_agent helper, tests for auto-approval logic, destructive shell command detection, and PendingApproval backward-compatible deserialization (without deferred_tool_calls field). - Remove unused _thread_state binding in process_approval. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address 14 audit findings in src/agent/ Audit of the agent module found 2 High, 7 Medium, 3 Low, and 2 Nit severity issues. This commit fixes all of them: High: - Remove 4 `.expect()` calls in session.rs (entry API, match, direct indexing, if-let) to eliminate panic paths in production - Add typed RoutineError enum replacing Result<_, String> across routine.rs, routine_engine.rs, and callers in history/store.rs and db/libsql/mod.rs Medium: - Sanitize routine names in path construction to prevent directory traversal (routine_engine.rs) - Log warnings for 5 silently-swallowed errors in scheduler.rs, compaction.rs, and worker.rs - Extract shared handle_auth_intercept helper to deduplicate auth interception in thread_ops.rs - Add session count warning threshold in session_manager.rs - Make FullJob stub degradation visible via warn-level log and prepended warning in output Low: - Restrict dead code visibility with #[cfg(test)] on 19 unused items in submission.rs, task.rs, and undo.rs - Narrow pub to pub(crate) on self_repair.rs builder methods - Remove TaskStatus from mod.rs re-exports (test-only type) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments - Reorder persist_turn before persist_response_chain so the conversation row exists before the metadata UPDATE runs - Add persist_response_chain call to handle_auth_intercept so auth-required paths preserve the response chain - Harden sanitize_routine_name to use allowlist (alphanumeric, dash, underscore) instead of denylist replacements - Fix stale active_thread ID in get_or_create_thread: fall back to create_thread() when the stored ID is missing from the map - Persist turn on approval rejection so user messages survive crashes after a tool is rejected Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> |
||
|
|
ffb1cc9be8 |
refactor: architecture improvements for contributor velocity (#198)
* refactor: split large files and consolidate test stubs for contributor velocity - Extract 7 Database sub-traits (ConversationStore, JobStore, SandboxStore, RoutineStore, ToolFailureStore, SettingsStore, WorkspaceStore) with Database as a supertrait combining them all - Split libsql_backend.rs (2769 lines) into src/db/libsql/ directory with one file per sub-trait implementation - Split config.rs (1753 lines) into src/config/ directory with 16 domain files - Consolidate 3 duplicate test LLM stubs into shared StubLlm in src/testing.rs - Split server.rs handlers into src/channels/web/handlers/ directory - Extract main.rs init phases into AppBuilder (src/app.rs) - Add developer setup script (scripts/dev-setup.sh) Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: move heartbeat test from examples/ to tests/ Convert standalone example binary into a proper #[ignore] integration test, matching the convention of the other integration tests. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix rustfmt formatting for CI Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments from Copilot - tunnel.rs: replace .ok().flatten() with ? to propagate env var errors - secrets.rs: remove misleading "process-wide cache" comment - database.rs: use uppercase "DATABASE_URL" in error key - testing.rs: gate harness tests with #[cfg(feature = "libsql")] 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]> |