61 Commits

Include renames

Author	SHA1	Message	Date
3 people	8a320ae9db	fix(routines): complete full_job execution reliability overhaul (#1650) ... * fix(routines): persist full LLM transcript and remove sandbox gate for full_job Routine execution output was invisible — routine_fire returned a one-liner, routine_history had no actual output, and the conversation thread contained only a summary. Full-job routines also hard-failed without Docker. Three fixes: 1. **Full transcript persistence**: execute_lightweight now persists every message (prompt, LLM responses, tool calls with params, tool results) to the routine's conversation thread as it executes, not just a summary after the fact. 2. **Routine output visibility**: routine_history includes conversation_id and recent_output messages. routine_fire tells the user to check routine_history. Web detail page has a "View Execution Thread" button that navigates to the chat tab. ROUTINE_OK stores "No issues found" instead of None. Full-job summary pulls actual job output instead of generic "Job X finished". 3. **Remove SandboxReadiness gate**: full_job routines dispatch through the scheduler like regular /job commands — no Docker required. The SandboxReadiness enum is removed entirely. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: apply cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(worker): treat AutonomousUnavailable tool errors as recoverable The job worker crashed the entire job when a tool was denied for autonomous execution (e.g. secret_list). The error was already recorded in reason_ctx for the LLM to see, but process_tool_result_job returned Err which propagated through the agentic loop and terminated the job. Now all tool errors (including AutonomousUnavailable) return Ok, letting the LLM see the denial and try a different approach. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(llm): sanitize tool names for OpenAI Codex Responses API The Codex API requires tool names to match `^[a-zA-Z0-9_-]+$` but MCP/extension tools can have dots in their names (e.g. `mcp.server.tool`). This caused HTTP 400 errors when the job worker sent tool calls back to the LLM. Sanitize tool names in both `convert_tool_definition` and `convert_message` (function_call items) by replacing invalid characters with underscores. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(routines): inject execution context into full_job description [skip-regression-check] When a full_job routine dispatches a job, the LLM had no context that it was already executing inside a routine. It wasted iterations on infrastructure (discovering tools, creating routines, setting up auth) instead of doing the actual work. Prepend a clear directive to the job description telling the LLM that tools and the routine are already configured, and to execute the task directly. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(mcp): auto-refresh expired OAuth tokens on access [skip-regression-check] When IronClaw restarts, MCP servers fail with "Secret has expired" because get_access_token() checks token expiry locally and returns an error before any HTTP request is made — so the existing 401-retry refresh logic never triggers. Now get_access_token() catches SecretError::Expired and automatically calls refresh_access_token() using the stored refresh token. If the refresh succeeds, the new token is returned transparently. If it fails, the error message includes both the expiry and the refresh failure. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(mcp): align refresh token naming and set expiry on stored tokens Two bugs prevented MCP OAuth token auto-refresh on restart: 1. Naming mismatch: the hosted OAuth flow stored the refresh token as `{token_secret_name}_refresh_token` (e.g. `mcp_notion_access_token_refresh_token`) but `McpServerConfig::refresh_token_secret_name()` returned `mcp_notion_refresh_token`. The refresh token was there but unfindable. 2. Missing expiry: `store_tokens` in auth.rs never called `with_expiry()` even though `AccessToken::expires_in` was available. Combined with the fix from the previous commit (auto-refresh on Expired), tokens stored via the MCP auth flow will now also trigger refresh correctly. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(web): show activity and transitions for agent jobs in job detail [skip-regression-check] The job events endpoint only checked sandbox jobs for ownership, returning 404 for agent jobs dispatched from routines. The detail handler also returned empty transitions for agent jobs. - events handler: fall back to agent job ownership check - detail handler: populate transitions from job's state history Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(routines): expose max_iterations for full_job routines (default 25) The max_iterations parameter was hardcoded to 10 and not configurable via routine_create or routine_update, causing complex tasks to hit the iteration cap. - Add max_iterations to full_job execution schema (1-200, default 25) - Thread it through parse → build → RoutineAction - Support updating via routine_update - Raise default from 10 to 25 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(routines): break self-dialogue loop after full_job plan execution After plan execution, the completion-check Q&A ("Is the job complete?" / "No, not complete...") was left in the message context, causing the agentic loop to repeat the same analysis instead of calling tools. Replace the stale dialogue with an action-oriented continuation prompt that instructs the LLM to use tools for remaining work. Also strip <suggestions> tags from all job output since they're only meaningful for interactive chat sessions. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(repl): prevent test hang in single-message mode In single-message mode, start() stored a clone of the mpsc sender in self.msg_tx for approval injection. After the thread sent /quit and exited, the stored clone kept the stream alive, so stream.next() blocked forever in the test assertion that the stream ends. Skip storing the sender in single-message mode since interactive approval is not needed. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(jobs): treat text responses as final answer in agentic loop When the LLM produces a non-empty text response with no tool intent (already filtered by the nudge mechanism), it is the job's final answer. Previously, handle_text_response only exited the loop if the text matched rigid completion phrases like "job is complete". Natural summaries like "Weekly review completed and saved to Notion" were added to context and the loop continued, causing the LLM to restate the same summary until max_iterations was hit. Now any non-empty text response marks the job complete and stops the loop, matching the chat dispatcher behavior. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * perf(tests): reduce skills catalog network failure test from 10s to 1s The test_search_returns_error_on_network_failure test connects to an unreachable RFC 5737 TEST-NET IP and waited for the full 10s production REQUEST_TIMEOUT. Add with_url_and_timeout test helper and use a 1s timeout instead. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(tools): accept 'message' as alias for 'content' in message tool LLMs frequently call the message tool with {"message": "..."} instead of {"content": "..."}. Fall back to the 'message' key when 'content' is missing to avoid InvalidParameters errors during autonomous job execution. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(tools): attach thread_id for gateway broadcast in message tool When the message tool broadcasts to all channels (channel=null), it sent an OutgoingResponse without a thread_id. The gateway silently dropped these messages (returned Ok but never sent the SSE event), so they appeared in repl but not in the web UI. The thread_id was only populated when channel was explicitly "gateway". Now it is always populated from notify_thread_id metadata, so broadcast_all delivers to the gateway correctly. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(gateway): return error instead of silently dropping messages Gateway broadcast() and respond() previously returned Ok(()) when thread_id was missing, silently swallowing the message. Callers (message tool, agent loop) believed delivery succeeded when it didn't. Now returns ChannelError::MissingRoutingTarget so callers can detect and report the failure. Four regression tests verify the contract: respond/broadcast with and without thread_id. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: resolve rebase conflicts with staging Restore sandbox_readiness field removed by pre-rebase commits (staging still uses it). Update repl test to match staging's single-message behavior (no longer sends /quit). Add missing reasoning field to ToolCall in codex test. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(tools): log error when routine conversation lookup fails The routine_history tool silently swallowed errors from get_or_create_routine_conversation, returning empty output without any diagnostic logging. Add tracing::warn so failures are visible in logs. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR #1650 review comments - E2E test: accept submitted/accepted as success states in job assertion - TimeTool: remove operation from required schema (defaults to "now") - jobs handler: log DB errors server-side, return generic message to client - routines handler: use read-only find_routine_conversation on GET - codex provider: reverse-map sanitized tool names so MCP tools resolve Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian review feedback on PR #1650 - MCP refresh token: fall back to legacy secret name (mcp_{name}_refresh_token) so existing users don't need to re-authenticate after the naming fix - Job worker: replace fragile messages.pop() with truncate-to-saved-count to avoid maintenance hazard if message flow changes - Document cost implications of max_iterations 10->25 default bump - Revert Cargo.toml dist profile change (thin LTO comment, codegen-units=16) as it's unrelated to this PR Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: resolve rebase conflicts and address new Copilot comments - Fix no_silent_drop tests for updated GatewayConfig (user_id moved to GatewayChannel::new second arg, user_tokens removed) - Fix handle_text_response param name (_reason_ctx -> reason_ctx) - Fix missing has_text_response field in test JobDelegate - Propagate row.get errors in find_routine_conversation instead of unwrap_or_default - Only fall back to legacy refresh token name on NotFound/Expired, propagate real errors (DB, decryption) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-28 12:27:43 -07:00
3 people	8f8cb7f7b1	feat: DB-backed user management, admin secrets provisioning, and multi-tenant isolation (#1626) ... * feat: complete multi-tenant isolation — per-user budgets, model selection, heartbeat cycling Finishes the remaining isolation work from phases 2–4 of #59: Phase 2 (DB scoping): Fix /status and /list commands to use _for_user DB variants instead of global queries that leaked cross-user job data. Phase 3 (Runtime isolation): Per-user workspace in routine engine's spawn_fire so lightweight routines run in the correct user context. Per-user daily cost tracking in CostGuard with configurable budget via MAX_COST_PER_USER_PER_DAY_CENTS. Multi-user heartbeat that cycles through all users with routines, auto-detected from GATEWAY_USER_TOKENS. Phase 4 (Provider/tools): Per-user model selection via preferred_model setting — looked up from SettingsStore on first iteration, threaded through ReasoningContext.model_override to CompletionRequest. Works with providers that support per-request model overrides (NearAI). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: use selected_model setting key to match /model command persistence The dispatcher was reading "preferred_model" but the /model command (merged from staging) persists to "selected_model". Since set_setting is already per-user scoped, using the same key makes /model work as the per-user model override in multi-tenant mode. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: heartbeat hygiene, /model multi-tenant guard, RigAdapter model override Three follow-up fixes for multi-tenant isolation: 1. Multi-user heartbeat now runs memory hygiene per user before each heartbeat check, matching single-user heartbeat behavior. 2. /model command in multi-tenant mode only persists to per-user settings (selected_model) without calling set_model() on the shared LlmProvider. The per-request model_override in the dispatcher reads from the same setting. Added multi_tenant flag to AgentConfig (auto-detected from GATEWAY_USER_TOKENS). 3. RigAdapter now supports per-request model overrides by injecting the model name into rig-core's additional_params. OpenAI/Anthropic/Ollama API servers use last-key-wins for duplicate JSON keys, so the override takes effect via serde's flatten serialization order. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — cost model attribution, heartbeat concurrency, pruning Fixes from review comments on #1614: - Cost tracking now uses the override model name (not active_model_name) when a per-user model override is active, for accurate attribution. - Multi-user heartbeat runs per-user checks concurrently via JoinSet instead of sequentially, preventing one slow user from blocking others. - Per-user failure counts tracked independently; users exceeding max_failures are skipped (matching single-user semantics). - per_user_daily_cost HashMap pruned on day rollover to prevent unbounded growth in long-lived deployments. - Doc comment fixed: says "routines" not "active routines". Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: /status ownership, model persistence scoping, heartbeat robustness Addresses second round of PR review on #1614: - /status <job_id> DB path now validates job.user_id == requesting user before returning data (was missing ownership check, security fix). - persist_selected_model takes user_id param instead of owner_id, and skips .env/TOML writes in multi-tenant mode (these are shared global files). handle_system_command now receives user_id from caller. - JoinSet collection handles Err(JoinError) explicitly instead of silently dropping panicked tasks. - Notification forwarder extracts owner_id from response metadata in multi-tenant mode for per-user routing instead of broadcasting to the agent owner. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: cost pricing, fire_manual workspace, heartbeat concurrency cap Round 3 review fixes: - Cost tracking passes None for cost_per_token when model override is active, letting CostGuard look up pricing by model name instead of using the default provider's rates (serrrfirat). - fire_manual() now uses per-user workspace, matching spawn_fire() pattern (serrrfirat). - Removed MULTI_TENANT env var — multi-tenant mode is auto-detected solely from GATEWAY_USER_TOKENS presence (serrrfirat + Copilot). - Multi-user heartbeat capped at 8 concurrent tasks to avoid flooding the LLM provider (serrrfirat + Copilot). - Fixed inject_model_override doc comment accuracy (Copilot). - Added comment explaining multi-tenant notification routing priority (Copilot). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: user-scoped webhook endpoint for multi-tenant isolation Adds POST /api/webhooks/u/{user_id}/{path} — a user-scoped webhook endpoint that filters the routine lookup by user_id, preventing cross-user webhook triggering when paths collide. The existing /api/webhooks/{path} endpoint remains unchanged for backward compatibility in single-user deployments. Changes: - get_webhook_routine_by_path gains user_id: Option<&str> param - Both postgres and libsql implementations add AND user_id = ? filter when user_id is provided - New webhook_trigger_user_scoped_handler extracts (user_id, path) from URL and passes to shared fire_webhook_inner logic - Route registered on public router (webhooks are called by external services that can't send bearer tokens) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(db): add UserStore trait with users, api_tokens, invitations tables Foundation for DB-backed user management (#1605): - UserRecord, ApiTokenRecord, InvitationRecord types in db/mod.rs - UserStore sub-trait (17 methods) added to Database supertrait - PostgreSQL migration V14__users.sql (users, api_tokens, invitations) - libSQL schema + incremental migration V14 - Full implementations for both PgBackend (via Store delegation) and LibSqlBackend (direct SQL in libsql/users.rs) - authenticate_token JOINs api_tokens+users with active/non-revoked checks; has_any_users for bootstrap detection Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(web): DB-backed auth, user/token/invitation API handlers Adds the web gateway layer for DB-backed user management (#1605): Auth refactor: - CombinedAuthState wraps env-var tokens (MultiAuthState) + optional DbAuthenticator for DB-backed token lookup with LRU cache (60s TTL, 1024 max entries) - auth_middleware tries env-var tokens first, then DB fallback - From<MultiAuthState> impl for backward compatibility - main.rs wires with_db_auth when database is available API handlers (12 new endpoints): - /api/admin/users — CRUD: create, list, detail, update, suspend, activate - /api/tokens — create (returns plaintext once), list, revoke - /api/invitations — create, list, accept (creates user + first token) Token creation: 32 random bytes → hex plaintext, SHA-256 hash stored. Invitation accept: validates hash + pending + not expired, creates user record and first API token atomically. All test files updated for CombinedAuthState type change. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: startup env-var user migration + UserStore integration tests Completes the DB-backed user management feature (#1605): - Startup migration: when GATEWAY_USER_TOKENS is set and the users table is empty, inserts env-var users + hashed tokens into DB. Logs deprecation notice when DB already has users. - hash_token made pub for reuse in migration code. - 10 integration tests for UserStore (libsql file-backed): - has_any_users bootstrap detection - create/get/get_by_email/list/update user lifecycle - token create → authenticate → revoke → reject cycle - suspended user tokens rejected - wrong-user token revoke returns false - invitation create → accept → user created - record_login and record_token_usage timestamps - libSQL migration: removed FK constraints from V14 (incompatible with execute_batch inside transactions). Tables in both base SCHEMA and incremental migration for fresh and existing databases. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: remove GATEWAY_USER_TOKENS, fix review feedback GATEWAY_USER_TOKENS never went to production — replaced entirely by DB-backed user management via /api/admin/users and /api/tokens. Removed: - UserTokenConfig struct and GATEWAY_USER_TOKENS env var parsing - user_tokens field from GatewayConfig - GatewayChannel::new_multi_auth() constructor - Env-var user migration block in main.rs (~90 lines) - multi_tenant auto-detection from GATEWAY_USER_TOKENS (now runtime via db.has_any_users() in app.rs) Review fixes (zmanian): - User ID generation: UUID instead of display-name derivation (#1) - Invitation accept moved to public router (no auth needed) (#3) - libSQL get_invitation_by_hash aligned with postgres: filters status='pending' AND expires_at > now (#4) - UUID parse: returns DatabaseError::Serialization instead of unwrap_or_default (#7) - PostgreSQL SELECT * replaced with explicit column lists (#8) - Sort order aligned (both backends use DESC) (#6) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: add role-based access control (admin/member) Adds a `role` field (admin|member) to user management: Schema: - `role TEXT NOT NULL DEFAULT 'member'` added to users table in both PostgreSQL V14 migration and libSQL schema/incremental migration - UserRecord gains `role: String` field - UserIdentity gains `role: String` field, populated from DB in DbAuthenticator and defaulting to "admin" for single-user mode Access control: - AdminUser extractor: returns 403 Forbidden if role != "admin" - /api/admin/users/* handlers: require AdminUser (create, list, detail, update, suspend, activate) - POST /api/invitations: requires AdminUser (only admins can invite) - User creation accepts optional "role" param (defaults to "member") - Invitation acceptance creates users with "member" role Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(web): add Users admin tab to web UI Adds a Users tab to the web gateway UI for managing users, tokens, and roles without needing direct API calls. Features: - User list table with ID, name, email, role, status, created date - Create user form with display name, email, role selector - Suspend/activate actions per user - Create API token for any user (shows plaintext once with copy button) - Role badges (admin highlighted, member muted) - Non-admin users see "Admin access required" message - Keyboard shortcut: Cmd/Ctrl+5 switches to Users tab CSS: - Reuses routines-table styles for the user list - Badge, token-display, btn-small, btn-danger, btn-primary components Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: move Users to Settings subtab, bootstrap admin user on first run - Moved Users from top-level tab to Settings sidebar subtab (under Skills, before Theme toggle) - On first startup with empty users table, automatically creates an admin user from GATEWAY_USER_ID config with a corresponding API token from GATEWAY_AUTH_TOKEN. This ensures the owner appears in the Users panel immediately. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: user creation shows token, + Token works, no password save popup Three UI/UX fixes: 1. Create user now generates an initial API token and shows it in a copy-able banner instead of triggering the browser's password save dialog. Uses autocomplete="off" and type="text" for email field. 2. "+ Token" button works: exposed createTokenForUser/suspendUser/ activateUser on window for inline onclick handlers in dynamically generated table rows. Token creation uses showTokenBanner helper. 3. Admin token creation: POST /api/tokens now accepts optional "user_id" field when the requesting user is admin, allowing token creation for other users from the Users panel. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: use event delegation for user action buttons (CSP compliance) Inline onclick handlers are blocked by the Content-Security-Policy (script-src 'self' without 'unsafe-inline'). Switched to data-action attributes with a delegated click listener on the users table. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add i18n for Users subtab, show login link on user creation - Added 'settings.users' i18n key for English and Chinese - Token banner now shows a full login link (domain/?token=xxx) with a Copy Link button, plus the raw token below - Login link works automatically via existing ?token= auto-auth Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: token hash mismatch — hash hex string, not raw bytes Critical auth bug: token creation hashed the raw 32 bytes (hasher.update(token_bytes)) but authentication hashed the hex-encoded string (hash_token(candidate) where candidate is the hex string the user sends). This meant newly created tokens could never authenticate. Fixed all 4 token creation sites (users, tokens, invitations create, invitations accept) to use hash_token(&plaintext_token) which hashes the hex string consistently with the auth lookup path. Removed now-unused sha2::Digest imports from handlers. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: remove invitation system The invitation flow is redundant — admin create user already generates a token and shows a login link. Invitations add complexity without value until email integration exists. Removed: - InvitationRecord struct and 4 UserStore trait methods - invitations table from V14 migration (postgres + both libsql schemas) - PostgreSQL Store methods (create/get/accept/list invitations) - libSQL UserStore invitation methods + row_to_invitation helper - invitations.rs handler file (212 lines) - /api/invitations routes (create, list, accept) - test_invitation_lifecycle test Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: user deletion, self-service profile, per-user job limits, usage API Four multi-tenancy improvements: 1. User deletion cascade (DELETE /api/admin/users/{id}): Deletes user and all data across 11 user-scoped tables (settings, secrets, routines, memory, jobs, conversations, etc.). Admin only. 2. Self-service profile (GET/PATCH /api/profile): Users can read and update their own display_name and metadata without admin privileges. 3. Per-user job concurrency (MAX_JOBS_PER_USER env var): Scheduler checks active_jobs_for(user_id) before dispatch. Prevents one user from exhausting all job slots. 4. Usage reporting (GET /api/admin/usage?user_id=X&period=day|week|month): Aggregates LLM costs from llm_calls via agent_jobs.user_id. Returns per-user, per-model breakdown of calls, tokens, and cost. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: add TenantCtx for compile-time tenant isolation Implements zmanian's architectural proposal from #1614 review: two-tier scoped database access (TenantScope/AdminScope) so handler code cannot accidentally bypass tenant scoping. TenantScope (default): wraps user_id + Arc<dyn Database>, auto-binds user_id on every operation. ID-based lookups return None for cross- tenant resources. No escape hatch — forgetting to scope is a compile error. AdminScope (explicit opt-in): cross-tenant access for system-level components (heartbeat, routine engine, self-repair, scheduler, worker). TenantCtx bundles TenantScope + workspace + cost guard + per-user rate limiting. Constructed once per request in handle_message, threaded through all command handlers and ChatDelegate. Key changes: - New src/tenant.rs (~920 lines): TenantScope, AdminScope, TenantCtx, TenantRateState, TenantRateRegistry - All command handlers: user_id: &str → ctx: &TenantCtx - ChatDelegate: cost check/record/settings via self.tenant - System components: store field changed to AdminScope - Config: TENANT_MAX_LLM_CONCURRENT, TENANT_MAX_JOBS_CONCURRENT env vars - Fixes bug: /status <job_id> cross-tenant leak (now auto-filtered) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR #1626 review feedback — bounded LRU cache, admin auth, FK cleanup - Replace HashMap with lru::LruCache in DbAuthenticator so the token cache is hard-bounded at 1024 entries (evicts LRU, not just expired) - Gate admin user endpoints (list/detail/update/suspend/activate) with AdminUser extractor so members get 403 instead of full access - Add api_tokens to libSQL delete_user cleanup list to prevent orphaned tokens (libSQL has no FK cascade) - Add regression tests for all three fixes Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: update CA certificates in runtime Docker image Ensures the root certificate bundle is current so TLS handshakes to services like Supabase succeed on Railway. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: resolve CI failures — formatting, no-panics check - Run cargo fmt on test code - Replace .expect() with const NonZeroUsize in DbAuthenticator - Add // safety: comments for test-only code in multi_tenant.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: switch PostgreSQL TLS from rustls to native-tls rustls with rustls-native-certs fails TLS handshake on Railway's slim container (empty or stale root cert store). native-tls delegates to OpenSSL on Linux which handles system certs more reliably. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * Adding user management api * feat: admin secrets provisioning API + API documentation - Add PUT/GET/DELETE /api/admin/users/{id}/secrets/{name} endpoints for application backends to provision per-user secrets (AES-256-GCM encrypted) - Add secrets_store field to GatewayState with builder wiring - Create docs/USER_MANAGEMENT_API.md with full API spec covering users, secrets, tokens, profile, and usage endpoints - Update web gateway CLAUDE.md route table Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add CatchPanicLayer to capture handler panics Without this, panics in async handlers silently drop the connection and the edge proxy returns a generic 503. Now panics are caught, logged, and returned as 500 with the panic message. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address second-round review — transactional delete, overflow, error logging - C1: Wrap PostgreSQL delete_user() in a transaction so partial cleanup can't leave users in a half-deleted state - M2: Add job_events to delete cleanup (both backends) — FK to agent_jobs without CASCADE would cause FK violation - H1/M4: Cap expires_in_days to 36500 before i64 cast (tokens + secrets) - H2: Validate target user exists before creating admin token to prevent orphan tokens on libSQL - H3: Log DB errors in DbAuthenticator::authenticate() instead of silently swallowing them as 401 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: revert to rustls with webpki-roots fallback for PostgreSQL TLS native-tls/OpenSSL caused silent crashes (segfaults in C code) during DB writes on Railway containers. Switch back to rustls but add webpki-roots as a fallback when system certs are missing, which was the original TLS handshake failure on slim container images. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore: update Cargo.lock for rustls + webpki-roots Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * debug: add /api/debug/db-write endpoint to diagnose user insert failure Temporary diagnostic endpoint that tests DB INSERT to users table with full error logging. No auth required. Will be removed after debugging. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * perf: use cargo-chef in Dockerfile for dependency caching Splits the build into planner/deps/builder stages. Dependencies are only recompiled when Cargo.toml or Cargo.lock change. Source-only changes skip straight to the final build stage. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * debug: add tracing to users_create_handler Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: guard created_by FK in user creation handler The auth identity user_id (from owner_id scope) may not match any user row in the DB, causing a FK violation on the created_by column. Check that the referenced user exists before setting created_by. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: collapse GATEWAY_USER_ID into IRONCLAW_OWNER_ID Remove the separate GATEWAY_USER_ID config. The gateway now uses IRONCLAW_OWNER_ID (config.owner_id) directly for auth identity, bootstrap user creation, and workspace scoping. Previously, with_owner_scope() rebinds the auth identity to owner_id while keeping default_sender_id as the gateway user_id. This caused a FK constraint violation when creating users because the auth identity ("default") didn't match any user in the DB ("nearai"). Changes: - Remove GATEWAY_USER_ID env var and gateway_user_id from settings - Remove user_id field from GatewayConfig - Add owner_id parameter to GatewayChannel::new() - Remove with_owner_scope() method - Remove default_sender_id from GatewayState - Remove sender override logic in chat/approval handlers - Remove debug endpoint and tracing from prior debugging - Update all tests and E2E fixtures Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: hide Users tab for non-admins, remove auth hint text - Fetch /api/profile after login and hide the Users settings tab when the user's role is not admin - Remove the "Enter the GATEWAY_AUTH_TOKEN" hint from the login page since tokens are now managed via the admin panel, not .env files Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review feedback (auth 503, token expiry, CORS PATCH) - DB auth errors now return 503 instead of 401 so outages are distinguishable from invalid tokens (serrrfirat H3) - Cap expires_in_days to 36500 before i64 cast to prevent negative duration from u64 overflow (serrrfirat H1) - Add PATCH to CORS allowed methods for profile/user update endpoints (Copilot) - Stop leaking panic details in CatchPanicLayer response body Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: harden multi-tenant isolation — review fixes from #1614 - Add conversation ownership checks in TenantScope: add_conversation_message, touch_conversation, list_conversation_messages (+ paginated), update_conversation_metadata_field, get_conversation_metadata now return NotFound for conversations not owned by the tenant (cross-tenant data leak) - Fix multi-user heartbeat: clear notify_user_id per runner so notifications persist to the correct user, not the shared config target - Move hygiene tasks into bounded JoinSet instead of unbounded tokio::spawn - Revert send_notification to private visibility (only used within module) - Use effective_model_name() for cost attribution in dispatcher so providers that ignore per-request model overrides report the actual model used - Fix inject_model_override doc comment; add 3 unit tests - Fix heartbeat doc comment ("routines" not "active routines") Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: add Jobs, Cost, Last Active columns to admin Users table Add UserSummaryStats struct and user_summary_stats() batch query to the UserStore trait (both PostgreSQL and libSQL backends). The admin users list endpoint now fetches per-user aggregates (job count, total LLM spend, most recent activity) in a single query and includes them inline in the response. The frontend Users table displays three new columns. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments and CI formatting failures CI fixes: - cargo fmt fixes in cli/mod.rs and db/tls.rs Security/correctness (from Copilot + serrrfirat + pranavraja99 reviews): - Token create: reject expires_in_days > 36500 with 400 instead of silent clamp - Token create: return 404 when admin targets non-existent user - User create: map duplicate email constraint violations to 409 Conflict - User create: remove unnecessary DB roundtrip for created_by (use AdminUser directly) - DB auth: log warn on DB lookup failures instead of silently swallowing errors - libSQL: add FK constraints on users.created_by and api_tokens.user_id Config fixes: - agent.multi_tenant: resolve from AGENT_MULTI_TENANT env var instead of hardcoding false - heartbeat.multi_tenant: fix doc comment to match actual env-var-based behavior UI fix: - showTokenBanner: pass correct title ("Token created!" vs "User created!") Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address remaining review comments (round 2) - Secrets handlers: normalize name to lowercase before store operations, validate target user_id exists (returns 404 if not found) - libSQL: propagate cost parsing errors instead of unwrap_or_default() in both user_usage_stats and user_summary_stats - users_list_handler: propagate user_summary_stats DB errors (was silently swallowed with unwrap_or_default) - loadUsers: distinguish 401/403 (admin required) from other errors - Docs: fix users.id type (TEXT not UUID), remove "invitation flow" from V14 migration comment Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: i18n for Users tab, atomic user+token creation, transactional delete_user i18n: - Add 31 translation keys for all Users tab strings (en + zh-CN) - Wire data-i18n attributes on HTML elements (headings, buttons, inputs, table headers, empty state) - Replace all hard-coded strings in app.js with I18n.t() calls Atomic user+token creation: - Add create_user_with_token() to UserStore trait - PostgreSQL: wraps both INSERTs in conn.transaction() with auto-rollback - libSQL: wraps in explicit BEGIN/COMMIT with ROLLBACK on error - Handler uses single atomic call instead of two separate operations Transactional delete_user for libSQL: - Wrap multi-table DELETE cascade in BEGIN/COMMIT transaction - ROLLBACK on any error to prevent partial cleanup / inconsistent state - Matches the PostgreSQL implementation which already used transactions Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: revert V14 migration to match deployed checksum [skip-regression-check] Refinery checksums applied migrations — editing V14__users.sql after it was already applied causes deployment failures. Revert the cosmetic comment changes (added in df40b22f) to restore the original checksum. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: bootstrap onboarding flow for multi-tenant users The bootstrap greeting and workspace seeding only ran for the owner workspace at startup, so new users created via the admin API never received the welcome message or identity files (BOOTSTRAP.md, SOUL.md, AGENTS.md, USER.md, etc.). Three fixes: - tenant_ctx(): seed per-user workspace on first creation via seed_if_empty(), which writes identity files and sets bootstrap_pending when the workspace is truly fresh - handle_message(): check take_bootstrap_pending() on the tenant workspace (not the owner workspace) and persist the greeting to the user's own assistant conversation + broadcast via SSE - WorkspacePool: seed new per-user workspaces in the web gateway so memory tools also see identity files immediately The existing single-user bootstrap in Agent::run() is preserved for non-multi-tenant deployments. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address remaining PR review comments (round 3) - Docs: fix metadata description from "merge patch" to "full replacement" - Secrets: reject expires_in_days > 36500 with 400 (was silently clamped) - libSQL: CAST(SUM(cost) AS TEXT) in user_usage_stats and user_summary_stats to prevent SQLite numeric coercion from crashing get_text() — this was the root cause of the Copilot "SUM returns numeric type" comments - Add 3 regression tests: user_summary_stats (empty + with data) and user_usage_stats (multi-model aggregation) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: add role change support for users (admin/member toggle) - Add update_user_role() to UserStore trait + both backends (PostgreSQL and libSQL) - Extend PATCH /api/admin/users/{id} to accept optional "role" field with validation (must be "admin" or "member") - Add "Make Admin" / "Make Member" toggle button in Users table actions - Add i18n keys for role change (en + zh-CN) - Update API docs to document the role field on PATCH - Fix test helpers to use fmt_ts() for timestamps (was using SQLite datetime('now') which produces incompatible format for string comparison) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: show live LLM spend in Users table instead of only DB-recorded costs [skip-regression-check] Chat turns record LLM cost in CostGuard (in-memory) but don't create agent_jobs/llm_calls DB rows — those are only written for background jobs. The Users table was querying only from DB, so it showed $0.00 for users who only chatted. Now supplements DB stats with CostGuard.daily_spend_for_user() — the same source displayed in the status bar token counter. Shows whichever is larger (DB historical total vs live daily spend). Also falls back to last_login_at for "Last Active" when no DB job activity exists. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: persist chat LLM calls to DB and fix usage stats query Two root causes for zero usage stats: 1. ChatDelegate only recorded LLM costs to CostGuard (in-memory) — never to the llm_calls DB table. Added DB persistence via TenantScope.record_llm_call() after each chat LLM call, with job_id=NULL and conversation_id=thread_id. 2. user_summary_stats query only joined agent_jobs→llm_calls, missing chat calls (which have job_id=NULL). Redesigned query to start from llm_calls and resolve user_id via COALESCE(agent_jobs.user_id, conversations.user_id) — covers both job and chat LLM calls. Both PostgreSQL and libSQL queries updated. TenantScope gets record_llm_call() method. Tests updated for new query semantics. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments — input validation, cost semantics, panic safety [skip-regression-check] - Validate display_name: trim whitespace, reject empty strings (create + update) - Validate metadata: must be a JSON object, return 400 if not (admin + profile) - secrets_list_handler: verify target user_id exists before listing - Cost display: use DB total directly (chat calls now persist to DB), remove confusing max(db,live) CostGuard fallback - CatchPanicLayer: truncate panic payload to 200 chars in log to limit potential sensitive data exposure Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot round 5 — docs, secrets consistency, token name, provider field [skip-regression-check] - Docs: users.id note updated to "typically UUID v4 strings (bootstrap admin may use a custom ID)" - secrets_list_handler: return 503 when DB store is None (was falling through to list secrets without user validation) - tokens_create: trim + reject empty token name (matching display_name pattern) - LlmCallRecord.provider: use llm_backend ("nearai","openai") instead of model_name() which returns the model identifier - user_summary_stats zero-LLM users: acceptable — handler already falls back to 0 cost and last_login_at for missing entries Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: DB auth returns 503 on outage, scheduler counts only blocking jobs From serrrfirat review: - DB auth: return Err(()) on database errors so middleware returns 503 instead of silently returning Ok(None) → 401 (auth miss) - Scheduler: add parallel_blocking_count_for() that uses is_parallel_blocking() (Pending/InProgress/Stuck) instead of is_active() for per-user concurrency — Completed/Submitted jobs no longer count against MAX_JOBS_PER_USER From Copilot: - CLAUDE.md: fix secrets route paths from {id} to {user_id} - token_hash: use .as_slice() instead of .to_vec() to avoid heap allocation on every token auth/creation call Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: immediate auth cache invalidation on security-critical actions (zmanian review #6) Add DbAuthenticator::invalidate_user() that evicts all cached entries for a user. Called after: - Suspend user (immediate lockout, was 60s delay) - Activate user (immediate access restoration) - Role change (admin↔member takes effect immediately) - Token revocation (revoked token can't be reused from cache) The DbAuthenticator is shared (via Clone, which Arc-clones the cache) between the auth middleware and GatewayState, so handlers can evict entries from the same cache the middleware reads. Also from zmanian's review: - Items 1-5, 7-11 were already resolved in prior commits - Item 12 (String→enum for status/role) is deferred as a broader refactor Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: last-admin protection, usage stats for chat calls, UTF-8 safe panic truncation Last-admin protection: - Suspend, delete, and role-demotion of the last active admin now return 409 Conflict instead of succeeding and locking out the admin API - Helper is_last_admin() checks active admin count before destructive ops Usage stats: - user_usage_stats() now includes chat LLM calls (job_id=NULL) by joining via conversations.user_id, matching user_summary_stats() - Both PostgreSQL and libSQL queries updated Panic handler: - Use floor_char_boundary(200) instead of byte-index [..200] to prevent panic on multi-byte UTF-8 characters in panic messages Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: workspace seed race, bootstrap atomicity, email trim, secrets upsert response [skip-regression-check] - WorkspacePool: await seed_if_empty() synchronously after inserting into cache (drop lock first to avoid blocking), so callers see identity files immediately instead of racing a background task - Bootstrap admin: use create_user_with_token() for atomic user+token creation, matching the admin create endpoint - Email: trim whitespace, treat empty as None to prevent " " being stored and breaking uniqueness - Secrets PUT: report "updated" vs "created" based on prior existence - Last token_hash.to_vec() → .as_slice() in authenticate_token Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: disable unscoped webhook endpoint in multi-tenant mode [skip-regression-check] The original /api/webhooks/{path} endpoint looks up routines across all users. In multi-tenant mode, anyone who knows the webhook path + secret could trigger another user's routine. Now returns 410 Gone with a message pointing to the scoped endpoint /api/webhooks/u/{user_id}/{path}. Detection uses state.db_auth.is_some() — present only when DB-backed auth is enabled (multi-tenant). Single-user deployments are unaffected. From: standardtoaster review comment Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: webhook multi-tenant check, secrets error propagation, stale doc comment [skip-regression-check] - Webhook: use workspace_pool.is_some() instead of db_auth.is_some() for multi-tenant detection — db_auth is set for any DB deployment, workspace_pool is only set when has_any_users() was true at startup - Secrets: propagate exists() errors instead of unwrap_or(false) so backend outages surface as 500 rather than incorrect "created" status - Config: fix stale workspace_read_scopes comment referencing user_id Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-28 00:19:17 -07:00
4 people	2f4eb08613	fix: sanitize tool error results before llm injection (#1639) ... * fix: sanitize tool error results before llm injection Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <[email protected]> * fix: wrap preflight tool rejection errors for llm safety Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <[email protected]> * style: apply rustfmt to error-path regressions Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <[email protected]> * fix: preserve wrapped tool errors in history replay * fix: address review findings on PR #1639 - Simplify legacy error handling in rebuild_chat_messages_from_db: remove redundant "Error: " prefix since legacy errors already contain descriptive text (e.g. "Tool 'http' failed: timeout"). Both wrapped (new) and plain (legacy) errors now pass through as-is. - Update existing test assertion to match simplified format. - Restore error-path doc line on process_tool_result. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: satisfy clippy on builder tool safety helper --------- Co-authored-by: Sisyphus <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-27 10:49:28 +03:00
rajulbhatnagarandGitHub	ed4d92932a	fix(agent): discard truncated tool calls when finish_reason == Length (#1631) (#1632)	2026-03-26 10:02:41 +03:00
3 people	4c043bf057	feat: complete multi-tenant isolation — phases 2–4 (#1614) ... * feat: complete multi-tenant isolation — per-user budgets, model selection, heartbeat cycling Finishes the remaining isolation work from phases 2–4 of #59: Phase 2 (DB scoping): Fix /status and /list commands to use _for_user DB variants instead of global queries that leaked cross-user job data. Phase 3 (Runtime isolation): Per-user workspace in routine engine's spawn_fire so lightweight routines run in the correct user context. Per-user daily cost tracking in CostGuard with configurable budget via MAX_COST_PER_USER_PER_DAY_CENTS. Multi-user heartbeat that cycles through all users with routines, auto-detected from GATEWAY_USER_TOKENS. Phase 4 (Provider/tools): Per-user model selection via preferred_model setting — looked up from SettingsStore on first iteration, threaded through ReasoningContext.model_override to CompletionRequest. Works with providers that support per-request model overrides (NearAI). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: use selected_model setting key to match /model command persistence The dispatcher was reading "preferred_model" but the /model command (merged from staging) persists to "selected_model". Since set_setting is already per-user scoped, using the same key makes /model work as the per-user model override in multi-tenant mode. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: heartbeat hygiene, /model multi-tenant guard, RigAdapter model override Three follow-up fixes for multi-tenant isolation: 1. Multi-user heartbeat now runs memory hygiene per user before each heartbeat check, matching single-user heartbeat behavior. 2. /model command in multi-tenant mode only persists to per-user settings (selected_model) without calling set_model() on the shared LlmProvider. The per-request model_override in the dispatcher reads from the same setting. Added multi_tenant flag to AgentConfig (auto-detected from GATEWAY_USER_TOKENS). 3. RigAdapter now supports per-request model overrides by injecting the model name into rig-core's additional_params. OpenAI/Anthropic/Ollama API servers use last-key-wins for duplicate JSON keys, so the override takes effect via serde's flatten serialization order. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — cost model attribution, heartbeat concurrency, pruning Fixes from review comments on #1614: - Cost tracking now uses the override model name (not active_model_name) when a per-user model override is active, for accurate attribution. - Multi-user heartbeat runs per-user checks concurrently via JoinSet instead of sequentially, preventing one slow user from blocking others. - Per-user failure counts tracked independently; users exceeding max_failures are skipped (matching single-user semantics). - per_user_daily_cost HashMap pruned on day rollover to prevent unbounded growth in long-lived deployments. - Doc comment fixed: says "routines" not "active routines". Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: /status ownership, model persistence scoping, heartbeat robustness Addresses second round of PR review on #1614: - /status <job_id> DB path now validates job.user_id == requesting user before returning data (was missing ownership check, security fix). - persist_selected_model takes user_id param instead of owner_id, and skips .env/TOML writes in multi-tenant mode (these are shared global files). handle_system_command now receives user_id from caller. - JoinSet collection handles Err(JoinError) explicitly instead of silently dropping panicked tasks. - Notification forwarder extracts owner_id from response metadata in multi-tenant mode for per-user routing instead of broadcasting to the agent owner. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: cost pricing, fire_manual workspace, heartbeat concurrency cap Round 3 review fixes: - Cost tracking passes None for cost_per_token when model override is active, letting CostGuard look up pricing by model name instead of using the default provider's rates (serrrfirat). - fire_manual() now uses per-user workspace, matching spawn_fire() pattern (serrrfirat). - Removed MULTI_TENANT env var — multi-tenant mode is auto-detected solely from GATEWAY_USER_TOKENS presence (serrrfirat + Copilot). - Multi-user heartbeat capped at 8 concurrent tasks to avoid flooding the LLM provider (serrrfirat + Copilot). - Fixed inject_model_override doc comment accuracy (Copilot). - Added comment explaining multi-tenant notification routing priority (Copilot). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: user-scoped webhook endpoint for multi-tenant isolation Adds POST /api/webhooks/u/{user_id}/{path} — a user-scoped webhook endpoint that filters the routine lookup by user_id, preventing cross-user webhook triggering when paths collide. The existing /api/webhooks/{path} endpoint remains unchanged for backward compatibility in single-user deployments. Changes: - get_webhook_routine_by_path gains user_id: Option<&str> param - Both postgres and libsql implementations add AND user_id = ? filter when user_id is provided - New webhook_trigger_user_scoped_handler extracts (user_id, path) from URL and passes to shared fire_webhook_inner logic - Route registered on public router (webhooks are called by external services that can't send bearer tokens) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: add TenantCtx for compile-time tenant isolation Implements zmanian's architectural proposal from #1614 review: two-tier scoped database access (TenantScope/AdminScope) so handler code cannot accidentally bypass tenant scoping. TenantScope (default): wraps user_id + Arc<dyn Database>, auto-binds user_id on every operation. ID-based lookups return None for cross- tenant resources. No escape hatch — forgetting to scope is a compile error. AdminScope (explicit opt-in): cross-tenant access for system-level components (heartbeat, routine engine, self-repair, scheduler, worker). TenantCtx bundles TenantScope + workspace + cost guard + per-user rate limiting. Constructed once per request in handle_message, threaded through all command handlers and ChatDelegate. Key changes: - New src/tenant.rs (~920 lines): TenantScope, AdminScope, TenantCtx, TenantRateState, TenantRateRegistry - All command handlers: user_id: &str → ctx: &TenantCtx - ChatDelegate: cost check/record/settings via self.tenant - System components: store field changed to AdminScope - Config: TENANT_MAX_LLM_CONCURRENT, TENANT_MAX_JOBS_CONCURRENT env vars - Fixes bug: /status <job_id> cross-tenant leak (now auto-filtered) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-25 17:24:48 -07:00
Henry ParkandGitHub	86d1143064	Fix libsql prompt scope regressions (#1651)	2026-03-25 14:36:53 -07:00
4 people	41ed0a0f98	feat(agent): thread per-tool reasoning through provider, session, and all surfaces (#1513) ... * feat(agent): thread per-tool reasoning from LLM through to REPL, HTTP, SSE, and DB Add end-to-end agent reasoning summaries so users can see *why* the agent chose specific tools, not just what it did. - Add `reasoning: Option<String>` to `ToolCall` (all providers) - Populate from LLM response content in `Reasoning::respond_with_tools` and `select_tools`, with per-tool override when providers supply it - Extend `Turn` with `narrative` and `TurnToolCall` with `rationale` + `tool_call_id` for identity-based result matching - Persist reasoning in DB via existing tool_calls JSON (no migration) - Add `StatusUpdate::ReasoningUpdate` and `SseEvent::ReasoningUpdate` + `SseEvent::JobReasoning` for real-time streaming - Emit reasoning events in both chat dispatcher and worker job path - Add `/reasoning [N|all]` command for inspecting turn reasoning - Surface `narrative` and `rationale` in HTTP `/api/chat/history` Based on the design from #361 and #456, reconstructed cleanly with Option<String> to minimize blast radius (vs mandatory String that broke compilation in #456). Closes #456 Co-Authored-By: panosAthDBX <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review feedback from Gemini and Copilot - Fix `_ => Ok(None)` in agent_loop.rs to avoid accidental shutdown - Fix fallback in record_tool_result_for/record_tool_error_for to use first pending call instead of last_mut (parallel execution safety) - Include per-tool decisions in WASM channel reasoning messages - Apply truncate_at_tool_tags + clean_response to shared_reasoning in select_tools (parity with respond_with_tools) - Persist turn-level narrative to DB in tool_calls JSON wrapper - Parse both old (array) and new (object) tool_calls formats in build_turns_from_db_messages for backward compatibility - Populate reasoning from action.reasoning in execute_plan ToolCalls [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address second round of review comments + merge fixes - Add reasoning: None to new github_copilot.rs ToolCall sites (from staging merge) - Run cargo fmt on 4 files with formatting diffs - Truncate narrative to 1000 chars before DB persistence - Clone turn data and drop session lock in /reasoning command - Extract ToolDecisionDto::from_json_array shared helper (deduplicate worker/job.rs and orchestrator/api.rs) - Add unit tests for wrapped tool_calls JSON format with narrative [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address third round of review comments (Copilot + serrrfirat) - Reword ToolCall.reasoning docstring to reflect provider-supplied or fallback contract - Sanitize narrative through SafetyLayer before storage/emission - Clean per-tool reasoning via truncate_at_tool_tags + clean_response in select_tools (parity with shared reasoning) - Convert 4 approval-path recording sites in thread_ops.rs to identity-based record_tool_result_for/record_tool_error_for - Preserve tool_call_id and reasoning through restore_from_messages - Fix has_result/has_error to reject JSON null values - Truncate tool_call_id to 128 chars before DB persistence - Add 4 unit tests for record_tool_result_for/error_for edge cases Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian review — sanitize JobDelegate reasoning + warn on dropped results - Sanitize narrative and per-tool rationale through SafetyLayer in JobDelegate reasoning events (parity with ChatDelegate) - Add tracing::warn when record_tool_result_for/error_for drops a result because no matching or pending tool call exists - Add 3 unit tests for reasoning normalization (thinking tags, tool tags, empty-after-cleaning) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address 4 remaining unreplied review comments - Clean per-tool reasoning in respond_with_tools via truncate_at_tool_tags + clean_response (parity with select_tools) - Handle wrapped JSON format in rebuild_chat_messages_from_db so cold hydration works after persist_tool_calls format change - Update persist_tool_calls doc comment to describe new JSON shape - Sanitize per-tool rationale through SafetyLayer in ChatDelegate before emission and storage (parity with JobDelegate) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian review round 2 - Add tracing::debug on fallback-to-pending path in record_tool_result_for and record_tool_error_for (item 1) - Add comment explaining why /reasoning is special-cased in agent_loop.rs (item 4) - Items 2 (narrative persistence), 3 (rationale sanitization), and 5 (catch-all fix) were already addressed in prior commits Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: panosAthDBX <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-25 08:35:41 -07:00
3 people	5847479fd8	fix(agent): persist /model selection to .env, TOML, and DB (#1581) ... * fix(agent): persist /model selection to .env, TOML, and DB The /model command only wrote selected_model to the DB and config.toml, but env vars from ~/.ironclaw/.env (e.g. NEARAI_MODEL) have the highest priority in LlmConfig::resolve_model(). The .env value was never updated, so it always shadowed the new model on restart. Now persist_selected_model updates all three persistence layers: 1. The backend-specific model env var in ~/.ironclaw/.env (only if the var already exists, to avoid injecting new vars) 2. The config.toml file (created if absent, since TOML > DB priority) 3. The DB settings table (for completeness) Also adds diagnostic logging when the DB store is unavailable. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(agent): address PR review — backend from deps, exact .env match Review feedback: - Use resolved llm_backend from AgentDeps instead of re-reading from disk/env (fixes DB-only backend detection, eliminates redundant I/O) - Match .env var with exact "KEY=" prefix and skip commented lines (prevents false matches on NEARAI_MODEL_VERSION etc.) - TOML is now loaded once (no double-read for backend + model update) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-23 22:24:26 -07:00
3 people	fa51b9f52d	fix: post-merge review sweep — 8 fixes across security, perf, and correctness (#1550) ... * fix: post-merge review sweep — 8 fixes across security, perf, and correctness 1. Fix code fence detection in extract_suggestions() (issue #1180) - rfind("```") couldn't handle odd fence counts (unclosed blocks) - Now counts all fence positions and checks parity 2. Cache routine parameters_schema() with OnceLock (issue #1361) - routine_create_parameters_schema() and event_emit_parameters_schema() were regenerating JSON on every LLM call 3. Replace O(n) LRU eviction with lru crate (issue #1430) - Embedding cache now uses lru::LruCache for O(1) eviction - Removes manual HashMap + last_accessed tracking 4. Fix WASM router secret_validated semantics (issue #1281) - Now reflects whether any auth (secret/Ed25519/HMAC) was performed - Previously only checked if a secret was configured 5. Sanitize channel/user in routine prompt interpolation (issue #1364) - Defense-in-depth: strip newlines, replace backticks, truncate to 128 chars before injecting into LLM prompt 6. Remove duplicate 401 retry in github_copilot.rs (PR #1512 review) - Internal retry conflicted with outer RetryProvider causing nested retries; now invalidates token and lets RetryProvider handle retry 7. Fix token error classification in github_copilot.rs (PR #1512 review) - AccessDenied/Expired errors now map to AuthFailed (non-retryable) - Transient errors remain RequestFailed (retryable) 8. Fix parse_extra_headers() hardcoded env var name (PR #1512 review) - Error messages now report the actual env var being parsed instead of always saying LLM_EXTRA_HEADERS Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review comments and fix formatting - sanitize_prompt_field: single-pass with map() instead of collect+replace - embed(): re-check cache under lock before cloning (thundering herd) - embed_batch(): limit caching to cache capacity, skip overflow entries - router: thread did_authenticate bool instead of re-calling async methods - github_copilot 401: use generic error message, avoid leaking response body - cargo fmt: fix two formatting violations caught by CI Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore: trigger CI re-run with updated refs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-23 14:50:15 -07:00
5 people	7034e910c4	fix: generate Mistral-compatible 9-char alphanumeric tool call IDs (#1242) ... * fix: generate Mistral-compatible 9-char alphanumeric tool call IDs Mistral's API requires tool call IDs to match [a-zA-Z0-9]{9} exactly. Previously, IDs like 'turn1_0', 'recovered_0', 'call_<uuid>', and 'generated_tool_call_N' were generated, which Mistral rejects with HTTP 400. Add generate_tool_call_id() that produces deterministic 9-char base-36 IDs from two seed values, and use it at all tool call ID generation sites. Fixes #1241 * Update src/llm/provider.rs Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <[email protected]> * fix: address review feedback on Mistral tool-call ID generation - Remove .unwrap() in generate_tool_call_id (provider.rs) per zero-tolerance policy - Remove .expect() in normalized_tool_call_id (rig_adapter.rs), use direct array indexing - Replace magic constant 99 with named RECOVERED_TOOL_CALL_SEED in reasoning.rs - Add tests for normalized_tool_call_id: passthrough, hashing, empty/whitespace, determinism - Add comment explaining intentional use of turn_idx vs turn.turn_number in session.rs - Fix duplicate `mod tests` block in provider.rs (pre-existing compile error) - Update stale test assertions expecting old `generated_tool_call_` prefix format [skip-regression-check] * Apply suggestions from code review Co-authored-by: Copilot Autofix powered by AI <[email protected]> --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <[email protected]> Co-authored-by: Illia Polosukhin <[email protected]>	2026-03-22 18:07:03 -07:00
5 people	3e73dbe615	perf(tools): remove unconditional params clone in shared execution (fix #893) (#926) ... * perf(tools): remove unconditional params clone in shared execution * Update src/tools/execute.rs Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * chore(fmt): apply rustfmt in worker container tool execution * fix(tools): restore owned param call sites * fix(tools): pass normalized_params to tool.execute() instead of raw params The ownership refactor accidentally passed the un-coerced `params` to `tool.execute()` while validation ran against the coerced `normalized_params`. This meant tools received un-normalized input (e.g. stringified JSON arrays instead of actual arrays). Since `normalized_params` is owned and unused after the execute call, passing it directly achieves the original zero-clone goal without breaking parameter coercion. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(tools): update empty-tool-name test for owned params signature Adapts the test_execute_empty_tool_name_returns_not_found test (added on staging) to pass owned Value instead of &Value, matching the new execute_tool_with_safety signature. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: [email protected] <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-22 17:48:02 -07:00
3 people	a09c023642	feat(ux): complete UX overhaul — design system, onboarding, web polish (#1277) ... * feat(ux): complete UX overhaul — design system, boot screen, onboarding, web polish Shared design system: CSS custom properties for spacing, typography, transitions, and color tokens used across web UI and boot screen. Boot screen: compact feature-tags line showing enabled subsystems (db, tools, routines, heartbeat, skills, sandbox, embeddings) at a glance. Downgrade startup info logs (libSQL, webhook, workspace seed) to debug level since the boot screen now covers this. Onboarding wizard: model picker with live API fetch, provider-aware auth flow, improved error recovery and progress display. Web UI: ARIA attributes, welcome card, streaming debounce, connection status banner, skeleton loaders, send cooldown. CLI: doctor command enhancements, status command cleanup, REPL banner consolidation, shared fmt module. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(ux): Apple-level design refinements — spring physics, glass morphism, chat polish Merge staging theme support (dark/light/system toggle) and layer UX polish on top: spring-physics motion, glass morphism depth, chat experience improvements, and responsive mobile refinements. Design system: - Restore and extend design token system (spacing, typography, timing, easing) with legacy aliases for theme compatibility - Add shadow tiers, accent glow, glass morphism, spring easing tokens - Tokens defined in both dark (:root) and light ([data-theme="light"]) Micro-interactions (Phase 2): - Spring-overshoot message entry animation (slideUp) - Spring-scale button press on all interactive buttons - Tab crossfade animation, tool card smooth accordion (max-height) - Modal scale(0.95) + blur(8px) entry, toast spring slide - Sidebar width crossfade, card hover lift Visual depth (Phase 3): - Tab bar glass morphism + surface highlight + sliding indicator - Active tab accent background pill - Assistant message accent left border, user message bubble tail - Floating input area (rounded + shadow + margin) Chat polish (Phase 4): - Smooth streaming cursor (cursorPulse), message hover timestamps - Time separators (Today/Yesterday/date) - Textarea smooth auto-expand, send button glow Settings & forms (Phase 5): - iOS-style toggle switches for boolean settings - Input focus glow, save feedback spring animation - Welcome card with gradient background + proper spacing - Sticky settings group headers with glass backdrop Accessibility & mobile (Phase 6): - Animated focus ring, prefers-reduced-motion global kill-switch - Touch target audit (44px min), mobile bottom-sheet modals - Mobile bottom tab bar, toast redesign (icon + border + countdown) - Thread hover translateX, badge in_progress pulse Bug fixes: - Gateway/TEE popover z-index (tab-bar z-index: 200, popovers 500) - Connection lost banner as fixed top bar instead of flex child - Sidebar collapse keeps toggle + new thread buttons visible - Downgrade noisy startup logs (db, webhook, vector) to debug - Remove green dot pulse animation on connected status - Deduplicate confirm-modal in HTML, add tab-indicator div Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(web): mobile layout improvements — sidebar toggle, settings drill-down, tab bar polish - Fix mobile sidebar toggle: use expanded-mobile class instead of collapsed, add backdrop overlay, auto-close on thread select, outside-click dismiss - Settings: replace cramped horizontal tabs with drill-down navigation (category list → detail view → back button) - Bottom tab bar: add glass morphism, hide theme toggle, flip tab indicator to top edge - Keep thread toggle button visible in collapsed 36px sidebar strip Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(repl): interactive approval selector and transient status lines - Replace ASCII-art approval box with clean horizontal rule card - Add inquire-based interactive selector for tool approvals (↑↓ + Enter) - Selector runs directly from send_status via spawn_blocking, with stdin_locked flag to prevent readline from competing for stdin - Transient thinking/tool-started lines: each replaces the previous, all erased before final output (no clutter left in scrollback) - Esc in selector sends denial so agent never gets stuck Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: widen TurnCost token fields to u64 and remove unused variable - Change input_tokens/output_tokens from u32 to u64 in StatusUpdate::TurnCost, SseEvent::TurnCost, and the thread_ops emit site to avoid truncation on large conversations - Remove unused _routine_engine_for_loop binding in agent_loop.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore: reduce startup log noise — demote info to debug Demote routine startup messages (builder, WASM tools, tunnel, WASM channels) from info to debug so the default log output stays clean. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(web): allow CDN scripts in CSP connect-src directive Add cdn.jsdelivr.net and cdnjs.cloudflare.com to connect-src so the browser can fetch marked.js and DOMPurify without CSP violations. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fix cargo fmt in repl.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(web): gate turn_cost SSE handler on current thread Prevents cost badge from attaching to the wrong message when switching threads or receiving events from background threads. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * ci: retrigger CI * fix: add missing extension_manager to webhook EngineContext The webhook trigger path added in #736 was missing the extension_manager field introduced by #1453. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore: ignore RUSTSEC-2026-0049 rustls-webpki CRL advisory Low impact — requires compromised CA to exploit. Tracked for upstream rustls-webpki upgrade. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(routines): use fields.join for cron normalization Use split_whitespace fields instead of re-trimming the original string to avoid preserving extra internal whitespace in cron expressions. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(repl): Apple-style approval card — clean vertical flow - Drop verbose tool description (the command IS the decision surface) - Unified vertical pipe layout: ◆ header → │ params → │ selector - Selector options show keyboard shortcuts inline: Approve (y) - Compact help message, answered state uses └ to close the flow - No horizontal rules, no blank-line padding — just breathing room Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor(repl): replace inquire with crossterm for approval selector Drop the inquire dependency (which pulled in crossterm 0.25, duplicating the existing 0.28). The 3-option approval selector is now built directly with crossterm raw mode — same UX, zero new dependencies. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore(deps): upgrade crossterm 0.28 → 0.29, eliminate duplication termimad (via crokey) uses crossterm 0.29. Upgrading our direct dependency from 0.28 to 0.29 collapses to a single crossterm version in the dependency tree. Also migrated termimad::crossterm:: references to the direct crossterm import. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments — box_top off-by-one, smart_truncate overflow, mobile theme toggle - Fix box_top() fill calculation: was off-by-one, producing boxes 1 char too wide (fmt.rs) - Fix smart_truncate(): account for "..." in the budget so output never exceeds max_chars (repl.rs) - Move theme toggle to settings sidebar on mobile instead of display:none, so mobile users can still switch themes (style.css, index.html, app.js) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt repl.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review — retry duplication, CSP connect-src, deny color - Remove failed message before retry to prevent duplicate user messages - Revert connect-src to 'self' — CDN hosts only need script-src - Use red for Deny confirmation in REPL approval selector Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-21 23:50:49 -07:00
4 people	b58b421535	feat(shell): add Low/Medium/High risk levels for graduated command approval (closes #172) (#368) ... * feat(shell): add Low/Medium/High risk levels for graduated approval (#172) - Add `RiskLevel` enum (Low/Medium/High, Ord-comparable) to `tool.rs` and re-export from `tools/mod.rs` - Add `risk_level_for(&params) -> RiskLevel` to the `Tool` trait (default: Low); override on `ShellTool` via `classify_command_risk` - Add `classify_command_risk(command: &str) -> RiskLevel` to `shell.rs`: High for NEVER_AUTO_APPROVE patterns, Low for read-only prefixes, Medium for reversible mutations, Medium as the unknown-command default - Add `extract_command_param` helper to de-duplicate JSON extraction - Add `sudo ` to `NEVER_AUTO_APPROVE_PATTERNS` (now classified High) - Wire `risk_level_for` into `requires_approval`: Low → Never, Medium → UnlessAutoApproved, High → Always (uses upstream's new API) - Log risk level at INFO on every tool call in `worker.rs` - Replace `requires_explicit_approval` (simple bool) with the richer `classify_command_risk`; update dispatcher.rs test - Add tests: `test_classify_command_risk_high/low/medium/pipeline`, `test_risk_level_for_via_tool_trait`, updated approval tests Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * style: apply cargo fmt to shell.rs and dispatcher.rs Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): fix pipeline risk aggregation and word-boundary matching Address reviewer feedback: - `classify_command_risk` now iterates ALL pipeline segments and takes the maximum risk, so `echo hello | cargo build` → Medium instead of the previous (wrong) Low - Replace `starts_with` with `matches_command_pattern`: single-word patterns use exact first-token comparison so `lsblk` no longer matches `ls`, `makeself` no longer matches `make`, etc.; multi-word patterns (e.g. `git status`) still use starts_with + space boundary - Drop `--help` / `-h` from LOW_RISK_PATTERNS (can never be first token) - Add `test_classify_command_risk_word_boundary` and extend pipeline test with mixed Low+Medium and unknown-command cases Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): move sed/awk/find from Low to Medium risk `sed -i`, `awk -i inplace`, and `find -delete`/`find -exec rm` can all modify or delete files. Classifying these as Low (auto-approve) was unsafe. Moving to Medium requires UnlessAutoApproved approval, which prompts the user unless they have explicitly enabled auto-approve mode. Fixes review feedback from zmanian on PR #368. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): update test to use classify_command_risk after requires_explicit_approval removal The rebase brought in upstream commits that removed requires_explicit_approval. Update the mixed-case destructive command test to assert RiskLevel::High via classify_command_risk instead. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): use word-boundary matching for High-risk patterns to prevent false positives The NEVER_AUTO_APPROVE_PATTERNS check used `contains()` on the full command string, causing false positives: `makeshutdownscript` matched `shutdown`, `nftables-config` matched `nft`, and `passwdqc-check` matched `passwd`. Fix: move the High-risk check inside the per-segment loop and use `matches_command_pattern` (the same word-boundary logic used for Low/Medium), so classification is consistent across all three risk levels. Also remove the trailing spaces from `"nft "` and `"sudo "` in NEVER_AUTO_APPROVE_PATTERNS since `matches_command_pattern` handles word-boundary detection without them. Adds three regression tests for the false-positive cases. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): address zmanian review — redirect safety + explicit git push pattern Two issues from zmanian's CHANGES_REQUESTED review on PR #368: 1. **Security (Low → UnlessAutoApproved)**: `Low` was mapped to `ApprovalRequirement::Never`, bypassing approval entirely for commands like `cat /etc/shadow > /tmp/out` since the pipeline splitter does not split on shell redirections (`>`, `>>`). Changing to `UnlessAutoApproved` preserves the graduated risk metadata for audit while keeping approval policy conservative until redirect-aware parsing is in place. 2. **Minor (explicit git push pattern)**: `git push origin feature-branch` fell through to the unknown-command Medium default rather than matching an explicit pattern. Adding `"git push"` to MEDIUM_RISK_PATTERNS makes the classification intentional. Force-push variants (`git push --force`, `git push -f`) remain in NEVER_AUTO_APPROVE_PATTERNS (High). Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * test(shell): add regression tests for redirect bypass and git push pattern fixes Two regression tests for the fixes in the previous commit: 1. `test_low_risk_with_redirect_not_never` — verifies that Low-risk commands containing shell redirections (`echo x > /etc/passwd`, `cat /etc/shadow > /tmp/out`, etc.) return `UnlessAutoApproved`, not `Never`. Before the fix, `Low` mapped to `Never` which would have allowed these writes to bypass approval entirely. 2. `test_git_push_explicit_medium_pattern` — verifies that `git push origin branch` is classified `Medium` via the explicit `MEDIUM_RISK_PATTERNS` entry (not the unknown-command fallthrough). Force variants (`--force`, `-f`) remain `High`. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * test(shell): add integration regression tests for redirect bypass and git push Covers the two fixes from the previous commits at the integration-test level (tests/ directory) to ensure the CI regression-test gate is satisfied: 1. `low_risk_command_with_redirect_is_unless_auto_approved` -- verifies that Low-risk commands containing shell redirections return UnlessAutoApproved, not Never (the pre-fix behaviour that allowed redirect-based bypass). 2. `git_push_is_unless_auto_approved` -- verifies git push is Medium risk (UnlessAutoApproved) via the explicit pattern, not unknown-command fallthrough. 3. `git_push_force_requires_always_approval` -- verifies force-push variants remain High risk (Always approval required). Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * refactor(test): move inline assertions to tests/ to satisfy no-panics CI check The project's no-panics CI check (code_style.yml) scans src/**/*.rs for assert_eq!/assert_ne!/.unwrap() in added lines. Moving classify_command_risk tests to tests/shell_risk_regression.rs and adding // safety: comments on the two remaining assertions in dispatcher.rs eliminates all false positives. - Remove test_classify_command_risk_* and related functions from shell.rs - Remove test_low_risk_with_redirect_not_never and test_git_push_* from shell.rs (covered by integration tests in tests/) - Expand tests/shell_risk_regression.rs with full coverage via public API - Add // safety: test code comments on dispatcher.rs assert lines Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(shell): address review findings — force-with-lease, test runners, Display - Add `git push --force-with-lease` to NEVER_AUTO_APPROVE_PATTERNS — the word-boundary matching in matches_command_pattern would not match it against the existing `git push --force` pattern (next char is `-`, not space), causing it to fall through to Medium instead of High. - Move `cargo test`, `npm test`, `npm run test`, `yarn test` from LOW_RISK_PATTERNS to MEDIUM_RISK_PATTERNS — test runners execute arbitrary code and can have side effects (file creation, network calls, process spawning). - Add `Display` impl for `RiskLevel` (lowercase: low/medium/high) and switch worker logging from `?risk` (Debug) to `%risk` (Display) for cleaner audit logs. - Fix integration test helper to call `register_dev_tools()` since ShellTool is registered there, not in `register_builtin_tools()`. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: [email protected] <[email protected]>	2026-03-21 22:05:18 -07:00
3 people	07c338f55d	fix(safety): escape tool output XML content and remove misleading sanitized attr (#1067) ... * fix(safety): escape tool output XML content and remove misleading sanitized attr The `sanitized="true/false"` attribute on `<tool_output>` misled LLMs into treating unfiltered content as pre-sanitized. Remove it and add `escape_xml_content()` to escape `<`, `>`, `&` in tool output body text, preventing injected XML from breaking the structural boundary. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(safety): replace contains assertions with exact assert_eq checks Address Gemini review feedback on PR #1067: replace weak `contains` assertions with precise `assert_eq!` comparisons in three safety tests (wrap_for_llm escaping, XML boundary escape, escape_xml_content). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: replace full XML escaping with targeted </tool_output escape to preserve JSON content The previous approach escaped all XML metacharacters (<, >, &) in tool output, which corrupted JSON content visible to the LLM. This was the same issue that caused PR #598 to be reverted. Now only the closing </tool_output sequence is neutralized (via a zero-width space insertion), matching the pattern already used by escape_skill_content(). All other content including JSON with angle brackets and ampersands passes through unchanged. Also: - Remove unused _sanitized parameter from wrap_for_llm() - Add unwrap_tool_output() with reverse escaping for round-trip fidelity - Add round-trip tests verifying JSON content survives wrap/unwrap - Update trace_llm test helper to use the new unwrap_tool_output() Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: remove unwrap/expect from escape_tool_output_close to pass CI Replace regex-based escaping with simple string search to avoid .unwrap()/.expect() in production code (enforced by CI). Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: re-trigger CI with latest changes Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: remove stale 3rd arg from wrap_for_llm bench call Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review - remove stale 3-arg call, add JSON round-trip test Fix the test_wrap_for_llm_escapes_attr_chars test that still passed a third `_sanitized` argument to wrap_for_llm (removed in earlier commit). Add explicit JSON round-trip test with XML metacharacters ({"query": "a < b & c > d"}) confirming they survive wrap/unwrap intact, as requested in PR #1067 review. https://claude.ai/code/session_017ckCCurNiBL8uzE4dJg59K * fix: remove stale sanitized= references from test fixtures, fix clippy warning Update web/util.rs test fixtures to use the new tool_output format without the removed sanitized="..." attribute. Remove redundant #![cfg(test)] in codex_test_helpers.rs (already gated in mod.rs). https://claude.ai/code/session_01Q4bRgRy96cqfmVPao4XiX8 * test: add round-trip JSON parsing regression gate for PR #598 Adds a test that verifies JSON content with XML metacharacters (<, >, &) survives the full wrap_for_llm -> unwrap_tool_output -> serde_json::from_str pipeline intact. This guards against the exact corruption scenario that motivated reverting full XML escaping in PR #598. https://claude.ai/code/session_01R2Zt832cV1xxDf7NXNq5GV * fix(safety): harden wrap_external_content against boundary injection Address reviewer feedback: apply the same targeted escaping strategy to wrap_external_content() that was applied to wrap_for_llm(). The closing delimiter "--- END EXTERNAL CONTENT ---" is now neutralized in content bodies using a zero-width space, preventing an attacker from injecting a fake closing delimiter to break out of the wrapper. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-21 20:51:03 -07:00
Henry ParkandGitHub	b952d229f9	fix: prefer execution-local message routing metadata (#1449) ... * fix: prefer execution-local message routing metadata * test: cover message routing fallback metadata * refactor: simplify message target resolution * fix: ignore stale channel defaults for notify user metadata	2026-03-19 23:07:55 -07:00
4 people	455f543ba5	fix(routines): surface errors when sandbox unavailable for full_job routines (#769) ... * feat(db): add list_dispatched_routine_runs to RoutineStore trait Add method to query routine runs with status='running' AND job_id IS NOT NULL, enabling the routine engine to sync completion status from background jobs. Implements for both PostgreSQL and libSQL backends. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(routines): sync dispatched full-job runs with background job status (#697) Full-job routines were immediately marked Ok on dispatch, so failures/completions were never reflected in the routine run record. Now dispatch returns Running status, and a periodic sync checks linked jobs to update the run when the job completes, fails, or is cancelled. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(routines): fail fast when sandbox unavailable at dispatch time (#697) Thread sandbox_available bool from Docker detection through AgentDeps to RoutineEngine. Full-job routines now fail immediately with a clear error message when sandbox is enabled but Docker is not available, instead of dispatching a job that silently fails. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(startup): notify user when sandbox unavailable (#697) When sandbox is enabled but Docker is not installed or not running, send a user-visible warning through all channels at startup (with a 2s delay to let channels connect). Previously this was only logged via tracing::warn, invisible to TUI/web users. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in routine_engine.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(tests): set sandbox_available=true in test rig for full_job traces Test rig doesn't use real Docker — full_job routines execute via trace replay. Setting sandbox_available=true allows the routine_news_digest trace test to dispatch full_job routines as before. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(routines): address review feedback on sync_dispatched_runs (#697) - Sanitize last_reason from job transitions before using in notifications (truncate to 500 chars, strip control characters) - Treat Submitted as in-progress (can still transition to Failed), only Completed and Accepted are terminal success states - Add test for sanitize_summary Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(tests): add missing sandbox_available field to test constructors Staging added sandbox_available to AgentDeps and RoutineEngine::new. Add the missing field/argument in test files to fix CI compilation. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: sanitize job reason in notifications, fix state handling for Submitted/Accepted - Enhance sanitize_summary to strip HTML tags and collapse whitespace, preventing injection via untrusted container job reasons - Use char-boundary-safe truncation to avoid panics on multi-byte strings - Treat Submitted and Accepted as in-progress states (continue polling) rather than terminal success, since they can still transition to Failed - Increase channel-connect delay from 2s to 5s and add debug log for sandbox-unavailable warning delivery Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * Replace sandbox_available bool with SandboxReadiness enum Distinguishes DisabledByConfig from DockerUnavailable so full-job routine errors give actionable guidance instead of a generic message. Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: re-trigger CI with latest changes Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add missing owner_id arg to send_notification call Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: update e2e tests to use SandboxReadiness enum Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: [email protected] <[email protected]>	2026-03-19 21:20:41 -07:00
3 people	09e1c97a27	fix(approval): make "always" auto-approve work for credentialed HTTP requests (#1257) ... The HTTP tool returned `ApprovalRequirement::Always` for requests with credentials, but `Always` is hardcoded to ignore the session auto-approve set. This meant users who clicked "always" were re-prompted on every subsequent HTTP call — the UI offered "always" but the backend ignored it. Two fixes: 1. HTTP credentialed requests now return `UnlessAutoApproved` instead of `Always`, so the session auto-approve set is respected. 2. `StatusUpdate::ApprovalNeeded` now carries `allow_always: bool`. All channel UIs (Telegram, Slack, Signal, REPL, Web) conditionally hide the "always" option when a tool truly requires per-invocation approval (`ApprovalRequirement::Always`, e.g. destructive shell commands). Also boxes `PendingApproval` in `AgenticLoopResult::NeedApproval` to fix a pre-existing clippy `large_enum_variant` warning. Regression tests included (test_credentialed_requests_respect_auto_approve, test_allow_always_matches_approval_requirement) but CI heuristic cannot detect them in cross-fork PR diffs. [skip-regression-check] Co-authored-by: Tyler <[email protected]>	2026-03-19 11:45:32 -07:00
3 people	3dcccc1e64	feat(self-repair): wire stuck_threshold, store, and builder (#712) ... * feat(self-repair): wire stuck_threshold, store, and builder (#647) Wire the previously dead-code fields in DefaultSelfRepair: - stuck_threshold: detect_stuck_jobs() now filters by duration, only reporting jobs stuck longer than the configured threshold - with_store(): wired in agent_loop.rs from AgentDeps.store for tool failure tracking via Database trait - with_builder(): wired from register_builder_tool() return value through AppComponents and AgentDeps for automatic tool rebuilding - tools: passed alongside builder for hot-reload logging Remove all #[allow(dead_code)] annotations. Add regression tests for threshold-based filtering (both above and below threshold). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add missing `builder` field to AgentDeps in gateway workflow harness After rebase onto staging, AgentDeps gained a `builder` field for self-repair tool rebuilding. The gateway workflow test harness was missing this field, causing CI compilation failure. Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: retrigger CI * fix: force CI refresh after path_routing_tests dedup * test: add E2E test for stuck job repair and tool rebuild cycle Tests the full self-repair flow requested in review: 1. Job transitions Pending -> InProgress -> Stuck 2. detect_stuck_jobs() finds it (zero threshold) 3. repair_stuck_job() recovers it back to InProgress 4. A broken tool is repaired via MockBuilder 5. Verify builder was invoked and repair succeeded Uses a MockBuilder (impl SoftwareBuilder) that returns successful BuildResult without requiring an LLM or filesystem. Uses libsql test database for the store (increment_repair_attempts, mark_tool_repaired). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(self-repair): measure stuck_duration from Stuck transition, not started_at - Use ctx.transitions to find the most recent Stuck transition timestamp instead of ctx.started_at (which reflects job start, not stuck time) - Fix StuckJob.last_activity to use stuck transition timestamp - Remove misleading "hot-reloaded into registry" log - Remove stray "// ci fix" comment in memory.rs - Add regression test: backdated started_at must not inflate stuck_duration Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: re-trigger CI with latest changes Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add type annotation to Ok(()) in test to resolve E0282 Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-18 20:51:21 -07:00
Nick PismenkovandClaude Haiku 4.5	b50eddfe0a	Merge branch 'main' into fix/resolve-conflicts ... Resolved merge conflicts in 5 files: 1. src/agent/job_monitor.rs - Used is_internal flag approach (HEAD) for safe internal message marking. Removed metadata-based approach which could be spoofed by external channels. 2. src/agent/agent_loop.rs - Used is_internal check (HEAD) for routing internal messages, consistent with security model where is_internal field cannot be spoofed. 3. src/agent/dispatcher.rs - Included notify_metadata in job context (main), needed for job routing through JobMonitorRoute. 4. src/setup/wizard.rs - Added build_nearai_model_fetch_config() function (main) for model selection during setup. 5. src/tools/builtin/job.rs - Used both comments from HEAD (clarifying notify_channel and notify_user logic) while removing metadata field from JobMonitorRoute (consistent with job_monitor.rs). All conflicts resolved with security-first approach: use is_internal boolean field for internal message marking (cannot be spoofed), while passing routing metadata through context. Co-Authored-By: Claude Haiku 4.5 <[email protected]>	2026-03-16 14:47:07 -07:00
Henry ParkandGitHub	878a67cdb6	Refactor owner scope across channels and fix default routing fallback (#1151) ... * refactor: add explicit owner scope across channels * fix: tighten routine owner target routing * fix: address owner scope review feedback * Fix owner-scope onboarding and event trigger isolation * Tighten routing fallback and wizard owner validation * fix: address owner-scope follow-up review * fix: tighten owner-scope follow-up details * fix: import Channel trait in telegram test * fix: normalize http webhook sender ids * fix: address remaining owner-scope review issues * fix: reconcile config rebase fallout * fix: reconcile extension manager rebase drift * fix: address current copilot review regressions * fix: restore clippy matrix after rebase	2026-03-16 13:31:03 -07:00
Henry ParkandGitHub	4890e73a34	Merge pull request #1132 from nearai/staging-promote/e805ec61-23059634819 ... chore: promote staging to main (2026-03-13 16:09 UTC)	2026-03-16 09:22:58 -07:00
3 people	bde0b77a86	fix(security): prevent metadata spoofing of internal job monitor flag (#1195) ... The `__internal_job_monitor` metadata key that bypassed the entire agent pipeline (hooks, safety checks, LLM processing) was spoofable by external channels — WASM channel plugins could inject arbitrary metadata including this key, causing attacker-controlled content to be forwarded directly as assistant responses. Replace the metadata-based check with a dedicated `is_internal` field on `IncomingMessage` that can only be set via `into_internal()` by trusted in-process code. Both the field and setter are `pub(crate)` to prevent external crates from spoofing the flag. Also remove `notify_metadata` forwarding (the monitor only needs channel/user/thread routing) and the unused `__job_monitor_job_id` metadata key. Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-15 21:33:04 +00:00
pikaxingeandGitHub	c4e098d4e3	Fix subagent monitor events being treated as user input (#1173) ... * Fix subagent monitor routing to avoid LLM re-entry * Update yanked uds_windows dependency in lockfile	2026-03-15 06:00:19 +00:00
3 people	757d24bd90	feat(web): add follow-up suggestion chips and ghost text (#1156) ... * feat(web): add follow-up suggestion chips and ghost text to chat UI The LLM now always generates 1-3 follow-up command suggestions via <suggestions> tags in its response. These are extracted server-side, broadcast as SSE events, and rendered as clickable chips above the chat input. The first suggestion also appears as ghost text in the input field (Tab to accept). Includes debug logging for LLM responses in the agentic loop and removes noisy NEAR AI status logging. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: resolve deferred review items from PR #1156 [skip-regression-check] - Remove literal backslashes from raw string prompt (reasoning.rs) - Make WASM channels skip Suggestions status (no-op instead of empty callback) - Add !e.shiftKey guard to Tab-to-accept ghost text handler - Cap extracted suggestions at 3 and trim whitespace-only entries - Extract suggestions in approval-resume path (prevents tag leaking) - Remove stale .has-ghost class during showSuggestionChips reset Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-14 18:57:24 +00:00
3 people	c94ecf19db	feat: add Slack approval buttons for tool execution in DMs (#796) ... * feat: add channel-relay integration for Slack via external relay service - Add RelayChannel and RelayClient for connecting to channel-relay SSE streams - Add RelayConfig with env-based configuration (CHANNEL_RELAY_URL, CHANNEL_RELAY_API_KEY) - Add channel-relay extension lifecycle: install, OAuth auth, activate with hot-add - Add proxy message sending through channel-relay for Slack chat.postMessage - Add extension registry entry for Slack relay with OAuth auth hint - Add relay integration test with mock SSE server - Wire relay channel into app startup with reconnect on stored credentials - Add AuthRequired extension error variant for cleaner auth flow detection [skip-regression-check] * chore: apply cargo fmt * fix: remove remaining Telegram test references in relay channel * fix: address PR #790 review feedback — parser handle leak, CSRF, circuit breaker - Fix parser handle leak on reconnect by sharing Arc<RwLock> instead of creating a local copy in start() (shutdown now aborts the correct task) - Add CSRF state nonce to OAuth flow: generate in auth_channel_relay, validate in slack_relay_oauth_callback_handler, one-time use - Remove dead proxy_slack method, update integration test to use proxy_provider - Add reconnect circuit breaker (max_consecutive_failures, default 50) - Fix stale docs (Telegram refs), extract event_types constants * fix: double backoff in reconnect loop and UTF-8 chunk-boundary corruption - Remove second sleep+backoff in list_connections error branch to prevent O(4^n) backoff growth (was sleeping and doubling twice per iteration) - Buffer raw bytes in SSE parser instead of per-chunk String::from_utf8_lossy to prevent U+FFFD corruption when multi-byte chars span chunk boundaries * feat: add Slack approval buttons for tool execution in DMs Send Block Kit Approve/Deny buttons via relay when a tool requires approval in a DM context. Auto-deny approval-requiring tools in shared channels to prevent prompt injection and stuck threads. * fix: address PR #796 review — use PreflightOutcome::Rejected, add tests - Auto-deny in non-DM relay channels now uses PreflightOutcome::Rejected instead of manually pushing to reason_ctx.messages, so the post-flight handler properly records the error in the turn - Add regression tests for relay auto-deny decision logic - Remove test_clean.db artifact * feat: restore Block Kit approval buttons in send_status The send_status implementation was accidentally dropped during the staging merge. Restores Approve/Deny Block Kit buttons for DM tool approval, with required sender_id validation, payload size docs, and 4 regression tests. Also removes test_clean.db. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: apply rustfmt formatting to dispatcher test code Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-12 11:38:53 -07:00
3 people	1f5b582c5f	fix: agent logging (#888) ... * fix: optimize agent logging to reduce DataDog bill * fix: log permanent repair failures as ERROR not WARN RepairResult::Failed is permanent failure requiring attention (ERROR level) not a temporary/retryable condition (WARN level). [skip-regression-check] Co-Authored-By: Claude Haiku 4.5 <[email protected]> * security: remove user message content from trace logs Never log user message content at any log level (includes TRACE). Log only safe metadata: content length, message ID, image count. This prevents accidental exposure of sensitive user data in logs even at the most verbose logging level. [skip-regression-check] Co-Authored-By: Claude Haiku 4.5 <[email protected]> * security: move LLM response body logging to TRACE level Response bodies can contain user-generated content, tool outputs, and leaked secrets. Moving to TRACE (not enabled in production) prevents exposure in DEBUG logs. Status log remains at DEBUG. [skip-regression-check] Co-Authored-By: Claude Haiku 4.5 <[email protected]> * refactor: simplify URL sanitization using url::Url API Use set_query, set_fragment, set_username, set_password methods instead of manual string reconstruction. Cleaner, handles edge cases, eliminates port branching complexity. [skip-regression-check] Co-Authored-By: Claude Haiku 4.5 <[email protected]> * test: add comprehensive unit tests for sanitize_url_for_logging Add 9 test cases covering: - URL with query parameters - URL with credentials (user:pass@host) - URL with fragment - URL with port - URL with all components combined - Malformed URL fallback behavior - Short strings (pass-through) - Non-URL-like strings - Path preservation Tests verify that sanitization correctly removes sensitive components while preserving safe components like host, port, and path. Co-Authored-By: Claude Haiku 4.5 <[email protected]> * fix: libsql per-migration logs should be DEBUG, not TRACE Individual migration logs are now visible with standard debug logging (RUST_LOG=ironclaw=debug), improving debuggability when troubleshooting migration issues. Summary log remains at INFO level. Fixes behavioral change that made it harder to identify which specific migration ran or failed without enabling full TRACE logging. [skip-regression-check] --------- Co-authored-by: Claude Haiku 4.5 <[email protected]>	2026-03-10 13:55:06 -07:00
7 people	88f4894a18	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]>	2026-03-10 11:19:23 -07:00
5 people	60881d6888	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]>	2026-03-10 11:07:29 -07:00
3 people	83950d11a4	fix: job token budget, iteration cap → Failed, web cancel stops worker (#788) ... * 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: add job token budget, change iteration cap to Failed, fix web cancel (#698) Jobs could enter infinite retry loops because: (1) no token budget was enforced, (2) iteration cap marked jobs as Stuck (allowing self-repair to restart them), and (3) the web UI cancel button only updated the DB without stopping the running worker. - Add `max_tokens_per_job` config (settings.json + AGENT_MAX_TOKENS_PER_JOB env var, default 0 = unlimited) with per-job metadata override - Track token usage after respond_with_tools() and fail the job on budget exceeded - Change iteration cap and persistent rate limiting from mark_stuck to mark_failed, preventing self-repair restart loops - Fix web cancel handler to call scheduler.stop() which updates in-memory state AND aborts the worker task, falling back to DB-only update Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review — always persist cancel to DB, simplify token check - Cancel handler now always persists Cancelled to DB regardless of whether scheduler.stop() ran, fixing the edge case where stop() returns Ok(()) for jobs not in the scheduler map - Collapse nested ifs per clippy (let-chains) - Add NOTE comment about select_tools() not exposing TokenUsage [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: rustfmt formatting in wizard.rs (pre-existing) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-10 02:19:56 +00:00
Nick PismenkovandGitHub	7d8576a464	fix: destructive actions from ambiguous user prompts (#782) ... * fix: destructive actions from ambiguous user prompts * review fixes * review fixes	2026-03-09 18:03:39 -07:00
ReidandGitHub	290d925c7f	fix: preserve tool-call history across thread hydration (#568) (#670) ... Prevent model re-attempts and data inconsistencies when rebuilding conversation context from persisted tool-call records. - Remove raw tool parameters from persisted tool_calls JSON to prevent unredacted sensitive data from being stored in the database. The LLM context rebuild only needs call_id + name + result. - Make record_tool_error/record_tool_result mutually exclusive in all three execution paths (dispatcher, approval, deferred). Previously error cases called both methods, violating the TurnToolCall invariant and sending contradictory outcomes to the LLM. - Unify call_id format to turn{N}_{i} between live sessions and persisted hydration to eliminate ID mismatch in the LLM context. - Auto-close </tool_output> XML tags after truncate_preview truncation to prevent malformed tool output reaching the LLM. [skip-regression-check]	2026-03-09 08:36:07 -07:00
4 people	553c306c52	feat: full image support across all channels (#725) ... * feat: full image support across all channels End-to-end image handling: upload, generation, analysis, editing, and rendering across web gateway, HTTP webhook, WASM (Telegram/Slack), and REPL channels. Builds on the attachment infrastructure from #596 and draws inspiration from PR #641's image pipeline approach — credit to that PR's author for the sentinel JSON pattern and base64-in-JSON upload design. Key changes: - Image upload in web UI (file picker, paste, preview strip) - Image generation tool (FLUX/DALL-E via /v1/images/generations) - Image edit tool (multipart /v1/images/edits with fallback) - Image analysis tool (vision model for workspace images) - Model detection utilities (image_models.rs, vision_models.rs) - Sentinel JSON detection in dispatcher for generated image rendering - StatusUpdate::ImageGenerated → SSE/WS/REPL/WASM broadcast - HTTP webhook attachment support (base64, 5MB/file, 10MB total) - WASM channel image download (Telegram via file API, Slack via host HTTP) - Tool registration wiring in app.rs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR #725 review comments (16 issues) - SecretString for API keys in all image tools (image_gen, image_edit, image_analyze) - Binary image read via tokio::fs::read instead of DB-backed workspace.read() - Replace Arc<Workspace> with Option<PathBuf> base_dir (workspace has no filesystem API) - ApprovalRequirement::UnlessAutoApproved for cost-sensitive image tools - Scope sentinel detection to image_generate/image_edit tool names only - Skip ToolResult preview broadcast for image sentinels (avoids multi-MB base64 in SSE) - Extract shared media_type_from_path() to builtin/mod.rs - Rename fallback_chat_edit → fallback_generate with tracing::warn - Increase gateway body limit from 1MB to 10MB for image uploads - Increase webhook body limit to 15MB (base64 overhead) - Log warning on invalid base64 in images_to_attachments - Client-side image size limits (5MB/file, 5 images max) in app.js - aria-label on attach button for accessibility - Update body_too_large test for new 10MB limit [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add Slack file size check before download (PR review item #15) Skip downloading files larger than 20 MB in the Slack WASM channel to avoid excessive memory use and slow downloads in the WASM runtime. Logs a warning when a file is skipped. Also bumps channel versions for Slack and Telegram (prior branch changes). [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(security): add path validation and approval requirement to image tools Add sandbox path validation via validate_path() to both ImageAnalyzeTool and ImageEditTool to prevent path traversal attacks that could exfiltrate arbitrary files through external vision/edit APIs. Also fix ImageAnalyzeTool::requires_approval to return UnlessAutoApproved, consistent with ImageEditTool and ImageGenerateTool. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: post-download size guards and empty data_url sentinel check - Slack: add post-download size check on actual bytes when metadata size_bytes is absent, preventing bypass of the 20MB limit - Telegram: add 20MB download size limit (matching Slack) enforced in download_telegram_file() after receiving response bytes - Dispatcher: skip broadcasting ImageGenerated SSE event when data_url is empty from unwrap_or_default(), log warning instead Closes correctness issues #3, #4, #5 from PR #725 review. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use mime_guess for media type detection, add alt attrs and media_type validation - Replace hardcoded media type mapping with mime_guess crate (already in deps) - Add alt attributes to img elements in web UI for accessibility - Validate media_type starts with "image/" in images_to_attachments() - Update bmp test assertion to match mime_guess behavior Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: Zaki <[email protected]>	2026-03-09 03:41:27 +00:00
3 people	272d31797e	chore: remove dead code (#648) (#703) ... * chore: remove dead code (LlmEvaluator, chunk_by_paragraphs, bundled channel installer, Reasoning::safety) Delete unused code flagged in #648: - evaluation/success.rs: delete LlmEvaluator struct/impl, remove #[allow(dead_code)] from RuleBasedEvaluator methods - workspace/chunker.rs: delete chunk_by_paragraphs() and its tests (zero production callers) - extensions/manager.rs: delete install_bundled_channel_from_artifacts() (hot-activation never shipped) - llm/reasoning.rs: remove unused safety field from Reasoning struct; cascade removal through ContextCompactor, HeartbeatRunner, LlmSoftwareBuilder, and all callers Closes #648 [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: move RuleBasedEvaluator into test module to fix dead_code warning RuleBasedEvaluator has no production callers -- it was only used in tests of itself. Moving it into #[cfg(test)] eliminates the clippy dead_code error that broke CI. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-08 08:26:04 +00:00
3 people	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]>	2026-03-08 08:01:56 +00:00
3 people	d144484b06	feat: WASM channel attachments with LLM pipeline integration (#596) ... * feat: add inbound attachment support to WASM channel system Add attachment record to WIT interface and implement inbound media parsing across all four channel implementations (Telegram, Slack, WhatsApp, Discord). Attachments flow from WASM channels through EmittedMessage to IncomingMessage with validation (size limits, MIME allowlist, count caps) at the host boundary. - Add `attachment` record to `emitted-message` in wit/channel.wit - Add `IncomingAttachment` struct to channel.rs and re-export - Add host-side validation (20MB total, 10 max, MIME allowlist) - Telegram: parse photo, document, audio, video, voice, sticker - Slack: parse file attachments with url_private - WhatsApp: parse image, audio, video, document with captions - Discord: backward-compatible empty attachments - Update FEATURE_PARITY.md section 7 - Add fixture-based tests per channel and host integration tests [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: integrate outbound attachment support and reconcile WIT types (#409) Reconcile PR #409's outbound attachment work with our inbound attachment support into a unified design: WIT type split: - `inbound-attachment` in channel-host: metadata-only (id, mime_type, filename, size_bytes, source_url, storage_key, extracted_text) - `attachment` in channel: raw bytes (filename, mime_type, data) on agent-response for outbound sending Outbound features (from PR #409): - `on-broadcast` WIT export for proactive messages without prior inbound - Telegram: multipart sendPhoto/sendDocument with auto photo→document fallback for files >10MB - wrapper.rs: `call_on_broadcast`, `read_attachments` from disk, attachment params threaded through `call_on_respond` - HTTP tool: `save_to` param for binary downloads to /tmp/ (50MB limit, path traversal protection, SSRF-safe redirect following) - Message tool: allow /tmp/ paths for attachments alongside base_dir - Credential env var fallback in inject_channel_credentials Channel updates: - All 4 channels implement on_broadcast (Telegram full, others stub) - Telegram: polling_enabled config, adjusted poll timeout - Inbound attachment types renamed to InboundAttachment in all channels Tests: 1965 passing (9 new), 0 clippy warnings [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add audio transcription pipeline and extensible WIT attachment design Add host-side transcription middleware (OpenAI Whisper) that detects audio attachments with inline data on incoming messages and transcribes them automatically. Refactor WIT inbound-attachment to use extras-json and a store-attachment-data host function instead of typed fields, so future attachment properties (dimensions, codec, etc.) don't require WIT changes that invalidate all channel plugins. - Add src/transcription/ module: TranscriptionProvider trait, TranscriptionMiddleware, AudioFormat enum, OpenAI Whisper provider - Add src/config/transcription.rs: TRANSCRIPTION_ENABLED/MODEL/BASE_URL - Wire middleware into agent message loop via AgentDeps - WIT: replace data + duration-secs with extras-json + store-attachment-data - Host: parse extras-json for well-known keys, merge stored binary data - Telegram: download voice files via store-attachment-data, add duration to extras-json, add /file/bot to HTTP allowlist, voice-only placeholder - Add reqwest multipart feature for Whisper API uploads - 5 regression tests for transcription middleware Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: wire attachment processing into LLM pipeline with multimodal image support Attachments on incoming messages are now augmented into user text via XML tags before entering the turn system, and images with data are passed as multimodal content parts (base64 data URIs) to LLM providers. This enables audio transcripts, document text, and image content to reach the LLM without changes to ChatMessage serialization or provider interfaces. - Add src/agent/attachments.rs with augment_with_attachments() and 9 unit tests - Add ContentPart/ImageUrl types to llm::provider with OpenAI-compatible serde - Carry image_content_parts transiently on Turn (skipped in serialization) - Update nearai_chat and rig_adapter to serialize multimodal content - Add 3 e2e tests verifying attachments flow through the full agent loop Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: CI failures — formatting, version bumps, and Telegram voice test - Fix cargo fmt formatting in attachments.rs, nearai_chat.rs, rig_adapter.rs, e2e_attachments.rs - Bump channel registry versions 0.1.0 → 0.2.0 (discord, slack, telegram, whatsapp) to satisfy version-bump CI check - Fix Telegram test_extract_attachments_voice: add missing required `duration` field to voice fixture JSON Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: bump WIT channel version to 0.3.0, fix Telegram voice test, add pre-commit hook - Bump wit/channel.wit package version 0.2.0 → 0.3.0 (interface changed with store-attachment-data) - Update WIT_CHANNEL_VERSION constant and registry wit_version fields to match - Fix Telegram test_extract_attachments_voice: gate voice download behind #[cfg(target_arch = "wasm32")] so host functions aren't called in native tests, update assertions for generated filename and extras_json duration - Add @0.3.0 linker stubs in wit_compat.rs - Add .githooks/pre-commit hook that runs scripts/check-version-bumps.sh when WIT or extension sources are staged - Symlink commit-msg regression hook into .githooks/ [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: extract voice download from extract_attachments into handle_message Move download_voice_file + store_attachment_data calls out of extract_attachments into a separate download_and_store_voice function called from handle_message. This keeps extract_attachments as a pure data-mapping function with no host calls, making it fully testable in native unit tests without #[cfg(target_arch)] gates. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments — security, correctness, and code quality Security fixes: - Add path validation to read_attachments (restrict to /tmp/) preventing arbitrary file reads from compromised tools - Escape XML special characters in attachment filenames, MIME types, and extracted text to prevent prompt injection via tag spoofing - Percent-encode file_id in Telegram getFile URL to prevent query injection - Clone SecretString directly instead of expose_secret().to_string() Correctness fixes: - Fix store_attachment_data overwrite accounting: subtract old entry size before adding new to prevent inflated totals and false rejections - Use max(reported, stored_size) for attachment size accounting to prevent WASM channels from under-reporting size_bytes to bypass limits - Add application/octet-stream to MIME allowlist (channels default unknown types to this) Code quality: - Extract send_response helper in Telegram, deduplicating on_respond and on_broadcast - Rename misleading Discord test to test_parse_slash_command_interaction - Fix .githooks/commit-msg to use relative symlink (portable across machines) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add tool_upgrade command + fix TOCTOU in save_to path validation Add `tool_upgrade` — a new extension management tool that automatically detects and reinstalls WASM extensions with outdated WIT versions. Preserves authentication secrets during upgrade. Supports upgrading a single extension by name or all installed WASM tools/channels at once. Fix TOCTOU in `validate_save_to_path`: validate the path *before* creating parent directories, so traversal paths like `/tmp/../../etc/` cannot cause filesystem mutations outside /tmp before being rejected. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: unify WIT package version to 0.3.0 across tool.wit and all capabilities tool.wit and channel.wit share the `near:agent` package namespace, so they must declare the same version. Bumps tool.wit from 0.2.0 to 0.3.0 and updates all capabilities files and registry entries to match. Fixes `cargo component build` failure: "package identifier near:[email protected] does not match previous package name of near:[email protected]" [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: move WIT file comments after package declaration WIT treats `//` comments before `package` as doc comments. When both tool.wit and channel.wit had header comments, the parser rejected them as "doc comments on multiple 'package' items". Move comments after the package declaration in both files. Also bumps tool registry versions to 0.2.0 to match the WIT 0.3.0 bump. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: display extension versions in gateway Extensions tab Add version field to InstalledExtension and RegistryEntry types, pipe through the web API (ExtensionInfo, RegistryEntryInfo), and render as a badge in the gateway UI for both installed and available extensions. For installed WASM extensions, version is read from the capabilities file with a fallback to the registry entry when the local file has no version (old installations). Bump all extension Cargo.toml and registry JSON versions from 0.1.0 to 0.2.0 to keep them in sync. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add document text extraction middleware for PDF, Office, and text files Extract text from document attachments (PDF, DOCX, PPTX, XLSX, RTF, plain text, code files) so the LLM can reason about uploaded documents. Uses pdf-extract for PDFs, zip+XML parsing for Office XML formats, and UTF-8 decode for text files. Wired into the agent loop after transcription middleware. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: download document files in Telegram channel for text extraction The DocumentExtractionMiddleware needs file bytes in the attachment `data` field, but only voice files were being downloaded. Document attachments (PDFs, DOCX, etc.) had empty `data` and a source_url with a credential placeholder that only works inside the WASM host's http_request. Add `download_and_store_documents()` that downloads non-voice, non-image, non-audio attachments via the existing two-step getFile→download flow and stores bytes via `store_attachment_data` for host-side extraction. Also rename `download_voice_file` → `download_telegram_file` since it's generic for any file_id. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: allow Office MIME types and increase file download limit for Telegram Two issues preventing document extraction from Telegram: 1. PPTX/DOCX/XLSX MIME types (application/vnd.*) were dropped by the WASM host attachment allowlist — add application/vnd., application/msword, and application/rtf prefixes. 2. Telegram file downloads over 10 MB failed with "Response body too large" — set max_response_bytes to 20 MB in Telegram capabilities. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: report document extraction errors back to user instead of silently skipping - Bump max_response_bytes to 50 MB for Telegram file downloads - When document extraction fails (too large, download error, parse error), set extracted_text to a user-friendly error message instead of leaving it None. This ensures the LLM tells the user what went wrong. - On Telegram download failure, set extracted_text with the error so the user sees feedback even when the file never reaches the extraction middleware. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: store extracted document text in workspace memory for search/recall After document extraction succeeds, write the extracted text to workspace memory at `documents/{date}/{filename}`. This enables: - Full-text and semantic search over past uploaded documents - Cross-conversation recall ("what did that PDF say?") - Automatic chunking and embedding via the workspace pipeline Documents are stored with metadata header (uploader, channel, date, MIME type). Error messages (extraction failures) are not stored — only successful extractions. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: CI failures — formatting, unused assignment warning - Run cargo fmt on document_extraction and agent_loop modules - Suppress unused_assignments warning on trace_llm_ref (used only behind #[cfg(feature = "libsql")]) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review comments — security, correctness, and code quality Security fixes: - Remove SSRF-prone download() from DocumentExtractionMiddleware (#13) - Sanitize filenames in workspace path to prevent directory traversal (#11) - Pre-check file size before reading in WASM wrapper to prevent OOM (#2) - Percent-encode file_id in Telegram source URLs (#7) Correctness fixes: - Clear image_content_parts on turn end to prevent memory leak (#1) - Find first *successful* transcription instead of first overall (#3) - Enforce data.len() size limit in document extraction (#10) - Use UTF-8 safe truncation with char_indices() (#12) Robustness & code quality: - Add 120s timeout to OpenAI Whisper HTTP client (#5) - Trim trailing slash from Whisper base_url (#6) - Allow ~/.ironclaw/ paths in WASM wrapper (#8) - Return error from on_broadcast in Slack/Discord/WhatsApp (#9) - Fix doc comment in HTTP tool (#4) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: formatting — cargo fmt Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address latest PR review — doc comments, error messages, version bumps - Fix DocumentExtractionMiddleware doc comment (no longer downloads from source_url) - Fix error message: "no inline data" instead of "no download URL" - Log error + fallback instead of silent unwrap_or_default on Whisper HTTP client - Bump all capabilities.json versions from 0.1.0 to 0.2.0 to match Cargo.toml Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: remove unsupported profile: minimal from CI workflows [skip-regression-check] dtolnay/rust-toolchain@stable does not accept the 'profile' input (it was a parameter for the deprecated actions-rs/toolchain action). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: merge with latest main — resolve compilation errors and PR review nits - Add version: None to RegistryEntry/InstalledExtension test constructors - Fix MessageContent type mismatches in nearai_chat tests (String → MessageContent::Text) - Fix .contains() calls on MessageContent — use .as_text().unwrap() - Remove redundant trace_llm_ref = None assignment in test_rig - Check data size before clone in document extraction to avoid unnecessary allocation [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-07 18:01:40 +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
5 people	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]>	2026-03-07 09:10:05 +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	4ac78a5b1f	fix: reliable network tests and improved tool error messages (#626) ... * fix(wasm): use per-engine cache dirs on Windows to avoid file lock error (#448) On Windows, multiple wasmtime Engine instances sharing the default compilation cache directory hit OS error 33 (ERROR_LOCK_VIOLATION) because Windows holds exclusive file locks on memory-mapped cache files. This is especially triggered when the Telegram channel WASM module is loaded at startup and then hot-activated via the Extensions UI. Fix by giving each engine its own cache subdirectory on Windows (~/.cache/ironclaw/wasmtime-tools/ and wasmtime-channels/). On Unix the shared default cache continues to work as before. Also adds Windows CI jobs (cargo check + clippy across all feature flag combinations) to catch Windows-specific issues going forward. Closes #448 Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: silence Windows clippy warnings for platform-gated code Gate PathBuf import behind #[cfg(unix)] in container.rs (only used in Unix socket path), suppress unused_mut on conflicts Vec in channels.rs (mutations are platform-gated), and add cfg gates on keychain constants and hex_to_bytes that are only used on macOS/Linux. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: escape directory path in TOML cache config to prevent injection Use double-quoted TOML strings with backslash and double-quote escaping for the cache directory path, preventing breakage or injection when paths contain special characters (e.g. single quotes on Unix, backslashes on Windows). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: resolve cargo fmt formatting errors Fix import ordering in container.rs and line wrapping in runtime.rs to pass the CI formatting check. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(ci): restore Path import for all platforms, keep PathBuf unix-only Path is used in non-cfg-gated functions (lines 148, 244) so it must be available on all platforms. Only PathBuf is unix-specific. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use RFC 5737 TEST-NET-1 IPs for reliable network failure tests Replace localhost/loopback addresses with 192.0.2.1 (TEST-NET-1) in network failure tests so they work consistently behind HTTP proxies. Tighten the catalog.rs error assertion to avoid matching any string containing "error". Closes #444 (takeover from hobostay) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: include tool name in error messages sent to LLM Format tool errors as "Tool '<name>' failed: <reason>" instead of the bare "Error: <reason>" so the LLM can identify which tool failed and reason about alternatives. Does not short-circuit the agent loop -- errors still flow back to the LLM for reasoning. Closes #487 (takeover from lustsazeus-lab, PR #530) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: resolve cargo fmt formatting in dispatcher Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-07 05:54:12 +00:00
3 people	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]>	2026-03-06 00:49:10 +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
3 people	902492bcdb	feat(web): show error details for failed tool calls (#490) ... * feat(web): show error details and input params for failed tool calls Failed tool calls in the gateway UI previously showed only a red X icon with an empty expandable body. This change: - Adds optional `error` and `parameters` fields to `ToolCompleted` SSE events so the browser receives failure details in real-time - Auto-expands failed tool cards to make errors immediately visible - Adds `StatusUpdate::tool_completed()` constructor that centralizes the 5 duplicated construction sites and applies `redact_params()` to prevent sensitive values (e.g. secret_save's "value" param) from leaking through SSE broadcasts - Adds `sensitive_params()` trait method to `Tool` for declaring which parameters must be redacted before logging, hooks, and UI display - Adds `redact_params()` utility and wires it through hooks, approvals, ActionRecord storage, and debug logs in dispatcher/worker - Adds `SecretListTool` and `SecretDeleteTool` for LLM-driven secret management (values never returned, only names/metadata) - Fixes auth flow: setup-only extensions show configure modal instead of OAuth card; auth_completed SSE dismisses both UI paths - CI: release workflow creates PR instead of pushing directly to main - Registry: MissingChecksum error enables source fallback for bootstrapping when checksums haven't been populated yet Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: apply cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: keep original params in PendingApproval for execution, redact only for display Address two PR review comments: 1. execute_chat_tool_standalone now redacts sensitive params before logging, matching the pattern already used in worker.rs. 2. PendingApproval previously stored redacted parameters, which meant approved tool calls received "[REDACTED]" instead of the actual values. Add a display_parameters field for UI/logs and keep parameters as the original values used for execution. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review comments - worker.rs: redact sensitive params before BeforeToolCall hook, matching dispatcher.rs — hooks in the autonomous job path now receive redacted params instead of raw values - registry.rs: fix docstring for register_secrets_tools (list, delete, not save/list/delete — no SecretSaveTool is registered) - app.js: fix double toast/loadExtensions in submitConfigureModal — for non-OAuth success the auth_completed SSE already handles both, so skip them in the HTTP response handler to avoid duplicates [skip-regression-check] Co-Authored-By: Claude Sonnet 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-04 15:38:26 -08:00
4 people	89600e2b5c	fix(agent): strip leaked [Called tool ...] text from responses (#497) ... * fix(agent): strip leaked [Called tool ...] text from agent responses When the NEAR AI provider flattens tool_call messages to plain text, markers like [Called tool ...] and [Tool ... returned: ...] can leak into the user-visible response if the LLM echoes them back. This adds a sanitization step in the agentic loop's text response path that strips these internal markers before returning. If stripping leaves the response empty, a generic fallback message is returned instead. Closes #487 Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: use fold instead of collect+join to avoid heap allocation Address review feedback: replace Vec collect + join with fold to build the filtered string directly, avoiding an intermediate heap allocation. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: Pierre LE GUEN <[email protected]>	2026-03-04 18:16:26 +00:00
3 people	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]>	2026-03-03 22:23:30 +08:00
3 people	a24fd3e8a3	Add automated QA: schema validator, CI matrix, Docker build, and P1 test coverage (#353) ... * Add automated QA: tool schema validator, feature-flag CI matrix, Docker build P0 items from the automated QA plan (#352): - Add validate_tool_schema() that checks OpenAI strict-mode rules (type: object, required keys in properties, nested object/array recursion) with 10 unit tests and 6 integration tests covering all core built-in tools - CI test matrix now runs with --all-features, default features, and --no-default-features --features libsql to catch dead code behind wrong cfg gates - CI clippy now runs the same 3-feature matrix with --all flags - Docker build job added to catch missing files in Dockerfile Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add P1 automated QA tests and fix LeakDetector prefix shadowing bug P1 test coverage: config round-trip (settings + bootstrap), shell tool arg handling, safety adversarial tests (sanitizer, leak detector, allowlist), turn persistence (conversations, metadata, pagination, jobs), and a clippy fix for libsql-only builds. Fixed a real bug where AhoCorasick non-overlapping prefix iteration caused shorter prefixes (e.g. "sk-") to shadow longer ones (e.g. "sk-ant-api"), preventing Anthropic API key and SSH private key detection. Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add P2 automated QA tests: chaos, lifecycle, collision, and recovery Cover all P2 items from the automated QA plan: - Circuit breaker chaos tests (hanging provider, rapid cycles, mixed errors) - Failover chaos tests (hanging failover, all-fail, tools path, single provider) - Value estimator boundary tests (negative cost, zero price, zero earnings) - Context length recovery test (ContextLengthExceeded -> compact -> retry) - WASM channel lifecycle tests (write/commit/read round-trip, namespace isolation) - Extension registry collision tests (same-name different-kind coexistence) - Extension filesystem collision tests (separate dirs, detect_kind priority) Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add P3 concurrent stress tests for ContextManager and SessionManager Tests verify thread safety of double-checked locking, TOCTOU prevention, and RwLock-based concurrent access patterns under load. Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add dispatcher loop guard and self-repair stuck job tests Dispatcher: test force_text mechanism prevents infinite tool call loops, verify iteration bound arithmetic guarantees termination for all configs. Self-repair: test stuck job detection, recovery within attempt limits, manual escalation when limit exceeded, graceful degradation without store/builder dependencies. Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add E2E testing infrastructure design doc Python + Playwright framework with mock LLM server for deterministic browser-level testing of the web gateway. Covers connection/auth, chat round-trip with SSE streaming, and skills lifecycle scenarios. Co-Authored-By: Claude Opus 4.6 <[email protected]> * Add E2E testing infrastructure implementation plan 10-task plan covering: scaffolding, mock LLM server, helpers, conftest fixtures, connection/chat/skills test scenarios, CI workflow, README, and integration run. Co-Authored-By: Claude Opus 4.6 <[email protected]> * scaffold: E2E test project with pyproject.toml Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: E2E helpers with DOM selectors and port discovery Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: mock OpenAI-compat LLM server for E2E tests Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: E2E conftest with session fixtures for mock LLM and ironclaw Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: E2E scenario 1 -- connection and tab navigation tests Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: E2E scenario 2 -- chat message round-trip tests Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: E2E scenario 3 -- skills search, install, remove tests Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: add weekly E2E test workflow with Playwright Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: E2E test README with setup and usage instructions Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: E2E test integration fixes from first run - Use temp file DB instead of :memory: (libSQL :memory: doesn't persist tables across execute_batch) - Fix installed skills selector: #skills-list not #installed-skills - Add pytest-timeout to dependencies - Improve skills install/remove test with wait_for instead of fixed sleeps 8 passed, 1 skipped (skills install depends on ClawHub availability) Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add OpenAI strict-mode schema validator for all built-in tools (QA 1.1) Add src/tools/schema_validator.rs with validate_strict_schema() that checks tool parameter schemas against OpenAI function calling strict-mode rules: type object at top level, required keys in properties, enum type consistency, array items definitions, nested object recursion, and additionalProperties. 17 tests validate all 34+ built-in tool schemas across 5 test groups: - 9 simple tools (echo, time, json, http, shell, file read/write/list/patch) - 4 job tools (create, list, status, cancel) - 4 skill tools (list, search, install, remove) - 13 inline schemas for extension, routine, and complex job tools - 4 memory tool schemas Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add E2E scenarios for SSE reconnect, HTML injection, and tool approval (QA 3.3/5/6) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: E2E test reliability for HTML injection and SSE reconnect - HTML injection: test sanitization directly via JS injection instead of depending on full LLM round-trip (avoids intermittent 404 from mock) - SSE reconnect: increase wait times for DB persistence and relax assertion to check total message count after history reload Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt formatting Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add WASM and MCP tool schema validation tests (QA 1.1) Extends the schema validator with representative WASM tool schemas (weather, HTTP client, batch processor, status), MCP tool schemas (default, file read, SQL query, strict mode), and defect detection tests for common external schema issues (missing type, typo in required, array without items, enum type mismatch). Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add auth middleware and compaction module tests Auth middleware (8 new tests): valid/invalid bearer tokens, query param fallback, case sensitivity, empty tokens, whitespace handling. Compaction module (16 new tests): truncation strategy, summarize strategy with mock LLM, workspace fallback, format_turns helper, sequential compactions, coherence after compaction, token decrease verification. Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add config round-trip integration tests (QA 1.2) Test the full bootstrap .env lifecycle: write via the same format as save_bootstrap_env/upsert_bootstrap_var, read back via dotenvy, and assert values match. Covers LLM backend selection, embedding disable flag, onboard completion flag, session token keys, multi-key preservation across upsert, and special characters (spaces, equals, quotes, backslashes, hashes). Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add value estimator boundary tests and dispatcher loop guard (QA 4.3/4.4) Value estimator (14 new tests): zero/negative prices, large values, negative cost, exact margin boundaries, custom margin configuration. Dispatcher loop guard (2 new tests): verifies the dispatch loop terminates when all tool calls fail (regression guard for PR #252 infinite loop) and when max iterations are reached. Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add failover edge cases and provider chaos tests (QA 2.6/4.1) Failover edge cases (4 new tests): cooldown at zero nanos, half-open failure reopens circuit, all providers fail gracefully (no panic), single failing provider with cooldown. Provider chaos tests (15 new tests): flakey provider with retries, hanging provider with timeout, garbage provider, circuit breaker trip/recover, failover chain cascading, non-transient error stops chain, full stack integration (retry + failover + circuit breaker). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR review feedback on QA tests - Fix Bearer auth case-sensitivity per RFC 6750 (auth.rs) - Refactor bootstrap.rs to expose path-parameterized variants so config_round_trip tests call real code instead of reimplementations - Remove deprecated event_loop fixture, use dynamic ports, minimal env, session-scoped browser, and wire HEADED=1 in E2E conftest - Add cross-referencing doc comments between schema validators - Simplify array validation logic in tool.rs - Bump e2e.yml checkout@v4 to @v6 Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt and fix clippy warning in signal.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: improve E2E fixture error reporting and prevent stdin blocking - Add --no-onboard flag to prevent wizard from blocking in CI - Pipe /dev/null to stdin to prevent any stdin reads from hanging - Add RUST_BACKTRACE=1 for crash diagnostics - On server startup timeout, dump stderr to pytest output so CI logs show why the server failed to start Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: set session-scoped event loop for E2E async fixtures pytest-asyncio 1.3.0 defaults asyncio_default_fixture_loop_scope to None (function scope), causing session-scoped async fixtures to be re-evaluated per test function with independent event loops. Each test then independently attempts to start the ironclaw server, times out at 120s, and wastes ~24 minutes of CI before the job is cancelled. Setting asyncio_default_fixture_loop_scope = "session" ensures all session-scoped async fixtures share a single event loop, so the server starts once and is reused across all tests. Also adds -x flag to pytest in CI to stop on first failure instead of running all 19 tests when the fixture is broken. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: set test loop scope to session to match fixture loop scope With asyncio_default_fixture_loop_scope=session but asyncio_default_test_loop_scope=function (the default), tests run on a per-function event loop while fixtures produce objects (Playwright pages, browser contexts) on the session event loop. This event loop mismatch causes the test to hang indefinitely awaiting Playwright operations that are bound to the wrong loop. Setting both scopes to "session" ensures a single event loop is shared across all fixtures and tests, eliminating the deadlock. Co-Authored-By: Claude Opus 4.6 <[email protected]> * ci: add roll-up jobs to match branch protection required checks Branch protection expects "Code Style (fmt + clippy)" and "Run Tests" status checks, but only individual job names were reported. Add roll-up jobs that aggregate results and report the expected names. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-02-27 09:09:45 +04:00
ibhagwanandGitHub	bf35b59222	feat(signal) attachment upload + message tool (#375) ... * feat(channels/signal): add attachment upload support - Add attachments field to OutgoingResponse for carrying file paths - Add with_attachments() builder method to OutgoingResponse - Update build_rpc_params() to include attachments array in JSON-RPC - Update respond() and broadcast() to handle attachments: - Text + attachments: sends text first, then each attachment - Attachments only: sends each attachment with path as message - Text only: original behavior (no change) - Add tests for build_rpc_params with attachments - Add tests for OutgoingResponse attachment builder This enables the Signal channel to send files via signal-cli daemon's JSON-RPC send method, matching the nullclaw implementation. Risk: Low - uses existing JSON-RPC infrastructure Tests: 85 signal tests pass, 1543 lib tests pass * feat(tools): add message tool for cross-channel messaging Add a new 'message' tool that allows the agent to send messages to any connected channel (signal, telegram, slack, etc.) with optional file attachments. Features: - Send messages to specific channel + target combinations - Support for attachments (file paths) - E.164 validation delegated to channel (signal expects +number, telegram accepts username/chat_id, slack uses #channels) - Helpful error messages showing available channels on failure Tool schema: - content: message text (required) - channel: target channel name (optional, defaults to current channel) - target: recipient (E.164, group ID, chat ID) (optional, defaults to current user/group chat) - attachments: optional file paths to send This complements the recently added attachment upload support for the Signal channel by giving the agent a proper way to specify attachments when sending messages. Tests: 4 new tests for message tool schema Risk: Low - new tool with no breaking changes Tests: All 1547 lib tests pass, clippy clean * feat(llm): add conversation context to system prompt for Signal Add conversation_context HashMap to Reasoning struct to pass channel-specific metadata (sender phone, sender UUID, group ID) to the LLM. This helps the agent know who/group it's talking to, preventing it from hallucinating phone numbers or sending to wrong recipients. Changes: - Add conversation_context field and with_conversation_data() builder method - Add build_conversation_section() to include current conversation info in system prompt - Update dispatcher to extract Signal metadata (sender, sender_uuid, group) and pass to Reasoning - Add signal_sender_uuid to Signal channel metadata for privacy mode users * feat(tools): add secure attachment path validation with sandbox enforcement Implement robust path validation for message tool attachments to prevent directory traversal attacks and unauthorized file access. Attachments are now sandboxed to ~/.ironclaw/ by default. Key changes: - Create shared path_utils module with validate_path() and is_path_safe_basic() - Extract normalize_lexical() from file.rs for reuse - MessageTool now enforces sandbox at ~/.ironclaw/ for all attachments - Path validation includes: traversal detection, canonicalization, symlink resolution - Error messages reveal the allowed sandbox directory for user clarity Security improvements: - Blocks path traversal attacks (../, URL-encoded, null bytes) - Canonicalizes paths to resolve symlinks before validation - Walks up to nearest existing ancestor for non-existent paths - Prevents escape from sandbox directory Backward compatibility: - File tools continue to work with their configured base_dir - Message tool defaults to ~/.ironclaw/ sandbox - Tests updated to create files within sandbox Tests added: - path_utils module tests (9 tests for validation logic) - message tool attachment validation tests - All 1571 existing tests pass * fix(channels/signal): use robust path validation with full security coverage Signal channel's validate_attachment_paths() now uses path_utils::validate_path() for consistent, secure path validation. Fixes: - Replaced weak path.contains('..') check with robust validate_path() - validate_path() now includes is_path_safe_basic() as first-pass filter to block null bytes and URL-encoded traversal sequences (%2e%2e%2f) - Error message now shows allowed sandbox directory (~/.ironclaw/) Security coverage: - Path traversal: ../, foo/../bar, ../../etc/passwd ✓ - URL-encoded traversal: %2e%2e%2fetc/passwd ✓ - Null byte injection: file\0.txt ✓ - Paths outside sandbox: /tmp/evil.txt ✓ - Symlink escape attempts (via canonicalization) ✓ Tests added: - validate_attachment_paths_rejects_path_outside_sandbox - validate_attachment_paths_rejects_url_encoded_traversal - validate_attachment_paths_rejects_null_byte - Fixed broken assertion in rejects_double_dot test * fix(llm): add Signal channel to build_channel_section to include message tool hint The catch-all '_' arm was returning early before the message_tool_hint section was constructed, which meant Signal users never got the '## Proactive Messaging' section with examples for: - Using attachments parameter - Targeting different users/groups - Cross-channel messaging Now Signal will include the full message_tool_hint section with usage examples. * fix(tools): use async locks in register_message_tools to prevent silent failures The method was using register_sync which calls try_write() on self.tools. If the lock was held, try_write() would return Err and silently skip adding the tool to the registry, while self.message_tool already held a reference. This creates an inconsistent state. Fix: use async write locks directly instead of register_sync to ensure the tool is always registered or the method fails explicitly. * refactor(dispatcher): use Channel trait for conversation context Replace hardcoded 'if message.channel == signal' block with generic conversation_context() method on the Channel trait. This allows any channel to provide context (sender, group, etc.) without hardcoding channel names. Changes: - Add conversation_context() method to Channel trait (default: empty) - Implement for SignalChannel: extracts sender, sender_uuid, group - Add get_channel() to ChannelManager (returns Arc<dyn Channel>) - Change ChannelManager storage from Box to Arc for shared access - Update dispatcher to use new trait method - Add tests for conversation_context extraction Other channels (Telegram, Slack, Discord) can now implement this method to provide conversation context without code changes in dispatcher. * fix(tests): split message_tool_with_attachments into sandbox and channel tests The original test was passing for the wrong reason - it expected an error because the channel doesn't exist, but actually failed earlier during sandbox validation because /tmp paths are outside ~/.ironclaw/. Split into two tests: - message_tool_with_attachments_outside_sandbox: verifies sandbox rejection with explicit error message check - message_tool_with_attachments_inside_sandbox_no_channel: uses files within sandbox (like message_tool_passes_attachment_to_broadcast does) and verifies the channel-related error message * security(message tool): add rate limiting, approval requirements, and audit logging The message tool can send to ANY connected channel/target making it a significant abuse vector if the LLM is compromised or prompt-injected. This commit adds: 1. Rate limiting: 10 messages/minute, 100/hour per user 2. Approval requirement: Always requires approval for cross-channel messages (when channel differs from the default conversation channel) 3. Audit logging: Every successful message send is logged with channel, target, and attachment count The approval logic: - If channel param is provided and differs from default -> Always require approval - If no default channel is set and explicit channel provided -> Always require approval - Otherwise (using default channel) -> UnlessAutoApproved * fix(message tool): return explicit error for malformed attachments array Previously, malformed attachments like {"attachments": [123, true]} would be silently ignored via .ok().unwrap_or_default(), leaving users confused when attachments weren't sent. Now returns explicit error: "Invalid attachments format: ..." * fix(message tool): verify attachment files exist before sending Previously, non-existent paths would pass sandbox validation and surface as confusing Signal RPC errors. Now returns clear "Attachment file not found" error. * fix(test): create sandbox directory if it doesn't exist for CI The test validate_attachment_paths_accepts_normal_paths uses tempfile::tempdir_in() which requires the parent directory to exist. In CI, ~/.ironclaw doesn't exist, causing test failure.	2026-02-26 18:06:21 +04:00
3 people	443b120272	feat(web): inline tool activity cards with auto-collapsing (#376) ... * feat(web): inline tool activity cards with auto-collapsing Add Claude/Codex-style inline tool activity cards to the web UI that show tool execution progress directly in the chat conversation. While processing: - Animated thinking dots with message text (e.g. "Calling LLM...") - Individual tool cards with live spinner and elapsed timer - Cards show tool name, duration, and expandable output preview After response arrives: - Activity group auto-collapses to "Used N tools (Xs)" - Click summary to expand and see individual tool cards - Click card header to see tool output in monospace Also includes: - "Calling LLM..." thinking status from dispatcher (all channels) - 5-minute max timer guard to prevent leaks on dropped SSE - Handles parallel tools, same tool twice, failures, thread switching Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(web): use frozen duration for completed tools in activity summary The collapsed activity summary was showing inflated total duration because finalizeActivityGroup() recalculated elapsed time from Date.now() for already-completed tools. Now each tool card stores its final duration at completion time and the summary uses that frozen value instead. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-02-25 16:01:35 -08:00
3 people	4e2dd76ae5	Fix skills system: enable by default, fix registry and install (#300) ... * feat: add Docker detection module with platform guidance Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add Docker sandbox step to setup wizard Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: show Docker status in boot screen Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: check Docker availability at startup When SANDBOX_ENABLED=true, proactively detect whether Docker is installed and running before creating the ContainerJobManager. If Docker is unavailable, log a warning with platform-specific guidance and disable the sandbox for the session. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: enable sandbox by default, improve wizard explanation, document detection limits - SandboxConfig defaults to enabled=true (startup check disables gracefully if Docker is unavailable) - Wizard step explains why Docker matters: isolation for LLM-generated code vs running directly on the host - Document detection confidence per platform in detect.rs module docs: high on macOS/Linux, medium on Windows (named pipe edge cases) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: cargo fmt + update test_builder_defaults for enabled-by-default Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: deduplicate wizard Docker status handling per review Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: fix skills system - enable by default, fix registry connectivity and install - Enable skills system by default (SKILLS_ENABLED no longer required) - Bypass Vercel TLS fingerprint blocking by pointing DEFAULT_REGISTRY_URL directly at the Convex backend (wry-manatee-359.convex.site) - Handle ZIP archives from ClawHub download API - the registry returns ZIP files containing SKILL.md, not raw text. Uses flate2 (existing dep) to extract SKILL.md from the archive. - Surface catalog search errors in the UI with a yellow warning banner instead of silently returning empty results - Handle both {"results":[...]} envelope and bare [...] array JSON formats from the search API - Add ClawHub links and metadata to search result cards (clickable skill names linking to clawhub.ai, relevance score, "updated X ago" recency) - Fix 3 pre-existing clippy warnings in tests/html_to_markdown.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address security review feedback on ZIP extraction and SSRF - Cap download size to 10 MB before reading response body - Guard against ZIP bombs: cap uncompressed_size at 1 MB, wrap DeflateDecoder with .take() read limit - Use checked_add for ZIP header offset arithmetic to prevent overflow - Remove .unwrap() on try_into() -- use direct array construction - Handle IPv4-mapped IPv6 addresses (::ffff:192.168.x.x) in SSRF checks - Don't leak internal registry URLs in user-facing catalog_error messages - Fix non-ASCII panic in catalog response debug logging (use .get() instead of byte slicing) Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: add /skills command and enrich search results with ClawHub metadata - Parse /skills and /skills search <query> as SystemCommands in submission.rs - Add skill_catalog to AgentDeps and wire it through main.rs - Handle "skills" command in commands.rs: list installed skills and search ClawHub - Add /skills and /skills search <q> entries to /help output - Add SkillDetail, SkillStats, SkillOwner structs to catalog.rs - Add fetch_skill_detail() calling GET /api/v1/skills/{slug} on Convex backend - Add enrich_search_results() to fetch stars/downloads/owner for top 5 results in parallel - Fix SkillDetailResponse wrapper struct to match actual API shape: {"skill":{...},"owner":{...}} - Surface stars, downloads, owner in web UI skill search cards (app.js) - Surface enriched data in skills web handler and skill_search tool output Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix: cargo fmt after merge conflict resolution Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix: separate installed_skills dir for correct trust on restart, remove duplicate handlers Trust level bug: skills installed from ClawHub were written to user_dir (~/.ironclaw/skills/) which is discovered as Trusted on restart. Now installs go to ~/.ironclaw/installed_skills/ which is discovered as Installed, matching the documented skill directory layout. Changes: - SkillsConfig: add installed_dir field (SKILLS_INSTALLED_DIR env var, default ~/.ironclaw/installed_skills/) - SkillRegistry: add with_installed_dir() builder, installed_dir()/ install_target_dir() accessors, and discover installed_dir with SkillTrust::Installed in discover_all() - All install paths (web handler, skill tool) use install_target_dir() instead of user_dir() so new installs land in the correct directory - 3 new registry tests: test_installed_dir_uses_installed_trust, test_install_target_dir_prefers_installed_dir, test_user_dir_stays_trusted_with_installed_dir Duplicate handler cleanup: handlers/skills.rs was the canonical implementation but the handlers module was never compiled (not declared in web/mod.rs), so server.rs had its own duplicate inline definitions that the router used. Wire up the handlers module, delete the 260-line duplicate in server.rs, and have server.rs import skills handlers from handlers::skills. Fix pre-existing compile error in handlers/extensions.rs (missing needs_setup field). Add #[allow(dead_code)] on not-yet-migrated handler modules to suppress warnings. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: probe more Docker socket paths on macOS Docker Desktop 4.13+ (stabilised in 4.18) no longer creates the /var/run/docker.sock symlink by default. The API socket lives at ~/.docker/run/docker.sock, which bollard's connect_with_local_defaults() does not try. Add a fallback probe list covering the common macOS container runtimes: - ~/.docker/run/docker.sock — Docker Desktop 4.13+ - ~/.colima/default/docker.sock — Colima - ~/.rd/docker.sock — Rancher Desktop Remove the bogus ~/.docker/desktop/docker.sock path that was added previously; it is not an API socket on any known Docker installation. Fixes the false-negative "Docker is installed but not running" warning reported by Illia on macOS with Docker Desktop 4.18+. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * Harden Docker detection for rootless Linux and Windows fallback --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-02-23 10:04:02 -08:00
3 people	6f21cfa680	fix: auto-compact and retry on ContextLengthExceeded (#315) ... * fix: auto-compact and retry on ContextLengthExceeded in agentic loop When the LLM returns a context-length-exceeded error mid-turn, the dispatcher now automatically compacts the conversation history and retries once instead of propagating the raw error to the user. The compaction keeps all system messages (system prompt, skill context), the last user message, and all subsequent messages (current turn's tool calls and results), dropping older conversation history. A note is inserted to inform the LLM that earlier context was dropped. If the retry also fails, the original error is returned. Fixes nearai/ironclaw#260 Co-Authored-By: Claude Opus 4.6 <[email protected]> * Address Gemini/Copilot review feedback - Fix system message duplication: only collect system messages before the last User message to avoid duplicating nudges in the tail slice (Gemini + Copilot) - Only add compaction note when earlier history is actually dropped (Copilot) - Propagate actual retry error instead of masking with original (Copilot) - Fix else branch to preserve system messages when no User messages exist - Add test for nudge-after-user deduplication Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-02-23 00:29:31 +00:00
3 people	ea57447649	feat: hot-activate WASM channels, channel-first prompts, unified artifact resolution (#297) ... * refactor: unify WASM artifact resolution into registry/artifacts.rs Consolidate duplicated WASM find/build/install logic from 5+ files into a single src/registry/artifacts.rs module. This fixes two bugs: - registry/installer.rs now respects CARGO_TARGET_DIR (was hardcoded) - channels/wasm/bundled.rs now searches all WASM triples (was wasip2 only) Also includes: extension manager hot-activation for WASM channels, extension guidance in LLM prompts, channel manager hot-add support, webhook router channel lookup, and minor cleanups. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: send approval prompts as messages on WASM channels (Telegram, Slack) WASM channels mapped ApprovalNeeded status to a typing indicator, so users on Telegram never saw tool approval prompts — the agent got stuck in AwaitingApproval and all subsequent messages failed with "Waiting for approval". - Intercept ApprovalNeeded in WasmChannel::handle_status_update and send the prompt as an actual message via call_on_respond, showing tool name, description, parameters, and yes/no/always instructions - Guard against empty LLM responses after clean_response() strips reasoning_content think-tags (defense-in-depth for reasoning models) - Add reasoning_content fallback to NearAiChatProvider::complete() for consistency with complete_with_tools() - Add debug logging when empty responses are suppressed - Improve error logging for channel respond() failures - Register WASM channel webhook routes before credential checks so platforms don't deactivate webhook URLs with 404s Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address PR #297 review comments - ChannelManager::add: use async write().await instead of try_write() - resolve_target_dir: resolve relative CARGO_TARGET_DIR against crate_dir - install_wasm_files: log warning on capabilities copy failure - refresh_active_channel: load capabilities file for webhook secret name - activate_wasm_channel: validate name against path traversal - Fix cargo fmt formatting in nearai_chat.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: wire up channel runtime for hot-activation and address PR review round 2 - Wire up set_channel_runtime() in main.rs so hot-activation actually works (with_channel_runtime was never called — hot-activation was dead code) - Change ExtensionManager channel runtime fields to RwLock<Option<...>> interior mutability so set_channel_runtime(&self) works after Arc wrapping - Fix artifact tests to use resolve_target_dir() instead of hardcoding "target/" (breaks when CARGO_TARGET_DIR is set) - Fix bundled.rs build hint: cargo component build (not cargo build --target) - Fix wasm_artifact_path doc: binary_name should not include .wasm extension Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use char-aware truncation to prevent UTF-8 panic in approval prompt &s[..77] panics on multi-byte UTF-8 (CJK, emoji). Use s.chars().take(77) for safe truncation at character boundaries. Co-Authored-By: Claude Opus 4.6 <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-02-22 08:09:56 +00:00