769 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
4 people	8638895879	feat(gemini_oauth): full Gemini CLI OAuth integration with Cloud Code API (#1356) ... * feat: integrate Gemini CLI OAuth with Cloud Code API - Add gemini_oauth.rs: full OAuth flow with PKCE, token refresh, and Cloud Code project discovery (loadCodeAssist + onboardUser) - Route preview/gemini-3 models through cloudcode-pa.googleapis.com with proper project ID injection in request payload - Trigger OAuth login during onboarding wizard (not first chat message) - Support manual redirect URL paste as fallback (tokio::select race) - Parse 429 rate-limit errors with retry_after from Google response - Add static model list: gemini-1.5/2.0/2.5/3.0/3.1 variants - Add GeminiOauthConfig with default credentials path (~/.gemini/) * feat(gemini): implement function calling, generationConfig, and update models - Implement function calling support (functionDeclarations, functionResponse) - Add functionCall SSE parsing and empty stream retry support - Add generationConfig (temperature, maxOutputTokens) - Add thinkingConfig for Gemini 3 and thinking models - Add toolConfig (functionCallingConfig.mode) - Fix .expect() panics with .ok_or_else() - Restrict oauth credentials file permissions to 0600 - Update docs and FEATURE_PARITY.md - Update wizard to current Gemini 3.1 and 2.5 models * fix: address code review issues in gemini-cli OAuth integration - Add cache_read_input_tokens/cache_creation_input_tokens fields (value 0) - Implement manual Debug for OAuthCredential to redact tokens - Fix hardcoded /tmp: use GeminiOauthConfig::default_credentials_path() - Replace emoji output with plain text markers - Propagate Client::builder() errors instead of silent fallback - Use tokio::fs for all file I/O in CredentialManager (was std::fs) - Use if let Some(ref pid) to avoid consuming credential.project_id - Extract uses_cloud_code_api() helper; route by major version (gemini-2+) - Concatenate multiple system messages into systemInstruction - Include functionCall parts in assistant message conversion - Add 401 retry loop with allow_retry flag for auth failures - Remove biased from tokio::select! in OAuth callback handler - Remove hardcoded context_length 1M; vary by model family - Change GOOG_API_CLIENT from Node.js spoof to gl-rust/1.0.0 - Implement list_models() with static model list - Move create_gemini_oauth_provider() before test module (clippy) - Fix 9 additional clippy warnings (collapsible_if, map_or, needless_borrow) - Run cargo fmt * Add dedicated regression tests for Gemini OAuth fixes * style: fix formatting in Gemini OAuth regression tests * feat(gemini-oauth): implement code review v3 refinements - Add force_refresh() for 401 retry (bypass timestamp check) - Standardize Gemini model list across docs, wizard, and provider - Restore gemini-3 check for thinkingConfig - Redact sensitive tokens in GoogleTokenRefreshResponse Debug output - Use dynamic version for GOOG_API_CLIENT - Improve model_metadata() context length heuristics - Use strip_prefix("data:") for safer SSE parsing - Skip re-auth in wizard if keeping existing provider * feat(gemini_oauth): full Cloud Code API integration with project discovery - Register gemini_oauth as a dedicated backend in config/llm.rs (skip registry fallback, preserve backend name, suppress unknown-backend warning) - Fix app.rs credential guard to exclude backends with dedicated configs (gemini_oauth, bedrock) from the provider.is_none() check - Auto-discover Cloud Code project_id via loadCodeAssist when credentials lack it (e.g. created by the original Gemini CLI) - Persist discovered project_id to credentials file for subsequent runs - Add safety settings (BLOCK_NONE), gated behind GEMINI_SAFETY_BLOCK_NONE env - Add thinkingConfig: budget-based for Gemini 2.5, level-based for Gemini 3.x (without includeThoughts to avoid empty responses from reasoning.rs stripping) - Add thought signature injection for Gemini 3.x preview APIs - Add history curation to filter invalid model outputs before re-sending - Add extended generationConfig env vars (topP, topK, seed, penalties, responseMimeType, responseJsonSchema, cachedContent) - Add custom headers support via GEMINI_CLI_CUSTOM_HEADERS - Add API key auth mode (GEMINI_API_KEY + GEMINI_API_KEY_AUTH_MECHANISM) - Add SSE metadata extraction (modelVersion, credits, promptFeedback, groundingMetadata, citationMetadata, cachedContentTokenCount) - Add countTokens API support - Add new models to wizard (gemini-3.1-pro-preview-customtools, gemini-3-pro-preview, gemini-3.1-flash-lite-preview) - Update docs/LLM_PROVIDERS.md with new models and routing rules - Rewrite regression tests with comprehensive coverage (23 unit tests pass) * fix: CI violations — add safety comment on expect, fix fmt - Add '// safety: hardcoded literal' to regex .expect() to satisfy the no-panic-in-prod CI check - Fix cargo fmt whitespace in collapsible if-let chain * fix: address PR review feedback from gemini-code-assist - Fix parse_custom_headers to preserve commas in values by splitting only on commas followed by a header-name:colon pattern (manual scan instead of simple split(',')) - Use matches! macro for backend exclusion check in app.rs - Merge SSE metadata extraction into single pass (was iterating twice) - Replace fragile substring-based context_length with explicit match on known Gemini model IDs via gemini_context_length() - Add missing models to regression test (8 models, not 5) * fix: address Copilot PR review feedback - Fix empty text part for assistant messages with tool calls (curate_contents could drop entire model turn) - Propagate cache_read/creation_input_tokens in complete_with_tools - Log warning on save_credential failure instead of silently ignoring - Fix doc comment to mention underscore in header name pattern - Handle gemini-oauth (hyphen variant) in setup wizard display - Fix docs: thinkingConfig uses thinkingBudget/thinkingLevel, not includeThoughts * fix: add missing allow_always field after staging merge * fix(gemini_oauth): align header parser doc with implementation [skip-regression-check] Update parse_custom_headers doc comments to include underscore in the header-name character class, matching the actual implementation. Also fix formatting from merge. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(gemini_oauth): curate_contents per-part filtering and dead code removal Fix curate_contents to filter invalid parts individually instead of dropping entire model turn sequences. Previously a single empty text part would discard all consecutive model turns including valid functionCall parts, breaking the tool-call flow. Also remove unused MID_STREAM_* constants. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style(gemini_oauth): rustfmt formatting [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(llm): support smart routing cheap model for gemini_oauth backend Add explicit gemini_oauth handling in create_cheap_provider_for_backend() to create a GeminiOauthProvider with the cheap model swapped in. Without this, setting LLM_CHEAP_MODEL with gemini_oauth backend would fail with a confusing "no registry provider config available" error. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * docs: add Gemini OAuth env vars to .env.example [skip-regression-check] Document GEMINI_MODEL, GEMINI_CREDENTIALS_PATH, GEMINI_API_KEY, and all extended generation config env vars in the example config file. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: [email protected] <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-21 22:41:44 -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	ccdea40e9d	feat(agent): queue and merge messages during active turns (#1412) ... * feat(agent): queue and merge messages during active turns Replace the hard rejection ("Turn in progress") when messages arrive during an active turn with a bounded queue (max 10) that auto-drains after the turn completes. Queued messages are merged with newlines into a single turn so the LLM receives full context from rapid consecutive inputs instead of producing fragmented responses from partial context. Key changes: - Thread.pending_messages (VecDeque) with queue_message/drain_pending_messages - Drain loop in agent_loop.rs merges all queued messages per iteration - interrupt() and /clear both clear the pending queue - MAX_PENDING_MESSAGES constant with cap enforced inside queue_message() - Drain loop continues on soft errors, stops on NeedApproval/Interrupted - Drain loop logs respond() failures instead of silently swallowing them Fixes #259 — debounces rapid inbound messages during processing Fixes #826 — drain loop is bounded by MAX_PENDING_MESSAGES cap Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — drain loop busy-loop guard and stale state re-check - Add Ok(SubmissionResult::Ok) to drain loop break conditions to prevent a tight busy-loop if process_user_input returns a queued-ack (e.g. from a corrupted/hydrated session stuck in Processing state) - Re-check thread.state under the mutable lock in the Processing arm to guard against the turn completing between the snapshot read and the queue operation Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: clear attachments on drain-loop queued message processing Queued messages are text-only (queued as strings during Processing state). The drain loop was reusing the original IncomingMessage reference which carried the first message's attachments, causing augment_with_attachments to incorrectly re-apply them to unrelated queued text. Clone the message with cleared attachments for drain-loop turns. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review round 2 — stale state fallthrough and thread-not-found guard - Processing arm: when re-checked state is no longer Processing, fall through to normal processing instead of dropping user input - Processing arm: return error when thread not found instead of false "queued" ack - Document intermediate drain-loop responses as best-effort for one-shot channels (HttpChannel) - Add regression tests for both edge cases Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review feedback for message queue drain loop [skip-regression-check] — test modifications present but hook has SIGPIPE/pipefail false negative when awk exits early on match - Replace wildcard match in drain loop with explicit `while let Ok(Response)` guard — stops on Error variant too, preventing confusing interleaved output after soft errors (review issue #1) - Reject queueing messages with attachments during Processing state instead of silently dropping them (review issue #2) - Document response routing limitation: all drain-loop responses route via original message identity (review issue #3) - Document why SubmissionResult::Ok is correct for queued ack and how it interacts with drain loop break condition (review issue #4) - Rewrite two dead regression tests to assert actual behavior: thread-gone returns error, state-changed does not queue (review #5) - Document MAX_PENDING_MESSAGES=10 as acceptable for personal assistant use case (review issue #6) - Fix misleading one-shot channel comment — HttpChannel consumes sender on first call, subsequent calls are dropped (review issue #8) - Simplify drain loop intermediate response since while-let guard guarantees Response variant Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add missing extension_manager field in webhook EngineContext The fire_webhook method's EngineContext initializer was missing the extension_manager field added in staging, causing CI compilation failure. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: gate TestRig::session_manager() behind libsql feature flag The field is #[cfg(feature = "libsql")] so the accessor must match. All callers are already inside #[cfg(feature = "libsql")] blocks. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: re-queue drained messages on drain loop failure If process_user_input fails after drain_pending_messages() removed all queued content, that user input was permanently lost. Now the merged content is re-queued at the front of pending_messages on any non-Response result so it will be processed on the next successful turn. Adds Thread::requeue_drained() helper and unit test. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: remove unreachable!() from drain loop, add lock-drop comments - Extract content binding in `while let` pattern instead of using a separate match with unreachable!() — satisfies the no-panic-in- production convention (zmanian review item #1) - Add comment clarifying session lock is dropped at Processing arm boundary before fall-through (zmanian review item #5) - Document bounded cap overshoot on requeue_drained (review item #2) [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(security): validate queued messages and touch updated_at on queue ops - Run safety validation, policy checks, and secret scanning on messages before queueing during Processing state. Previously, content with leaked secrets could be stored in pending_messages and serialized without hitting the inbound scanner. - Touch updated_at in queue_message(), drain_pending_messages(), and requeue_drained() so thread timestamps reflect queue activity. [skip-regression-check] — safety validation requires full Agent; updated_at is a data-level fix on existing tested methods 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 21:53:14 -07:00
3 people	89394ebd29	feat(cli): add ironclaw hooks list subcommand (#1023) ... Part of #83 Static discovery of lifecycle hooks from bundled (audit_log) and plugin (WASM *.capabilities.json sidecar) sources. Supports --verbose and --json output. Workspace hooks (DB-stored) noted but omitted without DB connection. [skip-regression-check] Co-authored-by: [email protected] <[email protected]>	2026-03-21 21:08:13 -07:00
Illia PolosukhinandGitHub	0e5837b83a	Merge pull request #1013 from rajulbhatnagar/fix/musl-installer-targets ... fix: add musl targets for Linux installer fallback	2026-03-21 21:06:32 -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
Illia PolosukhinandGitHub	189fc031e3	Merge branch 'staging' into fix/musl-installer-targets	2026-03-21 15:50:34 -07:00
5 people	b97d82dbe6	feat(extensions): support text setup fields in web configure modal (#496) ... * feat(extensions): support text setup fields in web configure modal * fix(extensions): use exported wasm setup schema types * fix(extensions): validate extension name in setup APIs * fix(extensions): restrict setup setting_path writes * refactor(web): use enum for setup field input type * fix: restore registry versions reverted during merge [skip-regression-check] The merge auto-resolved registry JSON conflicts in favor of the PR's older 0.2.0 versions. Restore discord, github, and web-search to 0.2.1 from staging. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: 您的GitHub用户名 <[email protected]> Co-authored-by: [email protected] <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-21 15:10:09 -07:00
3 people	9d538136b5	fix(oauth): reject malformed ic2.* states in decode_hosted_oauth_state (#1441) (#1454) ... * fix(oauth): reject malformed ic2.* states instead of falling through to legacy handler (#1441) When decode_hosted_oauth_state() encountered a versioned state (ic2.*) that failed to fully parse (bad base64, invalid JSON, missing separator), it silently fell through to legacy handling which used the full malformed envelope as the flow_id. This never matched the raw nonce stored in pending_oauth_flows, breaking the OAuth callback. Restructure the versioned decode path so any ic2.* state must parse as a valid envelope or return Err — never fall through to legacy handling. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(oauth): address PR review — avoid alloc in strip_prefix, strengthen JSON parse test - Replace `strip_prefix(&format!(...))` with a `HOSTED_STATE_PREFIX_DOT` constant to avoid per-call allocation. - Fix "valid base64 but not JSON" test to compute the correct checksum so it actually exercises the JSON parse error path instead of stopping at the checksum check. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add missing fallback_deliverable field in job_monitor tests The SseEvent::JobResult struct gained a fallback_deliverable field in the structured fallback deliverables feature, but the job_monitor test constructors were not updated. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(oauth): remove HOSTED_STATE_PREFIX_DOT to avoid drift with HOSTED_STATE_PREFIX concat! requires literals and cannot reference const items, so a separate _DOT constant would duplicate the prefix string. Revert to deriving the dotted prefix via format!() — both encode and decode now use the same single HOSTED_STATE_PREFIX constant, keeping them mechanically consistent. 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 14:39:52 -07:00
5 people	8ad7d78a70	fix: parameter coercion and validation for oneOf/anyOf/allOf schemas (#1397) ... * fix: parameter coercion and validation for oneOf/anyOf/allOf schemas WASM extension tools with multi-action schemas (e.g. github extension) fail when the LLM passes numeric parameters as strings because the coercion layer skips JSON Schema combinators. This causes serde deserialization errors like `invalid type: string "100", expected u32`. Add discriminated-union resolution to the coercion layer: for oneOf/anyOf, match the active variant by const or single-element enum discriminators; for allOf, merge all variants' properties. Also propagate combinator awareness to schema validators, WASM wrapper helpers, and tool discovery so they no longer reject or ignore valid combinator-based schemas. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * test: add e2e tests for oneOf discriminated union parameter coercion Add three end-to-end tests using a fixture tool that mirrors the github WASM tool's oneOf schema with #[serde(tag = "action")] deserialization. Each test sends string-typed numeric/boolean params through the full agent loop, verifying that coercion resolves them before serde runs: - list_issues: limit "100" → 100 (integer in oneOf variant) - get_issue: issue_number "42" → 42 (integer in different variant) - create_pull_request: draft "true" → true (boolean in variant) Without the coercion fix these fail with: invalid type: string "100", expected u32 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * test: add real WASM github tool e2e tests with HTTP interception Load the actual compiled github WASM binary, send params with string-typed numbers through the coercion layer, and verify the WASM tool constructs correct HTTP API calls via a new HTTP interceptor in the WASM wrapper. Changes: - Add `http_interceptor` field to `StoreData` and `WasmToolWrapper` so WASM tool HTTP requests can be captured/mocked in tests - Make `prepare_tool_params` and `coercion` module public for integration tests - Add 3 e2e tests loading the real github WASM binary: - list_issues: `limit: "50"` → URL contains `per_page=50` - get_issue: `issue_number: "42"` → URL contains `/issues/42` - list_pull_requests: `limit: "25"` → URL contains `per_page=25` Tests gracefully skip if the WASM binary isn't compiled. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: simplify WASM e2e tests to use TestRig with with_wasm_tool() Replace the manual WasmToolWrapper construction with TestRig integration: - Add `with_wasm_tool(name, wasm_path, capabilities_path)` to TestRigBuilder that loads real WASM binaries and wires the shared HTTP interceptor - Build the HTTP interceptor before tool registration so it can be shared between AgentDeps and WASM tool wrappers - Rewrite github WASM e2e tests to use the standard trace pattern: TraceLlm sends tool calls with string params, http_exchanges specify expected outgoing requests and canned responses The test code is now identical to other trace-based e2e tests — no custom interceptors or manual WASM construction needed. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments on combinator schema support - Validate `has_combinators` checks array type (`.as_array().is_some()`) instead of bare `.is_some()` to reject malformed `{ "oneOf": {} }` - Validate top-level `required` keys against merged combinator variant properties when no top-level `properties` exists (both validators) - Deduplicate oneOf/anyOf handling into single loop in coercion.rs - Revert `pub mod coercion` to private; only re-export `prepare_tool_params` - Call `after_response` on interceptor after real HTTP when `before_request` returns None (recording mode correctness) - Fix formatting (CI failure) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address second round of review comments - Fix headers deserialization bug: deserialize resp.headers_json as HashMap<String, String> then convert to Vec, not directly as Vec - Sort interceptor headers for deterministic trace fixtures - Update after_response comment: RecordingHttpInterceptor does exercise this path (returns None from before_request) - Mark WASM tests #[ignore] instead of silent skip — avoids false-green CI while keeping them runnable with --ignored - Fix with_wasm_tool signature: Option<PathBuf> instead of Option<impl Into<PathBuf>> which doesn't compile in nested position - Fix with_wasm_tool doc comment to match actual behavior - Revert prepare_tool_params to pub(crate) — no longer needed publicly Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: coerce empty strings to null for optional tool parameters LLMs often send "" instead of null/omitting optional parameters, causing parse errors in tools that expect typed values (e.g., timezone, schedule). PR #1127 fixed this per-field in the time tool. This commit adds dispatcher-level coercion so all tools benefit: - Non-required properties with value "" are coerced to null at the object level (based on the schema's `required` array) - Explicitly nullable schemas (`type: ["string", "null"]`) coerce "" to null in the per-value coercion path - Required string-only fields keep "" unchanged Closes #755 Co-Authored-By: spiritj <[email protected]> Co-Authored-By: Xing Ji <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat: complete coercion coverage for $ref, nested combinators, and additionalProperties Close remaining coercion gaps so 3rd-party tools (MCP servers, complex WASM tools) work correctly: - $ref resolution: inline all #/definitions/<name> and #/$defs/<name> references in a pre-pass before coercion, with depth limit (16) for circular ref safety - Nested combinators: resolve_effective_properties now recurses into variants that themselves contain allOf/oneOf/anyOf (depth limit 4) - additionalProperties inheritance: check allOf variants and matched oneOf/anyOf variant for additionalProperties schemas New tests: - resolves_ref_and_coerces_referenced_properties - resolves_nested_refs_in_oneof_variants - coerces_nested_combinators_allof_containing_oneof - coerces_array_items_with_oneof_discriminator - circular_ref_does_not_infinite_loop Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address third round of review comments - Validators: tighten has_combinators to require at least one object-typed variant (has type:"object" or properties), rejecting non-object combinator schemas like { "oneOf": [{"type":"integer"}] } - Empty-string coercion: only coerce "" → null when schema allows null or doesn't allow string; pure type:"string" fields keep "" as meaningful - Fix comment: "coerce to null" → "return unchanged" for empty strings with no type match (code returns None, not null) - Redact credentials before passing to after_response interceptor to prevent secret leakage into recorded trace files - Switch to tokio::fs::read for async WASM binary loading in test rig - Add doc comment explaining soft URL check in WASM e2e tests Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * ci: retrigger after staging merge [skip-regression-check] * fix: merge staging, report non-array combinator values as errors Merge latest staging to fix CI (missing fallback_deliverable field). Add explicit error reporting when oneOf/anyOf/allOf values are not arrays in both strict and lenient validators. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: recurse into combinator variants that have properties but no explicit type Both validators only recursed into variants with `type: "object"`, missing variants that define `properties` without an explicit type (common in allOf patterns). Now recurse when variant has either. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: spiritj <[email protected]> Co-authored-by: Xing Ji <[email protected]>	2026-03-21 12:41:46 -07:00
6 people	6232609080	feat(llm): add GitHub Copilot as LLM provider (#1512) ... * Add github copilot as LLM provider. * Fix Copilot in Openclaw * security: harden Copilot OAuth token handling C1: Use secrecy::SecretString for oauth_token and cached session token in CopilotTokenManager/CachedCopilotToken. Expose only at HTTP header injection point via .expose_secret(). C2: Document risks of hardcoded VS Code OAuth client ID and editor identity headers (ToS, rotation, staleness). Remove the unreliable paste-token setup path (setup_github_copilot_manual_token). C3: Fix TOCTOU race in get_token() — re-check token validity after acquiring write lock so concurrent callers don't all perform redundant token exchanges. I1: Remove dead empty else {} block in get_token(). I2: Map 401 responses to LlmError::AuthFailed instead of RequestFailed so retry/circuit-breaker logic handles auth failures correctly. I3: Replace prepare_github_copilot_setup() with call to existing set_llm_backend_preserving_model() helper to avoid logic drift. I4: Add unit tests for CopilotTokenManager (caching, invalidation, expiry/buffer behavior), poll response parsing (all OAuth device flow states), and DeviceCodeResponse/CopilotTokenResponse deserialization. Co-authored-by: Copilot <[email protected]> * fix: address review feedback and code improvements (takeover #1202) - Fix ContentPart::Text being silently dropped in convert_messages - Replace custom truncate_for_error with crate::util::floor_char_boundary - Fix CLAUDE.md: accurately describe dedicated provider (not "OpenAI-compatible path") - Fix "Github" -> "GitHub" capitalization in READMEs - Add manual token paste option to setup wizard (not just device login) - Fix missing extension_manager field in EngineContext (merge fixup) - cargo fmt applied Co-Authored-By: fallenwood <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review feedback for GitHub Copilot provider - Plumb request_timeout_secs into GithubCopilotProvider (was hardcoded 120s) - Forward stop_sequences to Copilot API via OpenAI `stop` field - Skip empty text part in multimodal message conversion - Improve paste-token wizard hint with specific file path guidance Co-Authored-By: fallenwood <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: 401 retry, retryable token exchange errors, shared retry-after parsing - Retry once inline on 401 after token invalidation (was returning AuthFailed immediately, guaranteeing user-visible failure) - Map token exchange failures to RequestFailed (retryable) instead of AuthFailed (non-retryable by RetryProvider) - Use shared crate::llm::retry::parse_retry_after for HTTP-date support and safe 60s default - Improve paste-token wizard hint: mention `gh auth token` as primary source Co-Authored-By: fallenwood <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: 401 retry error mapping, retry status logging, token whitespace safety - Map 401 retry get_token() failure to RequestFailed (retryable), consistent with initial token acquisition path - Log retry response status before returning AuthFailed - Trim oauth_token in exchange_copilot_token to prevent header panics from whitespace in env vars Co-Authored-By: fallenwood <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Fallenwood <[email protected]> Co-authored-by: Copilot <[email protected]> Co-authored-by: fallenwood <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-21 00:02:00 -07:00
3 people	1d6f7d5085	fix: persist startup-loaded MCP clients in ExtensionManager (#1509) ... * fix: persist startup-loaded MCP clients in ExtensionManager MCP servers loaded at startup had their tools registered in the ToolRegistry but the client references were dropped. This caused the ExtensionManager to report them as disconnected and broke reconnection/session management. Collect startup MCP clients from the JoinSet and inject them into the ExtensionManager via a new inject_mcp_client() method. Also fix missing extension_manager field in fire_webhook EngineContext. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — pub(crate) visibility and JoinError diagnostics - Narrow inject_mcp_client to pub(crate) and guard against empty names - Distinguish panic vs cancellation in MCP task JoinError logging [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * merge: sync with staging, fix duplicate extension_manager field [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: validate extension name in inject_mcp_client Add validate_extension_name() check to reject path traversal characters in MCP client names, consistent with other entry points. [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]>	2026-03-20 23:57:19 -07:00
4 people	9964d5dab8	feat(web-search): include thumbnail URLs in search results (#1313) ... Brave's API returns thumbnail objects on many web results, but the WASM tool was silently dropping them during deserialization. This adds the thumbnail.src field to the output so downstream consumers (chat UIs, agents) can render product images and rich previews. Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: Illia Polosukhin <[email protected]>	2026-03-20 22:16:13 -07:00
4 people	212d661e20	feat(workspace): layered memory with sensitivity-based privacy redirect (#1112) ... * feat(workspace): layered memory with sensitivity-based privacy redirect Introduce MemoryLayer type for named memory layers with sensitivity levels and write permissions. Layers map to synthetic user_id values in workspace tables, enabling shared/private memory isolation. - Add MemoryLayer, LayerSensitivity types with default_for_user() - Add layer-aware write methods (write_to_layer, append_to_layer) - Add PatternPrivacyClassifier to guard shared layer writes - Add optional 'layer' parameter to memory_write tool and HTTP API - Add 'redirected' and 'actual_layer' fields to write response - Add MEMORY_LAYERS env var (JSON) for layer configuration - Workspace user_id now derived from GATEWAY_USER_ID (was hardcoded "default") - 10 integration tests for layered memory operations Addresses prerequisite for Issue #59 (multi-tenancy). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: add explicit default to memory_write layer schema Add "default": "private" to the layer parameter's JSON schema so LLM tool consumers can see the default without reading code. Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: extract resolve_layer_target to deduplicate layer writes Consolidate shared layer-lookup, writable check, and privacy classification logic from write_to_layer and append_to_layer into a single resolve_layer_target helper. Flagged on #349 review — the duplication originates in this PR. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review feedback on layered memory PR - Fix email regex pipe bug in TLD character class (privacy.rs) - Add append support to web memory_write handler via `append` field - Validate MemoryLayer name/scope: reject empty, check duplicates - Remove hardcoded 'private' default from tool schema; omit layer fields from output when no layer specified - Document scope isolation risk for multi-tenant (Issue #59) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address adversarial review findings - CRITICAL: fix identity file protection bypass via trailing slash (normalize target path before protection checks) - HIGH: check private layer is writable before privacy redirect - HIGH: map LayerNotFound/ReadOnly to proper 4xx HTTP status codes - HIGH: honor `append` field in non-layer HTTP write path - MEDIUM: remove redundant DB fetch in append_to_layer (narrower TOCTOU window) - MEDIUM: remove dead memory_write_handler from handlers/memory.rs Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: opt-in privacy classifier, force override, confidence scoring Address review feedback from @zmanian: - Privacy classifier is now opt-in via with_privacy_classifier() instead of always-on. Default hardcoded patterns (doctor, therapy, email, phone) had unacceptable false positive rates in household contexts. LLM chooses the correct layer via system prompt; regex can't improve on that. - Add ConfigurablePrivacyClassifier for operator-supplied patterns. - PatternPrivacyClassifier defaults narrowed to hard PII only (SSN, credit card, credentials). - Add force param to write_to_layer/append_to_layer to skip classifier. - PrivacyClassifier trait returns SensitivityResult { is_sensitive, confidence } instead of bool, ready for probabilistic classifiers. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: remove redundant heartbeat match arm in memory_write The heartbeat arm was identical to the catch-all — resolved_path already points to paths::HEARTBEAT when target is "heartbeat". Addresses review feedback from gemini-code-assist on #1112. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: return Result from PatternPrivacyClassifier::new() Replace .expect() with proper error propagation per project no-panics policy. Remove Default impl (unused in production). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: move memory_layers from GatewayConfig to WorkspaceConfig Resolve merge conflicts between HEAD (transcription, search, env helpers) and the workspace config branch. GatewayConfig no longer owns memory_layers; WorkspaceConfig::resolve() handles parsing, validation (name length >64, character set, empty scope, duplicates), and fallback defaults. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * test: strengthen privacy classifier and layer isolation coverage Add 8 privacy classifier edge case tests (format variants, keywords, longer documents, empty/partial inputs) and 5 layer write isolation integration tests (cross-scope invisibility, overwrite, empty path, sensitive-to-private no-redirect). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: tautological test assertion and add WorkspaceConfig validation tests Replace always-true `is_ok() || is_err()` in write_empty_path_to_layer with actual behavior assertion (write succeeds with normalized empty path). Add 8 unit tests for WorkspaceConfig::resolve() covering valid JSON parsing, invalid JSON, empty/long/invalid-char layer names, empty scopes, duplicates, and default fallback behavior. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt after staging merge Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: [email protected] <[email protected]>	2026-03-20 22:15:29 -07:00
[email protected]andClaude Opus 4.6	0d1a5c210b	fix(deps): patch rustls-webpki vulnerability (RUSTSEC-2026-0049) ... Update rustls-webpki 0.103.9 → 0.103.10. Exempt 0.102.8 which is pinned by libsql's transitive dependency on an older rustls chain. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 20:44:13 -07:00
NigeandGitHub	e6277a399f	perf(safety): single-pass escape_xml_attr (#1028) ... * perf(safety): make XML attribute escaping single-pass * test(safety): annotate assertion for no-panics CI * test(safety): inline no-panics suppression comment	2026-03-20 20:33:09 -07:00
[email protected]andClaude Opus 4.6	a4f6cda5c9	fix(routines): add missing extension_manager field in trigger_manual EngineContext ... The EngineContext construction in trigger_manual was missing the extension_manager field, causing compilation failure on libsql-only builds (Windows CI). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 20:31:22 -07:00
3 people	c6d4abdb31	fix(ci): serialize env-mutating OAuth wildcard tests with ENV_MUTEX (#1280) (#1468) ... Replace `unwrap_or_else(|e| e.into_inner())` with `expect("env mutex poisoned")` in bind_rejects_wildcard_ipv4 and bind_rejects_wildcard_ipv6 tests to match the ENV_MUTEX pattern used in oauth_defaults.rs. The old pattern silently recovered from a poisoned mutex, potentially allowing concurrent env var access when a prior test panicked while holding the lock. [skip-regression-check] Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 20:30:56 -07:00
3 people	47ba486990	docs: Expand AGENTS.md with coding agents guidance (#1392) ... * Expand AGENTS.md with repo guidance for coding agents * Format AGENTS deeper docs as a multiline list * Move scoping guidance to change-discipline section * 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]> --------- Co-authored-by: Copilot Autofix powered by AI <[email protected]>	2026-03-20 20:29:27 -07:00
4 people	6d847c6009	feat(webhooks): add public webhook trigger endpoint for routines (#736) ... * feat(webhooks): add public webhook trigger endpoint for routines Add POST /api/webhooks/{path} endpoint that matches incoming webhooks against routines with Trigger::Webhook, validates secrets using constant-time comparison (subtle crate), and fires the matched routine through the message pipeline. Closes #651 Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(webhooks): address PR review feedback - access control, targeted query, rate limiting [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(ci): add missing webhook_rate_limiter field and fix formatting Add the webhook_rate_limiter field to the GatewayState initializer in gateway_workflow_harness.rs and fix rustfmt formatting for the webhook tuple in types.rs. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(security): require webhook secret, add rate limiting, improve tests Extract validate_webhook_secret() from the handler so the security-critical secret validation logic (mandatory secret, constant-time comparison) is directly testable without mocking the database layer. Improves the error message for misconfigured routines to guide users toward the fix. Replaces the previous unit tests (which only tested Rust pattern matching and status code constants) with tests that exercise the actual validation function against all rejection paths: missing secret (403), non-webhook trigger (403), wrong secret (401), empty secret (401), and different-length secret (401). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * Route webhook triggers through RoutineEngine instead of chat pipeline Adds fire_webhook() to RoutineEngine and updates the webhook handler to use it. This ensures webhook-triggered routines get proper run tracking, guardrail enforcement (cooldown + max_concurrent), notifications, and FullJob dispatch support. Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: fix formatting in webhook handler 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]>	2026-03-20 15:50:31 -07:00
3 people	9603fefd01	fix(setup): remove redundant LLM config and API keys from bootstrap .env (#1448) ... * fix(setup): remove redundant LLM vars and API keys from bootstrap .env Only true chicken-and-egg vars belong in ~/.ironclaw/.env — things needed to connect to the DB or decrypt secrets (DATABASE_BACKEND, DATABASE_URL, LIBSQL_PATH, SECRETS_MASTER_KEY, ONBOARD_COMPLETED). LLM settings (LLM_BACKEND, LLM_BASE_URL, OLLAMA_BASE_URL, model name, provider-specific URLs) are persisted to the DB via persist_settings() and loaded by Config::from_db_with_toml() after connection. API keys are stored encrypted in the secrets DB and injected via inject_llm_keys_from_secrets(). Writing them as plaintext to .env was redundant and a security regression. Also fixes for_model_discovery() and build_nearai_model_fetch_config() to use env_or_override() instead of std::env::var(), so they can read NEARAI_API_KEY from the thread-safe overlay during the onboarding wizard (where inject_single_var() sets the key after the user enters it). Also fixes incorrect secret names in README (anthropic_api_key → llm_anthropic_api_key, openai_api_key → llm_openai_api_key). Supersedes #266 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add missing fallback_deliverable field to job_monitor tests Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * docs: address review comments on bootstrap .env and README - Update write_bootstrap_env() docstring to reflect current behavior (no LLM vars, no credentials) - Fix Layer 1 .env examples in README to remove LLM_BACKEND/LLM_BASE_URL - Fix legacy secret name in README example (anthropic_api_key → llm_anthropic_api_key) - Document channel/sandbox vars in bootstrap vars list - Add cleanup comment in test explaining empty-value-as-unset behavior Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 14:07:19 -07:00
Henry ParkandGitHub	d3b69e7be3	Fix CI approval flows and stale fixtures (#1478) ... * Fix CI approval flows and stale fixtures * Backfill approval thread mapping across channels	2026-03-20 12:21:46 -07:00
Henry ParkandGitHub	ee6f5cd62a	Use live owner tool scope for autonomous routines and jobs (#1453) ... * Use live owner tool scope for autonomous runs * Address autonomous tool scope review feedback * Normalize routine context paths again	2026-03-20 10:12:32 -07:00
4 people	3da9810e87	feat(llm): Add OpenAI Codex (ChatGPT subscription) as LLM provider (#1461) ... * feat(llm): add OpenAI Codex backend config and OAuth session manager Add OpenAiCodex as a new LLM backend variant with config for auth endpoint, API base URL, client ID, and session persistence path. The session manager implements OpenAI's device code auth flow (headless-friendly, no browser required on the server) with automatic token refresh, following the same persistence pattern as the existing NEAR AI session manager. Closes #742 Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(llm): add Responses API client and token-refreshing decorator Native Responses API client for chatgpt.com/backend-api/codex/responses, the endpoint that works with ChatGPT subscription tokens. Handles SSE streaming, text completions, and tool call round-trips. Token-refreshing decorator wraps the provider to pre-emptively refresh OAuth tokens before API calls and retry once on auth failures. Reports zero cost since billing is through subscription. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(llm): wire OpenAI Codex into provider factory, CLI, and setup wizard Connect the new provider to the LLM factory, add openai_codex to the CLI --backend flag, and add it as an option in the onboarding wizard. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(llm): address PR #744 review feedback (20 items) Review fixes for the OpenAI Codex provider PR: - Remove dead `generate_pkce()` code (device flow gets PKCE from server) - Fix `refresh_tokens()` to use `.form()` instead of `.json()` per OAuth spec - Inline codex dispatch into `build_provider_chain()` (single async function, no separate `assemble_provider_chain()` helper — matches main's pattern) - Remove Clone from `OpenAiCodexSession`, restrict fields to `pub(crate)` - Propagate HTTP client builder error instead of silent fallback - Redact device code response body from debug log - Change `set_model()` in TokenRefreshingProvider to delegate to inner - Replace hardcoded `/tmp/` test path with `tempfile::tempdir()` - Accept `request_timeout_secs` from config instead of hardcoded 300s - Parse `Retry-After` header on 429 responses (matches nearai_chat.rs pattern) - Reuse `normalize_schema_strict()` for Codex tool definitions - Add warning log for dropped image attachments - Add doc comments on `list_models()` and `include` field - Add `OPENAI_CODEX_API_URL` to `.env.example` - Fix codex error message in `create_llm_provider()` for clarity - Revert unrelated `.worktrees` addition to `.gitignore` - Update `src/llm/CLAUDE.md` with Codex provider docs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review feedback and harden OpenAI Codex provider (takeover #744) Security: - Add SSRF validation (validate_base_url) on OPENAI_CODEX_AUTH_URL and OPENAI_CODEX_API_URL, matching the pattern used by all other base URL configs (regression test for #1103 included) Correctness: - Add missing cache_write_multiplier() and cache_read_discount() trait delegation in TokenRefreshingProvider - Cap device-code polling backoff at 60s to prevent unbounded interval growth on repeated 429 responses - Default expires_in to 3600s when server returns 0, preventing immediately-expired sessions - Fix pre-existing SseEvent::JobResult missing fallback_deliverable field in job_monitor.rs tests Cleanup: - Extract duplicated make_test_jwt() and test_codex_config() into shared codex_test_helpers module Co-Authored-By: Sanjeev-S <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review feedback on OpenAI Codex provider (#1461) - Login command now resolves OPENAI_CODEX_* env overrides even when LLM_BACKEND isn't set to openai_codex (Copilot review) - Setup wizard "Keep current provider?" for codex no longer re-triggers device code login — mirrors Bedrock's keep-and-return pattern (Copilot) - Revert provider init log from info back to debug (Copilot) - Add warning log when token expires_in=0, before defaulting to 3600s (Gemini review) Co-Authored-By: Sanjeev-S <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Sanjeev Suresh <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-20 08:14:20 -07:00
4 people	cba1bc3799	feat(web): add light theme with dark/light/system toggle (#1457) ... * feat(web): add light theme with dark/light/system toggle (#761) Add three-state theme toggle (dark → light → system) to the Web Gateway: - Extract 101 hardcoded CSS colors into 30+ CSS custom properties - Add [data-theme='light'] overrides for all variables - Add theme toggle button in tab-bar (moon/sun/monitor icons) - Theme persists via localStorage, defaults to 'system' - System mode follows OS prefers-color-scheme in real-time - FOUC prevention via inline script in <head> - Delayed CSS transition to avoid flash on initial load - Pure CSS icon switching via data-theme-mode attribute Closes #761 * fix: address review feedback and code improvements (takeover #853) - Fix dark-mode readability bug: .stepper-step.failed and .image-preview-remove used --text-on-accent (#09090b) on var(--danger) background, making text unreadable. Changed to --text-on-danger (#fff). - Restore hover visual feedback on .image-preview-remove:hover using filter: brightness(1.2) instead of redundant var(--danger). - Use const/let instead of var in theme-init.js for consistency with app.js (per gemini-code-assist review feedback). Co-Authored-By: CPU-216 <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address CI failures and Copilot review feedback (takeover #853) - Fix missing `fallback_deliverable` field in job_monitor test constructors (pre-existing staging issue surfaced by merge) - Validate localStorage theme value against whitelist in both theme-init.js and app.js to prevent broken state from invalid values - Add matchMedia addEventListener fallback for older Safari/WebKit - Add i18n keys for theme tooltip and aria-live announcement strings (en + zh-CN) to match existing localization patterns - Move .sr-only utility from inline <style> to style.css [skip-regression-check] Co-Authored-By: CPU-216 <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Gao Zheng <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 00:45:17 -07:00
5 people	1b97ef4feb	fix: resolve wasm broadcast merge conflicts with staging (#395) (#1460) ... * channels/wasm: implement telegram broadcast path for message tool * channels/wasm: tighten telegram broadcast contract and tests * fix: resolve merge conflicts with staging for wasm broadcast - Remove duplicate broadcast() impls from WasmChannel and SharedWasmChannel (staging already has the generic call_on_broadcast path) - Remove obsolete telegram-specific test helpers and tests that tested the old telegram-only broadcast logic - Add test_broadcast_delegates_to_call_on_broadcast for the generic path - Fix missing fallback_deliverable field in job_monitor test SseEvents Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: davidpty <[email protected]> Co-authored-by: firat.sertgoz <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-20 00:41:20 -07:00
4 people	c17626160c	fix: skip credential validation for Bedrock backend (#1011) ... Bedrock uses IAM credentials (instance roles, env vars, SSO) resolved by the AWS SDK at call time, so `provider` is never set during startup. Exclude it from the post-init validation that checks for missing API keys. Closes #1009 Co-authored-by: brajul <[email protected]> Co-authored-by: Illia Polosukhin <[email protected]>	2026-03-19 23:25:03 -07:00
3 people	e82f4bd2e5	fix: register sandbox jobs in ContextManager for query tool visibility (#1426) ... * fix: register sandbox jobs in ContextManager for query tool visibility Sandbox jobs created via execute_sandbox() were persisted to the database but never registered in the in-memory ContextManager. Since all query tools (list_jobs, job_status, job_events, cancel_job) only search the ContextManager, sandbox jobs were invisible to the agent despite running successfully in Docker containers. Changes: - Add register_sandbox_job() to ContextManager (pre-determined UUID, starts InProgress, respects max_jobs) - Extract insert_context() helper to deduplicate create_job_for_user and register_sandbox_job - Add update_context_state / update_context_state_async to sync ContextManager state on sandbox job completion/failure - Extend job_monitor with spawn_job_monitor_with_context() and spawn_completion_watcher() so fire-and-forget jobs transition out of InProgress when the container finishes - Make CancelJobTool sandbox-aware (stops container + updates DB) - Wire sandbox deps into CancelJobTool in register_job_tools() - 8 regression tests across context manager and job monitor Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add missing allow_always field in PendingApproval test literal Upstream commit 09e1c97 added the allow_always field to PendingApproval but missed updating the test struct literal, breaking compilation. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 23:22:34 -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	ef3d769742	fix(security): validate embedding base URLs to prevent SSRF (#1221) ... * fix(security): validate embedding base URLs to prevent SSRF (#1103) User-configurable base URLs (OLLAMA_BASE_URL, EMBEDDING_BASE_URL) were passed directly to reqwest with no validation, allowing SSRF attacks against cloud metadata endpoints, internal services, or file:// URIs. Adds validate_base_url() that rejects: - Non-HTTP(S) schemes (file://, ftp://) - HTTP to non-localhost destinations (prevents credential leakage) - HTTPS to private/loopback/link-local/metadata IPs (169.254.169.254, 10.x, 192.168.x, 172.16-31.x, CGN 100.64/10) - IPv4-mapped IPv6 bypass attempts Validation runs at config resolution time so bad URLs fail at startup. Closes #1103 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(security): add DNS resolution check, ULA blocking, and NEARAI_BASE_URL validation Address review feedback: - Resolve hostnames to IPs and check all resolved addresses against the blocklist (prevents DNS-based SSRF bypass where attacker uses a domain pointing to 169.254.169.254) - Add IPv6 Unique Local Address (fc00::/7) to the blocklist - Validate NEARAI_BASE_URL in llm config (was missing — especially dangerous since bearer tokens are forwarded to the configured URL) - Allow DNS resolution failure gracefully (don't block startup when DNS is temporarily unavailable) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fix formatting Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(security): add SSRF validation to all base URL chokepoints - Add validate_base_url() in resolve_registry_provider() covering all LLM providers (OpenAI, Anthropic, Ollama, openai_compatible, etc.) - Add validate_base_url() for NEARAI_AUTH_URL in LlmConfig::resolve() - Add validate_base_url() for TRANSCRIPTION_BASE_URL in TranscriptionConfig - Add missing SSRF test cases: CGN range, IPv4-mapped IPv6, ULA IPv6, URLs with credentials, empty/invalid URLs 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]> * ci: trigger new run with skip-regression-check label Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(security): validate embedding base URLs to prevent SSRF (#1103) User-configurable base URLs (OLLAMA_BASE_URL, EMBEDDING_BASE_URL) were passed directly to reqwest with no validation, allowing SSRF attacks against cloud metadata endpoints, internal services, or file:// URIs. Adds validate_base_url() that rejects: - Non-HTTP(S) schemes (file://, ftp://) - HTTP to non-localhost destinations (prevents credential leakage) - HTTPS to private/loopback/link-local/metadata IPs (169.254.169.254, 10.x, 192.168.x, 172.16-31.x, CGN 100.64/10) - IPv4-mapped IPv6 bypass attempts Validation runs at config resolution time so bad URLs fail at startup. Closes #1103 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(security): add DNS resolution check, ULA blocking, and NEARAI_BASE_URL validation Address review feedback: - Resolve hostnames to IPs and check all resolved addresses against the blocklist (prevents DNS-based SSRF bypass where attacker uses a domain pointing to 169.254.169.254) - Add IPv6 Unique Local Address (fc00::/7) to the blocklist - Validate NEARAI_BASE_URL in llm config (was missing — especially dangerous since bearer tokens are forwarded to the configured URL) - Allow DNS resolution failure gracefully (don't block startup when DNS is temporarily unavailable) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fix formatting Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(security): add SSRF validation to all base URL chokepoints - Add validate_base_url() in resolve_registry_provider() covering all LLM providers (OpenAI, Anthropic, Ollama, openai_compatible, etc.) - Add validate_base_url() for NEARAI_AUTH_URL in LlmConfig::resolve() - Add validate_base_url() for TRANSCRIPTION_BASE_URL in TranscriptionConfig - Add missing SSRF test cases: CGN range, IPv4-mapped IPv6, ULA IPv6, URLs with credentials, empty/invalid URLs 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]> * ci: trigger new run with skip-regression-check label 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]>	2026-03-19 22:52:33 -07:00
4 people	31c3b5b041	feat(agent): activate stuck_threshold for time-based stuck job detection (#1234) ... * feat(agent): activate stuck_threshold for time-based stuck job detection (#1223) The stuck_threshold field on DefaultSelfRepair was defined but never used (marked #[allow(dead_code)]). Jobs that got stuck in InProgress without transitioning to Stuck state (e.g., deadlock, unhandled timeout) were never detected by self-repair. Changes: - Add find_stuck_jobs_with_threshold() to ContextManager that detects InProgress jobs running longer than the threshold - Wire stuck_threshold into detect_stuck_jobs() so it uses threshold-based detection alongside explicit Stuck state detection - Remove dead_code annotation from stuck_threshold - Accept InProgress jobs in the stuck job detection filter Configurable via AGENT_STUCK_THRESHOLD_SECS (default: 300s). Closes #1223 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(agent): address PR #1234 review feedback for stuck_threshold - Transition InProgress jobs to Stuck before returning them from detect_stuck_jobs(), so attempt_recovery() (which requires Stuck state) works correctly on threshold-detected jobs - Add detect-and-repair E2E test covering the full InProgress -> Stuck -> recovery -> InProgress cycle - Rename idle_threshold -> elapsed_threshold in find_stuck_jobs_with_threshold for clarity - Add `use std::time::Duration` import and remove fully qualified paths - Update CLAUDE.md to reflect that stuck_threshold is now actively used Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: measure stuck_duration from Stuck transition, handle InProgress→Stuck in repair - Fix stuck_duration computation to use the most recent Stuck transition timestamp instead of started_at, preventing jobs that ran for hours before becoming stuck from immediately exceeding the threshold - Fix last_activity to also use the Stuck transition timestamp - Transition InProgress jobs to Stuck before calling attempt_recovery() in repair_stuck_job(), since attempt_recovery() requires JobState::Stuck - Add regression test verifying a recently-stuck job with old started_at is not misdetected as exceeding a 5-minute threshold Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(agent): address Copilot review comments on PR #1234 - Add comment in find_stuck_jobs_with_threshold() noting that started_at is not reset on Stuck->InProgress recovery, which may cause false positives for recovered jobs. Suggests tracking in_progress_since or using the most recent StateTransition as a future improvement. - Fix misleading test comment in stuck_duration_measured_from_stuck_transition test: explicitly Stuck jobs are always returned regardless of threshold. The test verifies stuck_duration is near-zero, not that the job is excluded. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]> Co-authored-by: [email protected] <[email protected]>	2026-03-19 22:36:34 -07:00
4 people	806d402876	feat: chat onboarding and routine advisor (#927) ... * feat: port NPA psychographic profiling system into IronClaw Port the complete psychographic profiling system from NPA into IronClaw, including enriched profile schema, conversational onboarding, profile evolution, and three-tier prompt augmentation. Personal onboarding moved from wizard Step 9 to first assistant interaction per maintainer feedback — the First Contact system prompt block now instructs the LLM to conduct a natural onboarding conversation that builds the psychographic profile via memory_write. Changes: - Enrich profile.rs with 5 new structs, 9-dimension analysis framework, custom deserializers for backward compatibility, and rendering methods - Add conversational onboarding engine with one-step-removed questioning technique, personality framework, and confidence-scored profile generation - Add profile evolution with confidence gating, analysis metadata tracking, and weekly update routine - Replace thin interaction style injection with three-tier system gated on confidence > 0.6 and profile recency - Replace wizard Step 9 with First Contact system prompt block that drives conversational onboarding during the user's first interaction - Add autonomy progression to SOUL.md seed and personality framework to AGENTS.md seed Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat: replace chat-based onboarding with bootstrap greeting and workspace seeds Remove the interactive onboarding_chat.rs engine in favor of a simpler bootstrap flow: fresh workspaces get a proactive LLM greeting that naturally profiles the user. Identity files are now seeded from src/workspace/seeds/ instead of being hardcoded. Also removes the identity-file write protection (seeds are now managed), adds routine advisor integration, and includes an e2e trace for bootstrap greeting. Co-Authored-By: Claude Opus 4.6 <[email protected]> * feat(safety): sanitize identity file writes via Sanitizer to prevent prompt injection Identity files (SOUL.md, AGENTS.md, USER.md, IDENTITY.md) are injected into every system prompt. Rather than hard-blocking writes (which broke onboarding), scan content through the existing Sanitizer and reject writes with High/Critical severity injection patterns. Medium/Low warnings are logged but allowed. Also clarifies AGENTS.md identity file roles (USER.md = user info, IDENTITY.md = agent identity) and adds IDENTITY.md setup as an explicit bootstrap step. Co-Authored-By: Claude Opus 4.6 <[email protected]> * docs: update profile_onboarding_completed comment to reflect current wiring The field is now actively used by the agent loop to suppress BOOTSTRAP.md injection — remove the stale "not yet wired" TODO. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(setup): use env_or_override for NEARAI_API_KEY in model fetch config When the user authenticates via NEAR AI Cloud API key (option 4), api_key_login() stores the key via set_runtime_env(). But build_nearai_model_fetch_config() was using std::env::var() which doesn't check the runtime overlay — so model listing fell back to session-token auth and re-triggered the interactive NEAR AI authentication menu. Switch to env_or_override() which checks both real env vars and the runtime overlay. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(agent): correct channel/user_id in bootstrap greeting persist call persist_assistant_response was called with channel="default", user_id="system" but the assistant thread was created via get_or_create_assistant_conversation("default", "gateway") which owns the conversation as user_id="default", channel="gateway". The mismatch caused ensure_writable_conversation to reject the write with: WARN Rejected write for unavailable thread id user=system channel=default [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(web): remove all inline event handlers for CSP compliance The Content-Security-Policy header (added in f48fe95) blocks inline JS via script-src 'self'. All onclick/onchange attributes in index.html are replaced with getElementById().addEventListener() calls. Dynamic inline handlers in app.js (jobs, routines, memory breadcrumb, code blocks, TEE report) are replaced with data-action attributes and a single delegated click handler on document. [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(agent): align bootstrap message user/channel and update fixture schema field - Bootstrap IncomingMessage now uses ("default", "gateway") consistently with persist and session registration calls - Update bootstrap_greeting.json fixture: schema_version → version to match current PROFILE_JSON_SCHEMA [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(safety): address PR review — expand injection scanning and harden profile sync - BOOTSTRAP.md: fix target "profile" → "context/profile.json" so the write hits the correct path and triggers profile sync - IDENTITY_FILES: add context/assistant-directives.md to the scanned set since it is also injected into the system prompt - sync_profile_documents(): scan derived USER.md and assistant-directives content through Sanitizer before writing, rejecting High/Critical injection patterns - profile_evolution_prompt(): wrap recent_messages_summary in <user_data> delimiters with untrusted-data instruction to mitigate indirect prompt injection - routine-advisor skill: update cron examples from 6-field to standard 5-field format for consistency with routine_create tool docs [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * style: cargo fmt [skip-regression-check] Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix(setup): detect env-provided LLM keys during quick-mode onboarding Quick-mode wizard now checks LLM_BACKEND, NEARAI_API_KEY, ANTHROPIC_API_KEY, and OPENAI_API_KEY env vars to pre-populate the provider setting, so users aren't re-prompted for credentials they already supplied. Also teaches setup_nearai() to recognize NEARAI_API_KEY from env (previously only checked session tokens). Includes web UI cleanup (remove duplicate event listeners) and e2e test response count adjustment. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(test): update routine_create_list to expect 7-field normalized cron The cron normalizer now always expands to 7-field format, so the stored schedule is "0 0 9 * * * *" not "0 0 9 * * *". [skip-regression-check] Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * feat(setup): skip LLM provider prompts when NEARAI_API_KEY is present In quick mode, if NEARAI_API_KEY is set in the environment and the backend was auto-detected as nearai, skip the interactive inference provider and model selection steps. The API key is persisted to the secrets store and a default model is set automatically. Also simplify the static fallback model list for nearai to a single default entry. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: unify default model, static bootstrap greeting, and web UI cleanup - Add DEFAULT_MODEL const and default_models() fallback list in llm/nearai_chat.rs; use from config, wizard, and .env.example so the default model is defined in one place - Restore multi-model fallback list in setup wizard (was reduced to 1) - Move BOOTSTRAP_GREETING to module-level const (out of run() body) - Replace LLM-based bootstrap with static greeting (persist to DB before channels start, then broadcast — eliminates startup LLM call and race) - Fix double env::var read for NEARAI_API_KEY in quick setup path - Move thread sidebar buttons into threads-section-header (web UI) - Remove orphaned .thread-sidebar-header CSS and fix double blank line - Update bootstrap e2e test for static greeting (no LLM trace needed) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(safety): move prompt injection scanning into Workspace write/append Addresses PR #927 review comments (#1, #3) — identity file write protection and unsanitized profile fields in system prompt. Instead of scanning at the tool layer (memory.rs) or the sync layer (sync_profile_documents), injection scanning now lives in Workspace::write() and Workspace::append() for all files that are injected into the system prompt. This ensures every code path that writes to these files is protected, including future ones. - Add SYSTEM_PROMPT_FILES const and reject_if_injected() in workspace - Add WorkspaceError::InjectionRejected variant - Add map_write_err() in memory.rs to convert InjectionRejected to ToolError::NotAuthorized - Remove redundant IDENTITY_FILES/Sanitizer from memory.rs - Remove redundant sanitizer calls from sync_profile_documents() - Move sanitization tests to workspace::tests - Existing integration test (test_memory_write_rejects_injection) continues to pass through the new path Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — merge marker order, orphan thread, stale fixture - merge_profile_section: search for END marker after BEGIN position to avoid matching a stray END earlier in the file - Bootstrap phase 2: use get_or_create_session + Thread::with_id instead of resolve_thread(None) to avoid creating an orphan thread - setup_nearai: use env_or_override for NEARAI_API_KEY consistency with runtime overlay - Delete orphaned bootstrap_greeting.json fixture (no test references it) - Add test_merge_end_marker_must_follow_begin regression test Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fmt agent_loop.rs (CI stable rustfmt) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: lazy-init sanitizer, check profile non-empty before skipping bootstrap Address Copilot review: - Use LazyLock<Sanitizer> to avoid rebuilding Aho-Corasick + regexes on every workspace write - has_profile check now requires non-empty content, not just file existence, to prevent empty profile.json from suppressing onboarding - Add seed_tests integration tests (libsql-backed) verifying: - Empty profile.json does not suppress BOOTSTRAP.md seeding - Non-empty profile.json correctly suppresses bootstrap for upgrades Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: duplicate language handler, empty LLM_BACKEND, test_rig style Address Copilot review on PR #927: - Remove duplicate language-option click listeners (delegated data-action handler already covers them) - Guard LLM_BACKEND env prefill against empty string to prevent suppressing API-key-based auto-detection - Use destructured local `keep_bootstrap` instead of `self.keep_bootstrap` in test_rig for consistency after destructure Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: update stale BOOTSTRAP.md write-protection comment [skip-regression-check] BOOTSTRAP.md is now in SYSTEM_PROMPT_FILES and gets injection scanning on write. The old comment incorrectly stated it was not write-protected. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: replace debug_assert panics with graceful error returns [skip-regression-check] debug_assert! in execute_tool_with_safety and JobContext::transition_to panicked in test builds before the graceful error path could run. Existing tests (test_cancel_job_completed, test_execute_empty_tool_name_returns_not_found) already cover these paths — they were the ones failing. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — schema label, env var check, path normalization, profile validation 1. Label ANALYSIS_FRAMEWORK and PROFILE_JSON_SCHEMA sections separately in bootstrap prompt so the LLM knows which blob is the target structure. 2. Wizard quick-mode backend auto-detection now rejects empty env vars (std::env::var().is_ok_and(|v| !v.is_empty())) to avoid selecting the wrong backend when e.g. NEARAI_API_KEY="" is set. 3. Normalize the target path before comparing with paths::PROFILE in memory_write so non-canonical variants like "context//profile.json" still trigger profile sync. 4. seed_if_empty now requires valid JSON parse of context/profile.json before treating it as a populated profile. Corrupted content no longer permanently suppresses bootstrap seeding. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: cargo fmt * fix: address Copilot review — append scan, profile validation, env_or_override 1. Workspace::append() now scans the combined content (existing + new) for prompt injection, not just the appended chunk. Prevents split- injection evasion across multiple appends. 2. seed_if_empty() now deserializes into PsychographicProfile instead of serde_json::Value for profile validation. Stray/legacy JSON that doesn't match the expected schema no longer suppresses bootstrap. 3. Wizard quick-mode backend auto-detection now uses env_or_override() to honor runtime overlays and injected secrets. LLM_BACKEND value is trimmed before storage. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * test: add bootstrap_onboarding_clears_bootstrap E2E trace test Exercises the full onboarding flow end-to-end: 1. Bootstrap greeting fires automatically on fresh workspace 2. User converses for 3 turns (name, tools, work style) 3. Agent writes psychographic profile to context/profile.json 4. Profile sync generates USER.md and assistant-directives.md 5. Agent writes IDENTITY.md (chosen persona) 6. Agent clears BOOTSTRAP.md via memory_write(target: "bootstrap") Verifies: - BOOTSTRAP.md is non-empty before onboarding, empty after - bootstrap_completed flag is set - Profile contains expected user data (name, profession, interests) - USER.md contains profile-derived content (name, tone, profession) - Assistant-directives.md references user and communication style - IDENTITY.md contains agent's chosen persona name - All memory_write calls succeed Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address Copilot review — slash collapse, env_or_override, cron trim [skip-regression-check] 1. memory.rs path normalization now uses the same char-by-char loop as Workspace::normalize_path() to fully collapse consecutive slashes (e.g. "context///profile.json" → "context/profile.json"). 2. Quick-mode NEARAI_API_KEY check (line 239) now uses env_or_override() consistently with the backend auto-detection block above it. 3. normalize_cron_expression() trims input before field counting so the passthrough branch (7+ fields) also strips whitespace. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Jay Zalowitz <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-19 22:20:34 -07:00
4 people	3a523347b0	fix: f32→f64 precision artifact in temperature causes provider 400 errors (#1450) ... * fix: f32→f64 precision artifact in temperature causes provider 400 errors Direct f32-as-f64 preserves the binary representation, producing values like 0.699999988079071 instead of 0.7. Some OpenAI-compatible providers (e.g. Zhipu GLM-5) reject these with a 400 error. Add round_f32_to_f64() that formats to 6 decimal places before parsing back to f64. * fix: address clippy redundant_closure lint (takeover #1418) [skip-regression-check] Co-Authored-By: Boomboomdunce <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: use numeric rounding, update doc comment, remove duplicate assertion [skip-regression-check] Address review feedback on #1450: - Replace format!+parse with numeric rounding to avoid allocation - Update doc comment to only mention temperature (not top_p) - Remove duplicate assert_eq in test Co-Authored-By: Boomboomdunce <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Boomboomdunce <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 21:46:25 -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	8526cde1be	fix: restore libSQL vector search with dynamic dimensions (#1393) ... * fix: restore libSQL vector search with dynamic embedding dimensions (#655) The V9 migration dropped the libsql_vector_idx and changed memory_chunks.embedding from F32_BLOB(1536) to BLOB, but the documented brute-force cosine fallback was never implemented. hybrid_search silently returned empty vector results — search was FTS5-only on libSQL. Add ensure_vector_index() which dynamically creates the vector index with the correct F32_BLOB(N) dimension, inferred from EMBEDDING_DIMENSION / EMBEDDING_MODEL env vars during run_migrations(). Uses _migrations version=0 as a metadata row to track the current dimension (no-op if unchanged, rebuilds table on dimension change). Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: move safety comments above multi-line assertions for rustfmt stability Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: remove unnecessary safety comments from test code Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments from PR #1393 [skip-regression-check] - Share model→dimension mapping via config::embeddings::default_dimension_for_model() instead of duplicating the match table (zmanian, Copilot) - Add dimension bounds check (1..=65536) to prevent overflow (zmanian, Copilot) - DROP stale memory_chunks_new before CREATE to handle crashed previous attempts (zmanian, Copilot) - Use plain INSERT instead of INSERT OR IGNORE to surface constraint errors (Copilot) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: add missing builder field to AgentDeps in telegram routing test [skip-regression-check] The self-repair builder field was added to AgentDeps in #712 but this test was not updated. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address zmanian's second review on PR #1393 - Add tracing::info when resolve_embedding_dimension returns None (#2) - Document connection scoping for transaction safety (#1) - Document _rowid preservation for FTS5 consistency (#4) - Document precondition that migrations must run first (#5) - Note F32_BLOB dimension enforcement in insert_chunk (#3) - Add unit tests for resolve_embedding_dimension (#6) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 20:51:37 -07:00
3 people	8920322589	fix: staging CI triage — consolidate retry parsing, fix flaky tests, add docs (#1427) ... * fix: consolidate retry-after parsing and fix flaky OAuth env tests (#1288, #1280) - Extract shared `parse_retry_after()` into `src/llm/retry.rs` supporting both delay-seconds and RFC2822 formats, replacing duplicated inline parsing in anthropic_oauth.rs, nearai_chat.rs, and embeddings.rs - Fix flaky `bind_rejects_wildcard_*` tests in oauth_helpers.rs by adding `tokio::sync::Mutex` to serialize env var access (matching the ENV_MUTEX pattern in oauth_defaults.rs) - Add regression tests for parse_retry_after edge cases Closes #1288, #1280 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * docs: add comments explaining CLI_ENABLED=false in service templates (#990) Clarify that CLI_ENABLED=false is needed in daemon mode (launchd/systemd) to prevent blocking on stdin when running as a background service. Closes #990 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address review comments on retry-after consolidation - Change parse_retry_after() return type from Option<Duration> to Duration (it never returns None due to the 60s fallback) - Fix doc comment: reference RFC 7231 §7.1.1 for HTTP-date, not RFC 2822 - Add parse_retry_after_http_date test for the RFC 2822 date parsing branch - Remove stale per-file test helpers (parse_retry_after_*_for_test) that duplicated old inline logic instead of testing the shared function - Remove unnecessary comments above #[cfg(test)] imports - Use crate-wide ENV_MUTEX instead of local tokio::sync::Mutex in oauth_helpers tests to prevent cross-module env-var races Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: reword await_holding_lock safety comment Drop runtime-flavor assumption; justify by short-lived awaited operation. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 18:33:15 -07:00
3 people	6b0f84bbe0	perf: use Arc in embedding cache to avoid clones on miss path (#1438) ... * docs: add comments explaining CLI_ENABLED=false in service templates (#990) Clarify that CLI_ENABLED=false is needed in daemon mode (launchd/systemd) to prevent blocking on stdin when running as a background service. Closes #990 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * perf: use Arc<Vec<f32>> in embedding cache to avoid clones on miss path (#1429) Store embeddings as Arc<Vec<f32>> internally so that cache insertions share the allocation with the return value via Arc::clone instead of cloning the entire float vector (6-12 KB per embedding). - embed() miss path: Arc::try_unwrap avoids a clone when returning (the cache holds one Arc ref, the return path holds the other; try_unwrap succeeds when the thundering-herd path doesn't fire) - embed_batch() miss path: cache first via Arc::clone, then try_unwrap for results — embeddings skipped due to capacity limits are returned without any clone - Hit path still clones (trait returns Vec<f32>); a future trait change to Arc<Vec<f32>> could eliminate this too Closes #1429 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * style: fix formatting in embedding_cache.rs Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: address PR review — correct doc comment and remove dead try_unwrap - Reword CacheEntry doc comment to accurately reflect that hit/miss paths still clone into a fresh Vec<f32> for callers; Arc sharing only helps in embed_batch when embeddings are skipped from caching - Remove Arc::try_unwrap in embed() which could never succeed (cache always holds an Arc ref, so refcount >= 2) Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: revert embed() to plain Vec, keep Arc only in embed_batch() In embed(), Arc adds overhead (allocation + refcount) without saving any clones — the original pattern (clone for cache, return by move) was already optimal. Arc only helps in embed_batch() where capacity-skipped embeddings can be returned via try_unwrap. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: move clone+Arc::new outside mutex in embed() Clone the embedding and wrap in Arc before acquiring the lock so the mutex is held only for the HashMap insert, not during the O(n) copy. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: drop Arc, use cache-then-move pattern instead Arc was the wrong abstraction — the trait returns Vec<f32>, so Arc can't avoid clones on return paths. Instead: - embed(): skip clone in thundering-herd case (just touch timestamp) - embed_batch(): cache first (clone only cacheable subset), then move originals into results (zero-copy). For N misses with K cacheable: old = 2N clones, new = K clones. - CacheEntry reverted to plain Vec<f32>, no Arc overhead Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 18:33:04 -07:00
3 people	cac6f4013c	Add owner-scoped permissions for full-job routines (#1440) ... * docs: add comments explaining CLI_ENABLED=false in service templates (#990) Clarify that CLI_ENABLED=false is needed in daemon mode (launchd/systemd) to prevent blocking on stdin when running as a background service. Closes #990 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * Add owner-scoped full-job routine permissions * Address PR review feedback * Fix owner gate test timing --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 18:32:47 -07:00
Henry ParkandGitHub	c4ab382522	Make hosted OAuth and MCP auth generic (#1375) ... * Make hosted OAuth and MCP auth generic * Address PR feedback and lint issues * Suppress built-in Google secret in hosted proxy flows * Align hosted OAuth secret suppression with proxy config * Harden hosted OAuth callback helpers * Tighten hosted OAuth URL rewriting	2026-03-19 15:50:54 -07:00
3 people	65062f3cc0	feat: structured fallback deliverables for failed/stuck jobs (#236) ... * feat: structured fallback deliverables for failed/stuck jobs (#221) When a job fails or gets stuck, build a FallbackDeliverable that captures partial results, action statistics, cost, timing, and repair attempts. This replaces opaque error strings with structured data users can act on. - Add FallbackDeliverable, LastAction, ActionStats types in context/fallback.rs - Store fallback in JobContext.metadata["fallback_deliverable"] on failure - Surface fallback in job_status tool output and SSE job_result events - Update mark_failed() and mark_stuck() in worker to build fallback - 8 unit tests covering zero/mixed actions, truncation, timing, serialization Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review comments on fallback deliverables - Fix doc comment: "200 chars" -> "200 bytes (UTF-8 safe)" since truncate_str operates on byte length, not character count. - Add code comment documenting that SSE fallback_deliverable is currently always None (forward-compatible infrastructure). Co-Authored-By: Claude Opus 4.6 <[email protected]> * refactor: take Option<&FallbackDeliverable> instead of &Option<…> Addresses Gemini review feedback: idiomatic Rust prefers Option<&T> over &Option<T> for borrowed optional values. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: guard against non-object metadata and add fallback test - store_fallback_in_metadata now resets metadata to {} when it's any non-object type (string, array, number), not just null. Prevents panic on index assignment. - Add test_job_status_includes_fallback_deliverable to verify the fallback field is surfaced in job_status tool output. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: use sanitized output in fallback preview + add integration tests Security fix: FallbackDeliverable::build() now uses output_sanitized instead of output_raw, preventing secrets/PII from leaking through the job_status tool and SSE job_result events. Also adds: - test_fallback_uses_sanitized_output: proves raw secrets don't leak - test_store_fallback_in_metadata_roundtrip: full serialize/deserialize - test_store_fallback_handles_non_object_metadata: edge case coverage - test_store_fallback_none_is_noop: None input is safe Addresses serrrfirat review feedback on PR #236. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: harden fallback deliverables against review findings - Truncate failure_reason to 1000 bytes to prevent metadata bloat - Add tracing::warn on fallback serialization failure (was silently discarded) - Fix module/struct docs to cover stuck jobs, remove stale SSE claim - Fix job.rs test to use real FallbackDeliverable field names - Add tests for failure_reason truncation and completed_at=None elapsed time - Fix pre-existing clippy warning in settings.rs (field_reassign_with_default) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address Copilot review findings on fallback deliverables - Fix output_raw/output_sanitized field swap in ActionRecord::succeed() so sanitized data actually goes into the sanitized field (security) - Return None instead of empty Memory when get_memory fails in build_fallback, with tracing::warn for observability - Replace manual elapsed calculation with ctx.elapsed() which already clamps negative durations Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: resolve rebase conflicts and update tests for parameter swap - Add fallback field to SseEvent::JobResult in job_monitor - Fix type annotation in fallback deliverable test - Update test_action_record_succeed_sets_fields for new parameter order - Use create_job_for_user in test (API changed on main) Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: trigger CI re-check after rebase * fix: fall back to error message for failed action output_preview When the last action is a failed tool call, output_sanitized is None, leaving output_preview empty. Now falls back to the action's error message so users see what went wrong. [skip-regression-check] * ci: add safety comments to test code for no-panics check The CI no-panics grep check cannot distinguish test code inside src/ files from production code. Add // safety: test annotations to .unwrap(), .expect(), and assert!() calls in #[cfg(test)] modules. * fix: clarify succeed() doc and avoid clone in output_preview - Fix doc comment: output_raw is stored as pretty-printed JSON string, not a raw JSON value - Borrow string slice directly in fallback preview to avoid cloning potentially large sanitized outputs before truncation * refactor: reuse floor_char_boundary in truncate_str Replace hand-rolled UTF-8 boundary logic with existing crate::util::floor_char_boundary to reduce duplication. * fix: rename SSE fallback field to fallback_deliverable for consistency The SSE JobResult field was named `fallback` while everywhere else (metadata key, job_status tool) uses `fallback_deliverable`. Align the SSE wire format to avoid forcing clients to handle two names. --------- Co-authored-by: Claude Opus 4.6 <[email protected]>	2026-03-19 13:43:04 -07:00
5 people	86ae12747b	feat: LRU embedding cache for workspace search (#1423) ... * feat: LRU embedding cache for workspace search (#165) Add CachedEmbeddingProvider that wraps any EmbeddingProvider with an in-memory LRU cache keyed by SHA-256(model_name + text). This avoids redundant HTTP calls when the same text is embedded multiple times (common during reindexing and repeated searches). - Cache uses HashMap + last_accessed tracking with manual LRU eviction (same pattern as llm::response_cache::CachedProvider) - Lock is never held during HTTP calls to prevent blocking - embed_batch() partitions into hits/misses and only fetches misses - Default 10,000 entries (~58 MB for 1536-dim vectors) - Configurable via EMBEDDING_CACHE_SIZE env var - Workspace.with_embeddings() auto-wraps; with_embeddings_uncached() available for tests Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address review comments on embedding cache - Validate embed_batch return count matches expected miss count - Replace unwrap_or_default() with proper error propagation - Fix batch eviction: run final eviction pass after insert to enforce cap - Fix test: use different-length inputs to verify ordering correctness - Reject EMBEDDING_CACHE_SIZE=0 in config validation (minimum is 1) Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: replace .expect() with proper error handling in embed_batch The all-cache-hits early-return path used .expect("all cache hits") which violates the project convention of no .unwrap()/.expect() in production code. Replaced with the same ok_or_else pattern used in the normal path. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: clarify memory sizing docs and use saturating_add for eviction - Update memory comments in embedding_cache.rs, config/embeddings.rs, and workspace/mod.rs to note the ~58 MB figure is payload-only (actual memory is higher due to HashMap/key/allocation overhead) - Use saturating_add(1) instead of + 1 for eviction threshold to prevent overflow if max_entries is usize::MAX Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address Copilot review on embedding cache - Avoid double-clone per miss in embed_batch: move embedding into results, clone only for the cache entry - Evict per-insert instead of after all inserts to keep peak memory bounded during large batches - Clamp max_entries to at least 1 in constructor to prevent unexpected eviction behavior when set to 0 via the public API Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: reduce embedding_cache module visibility to private Types are already re-exported via `pub use`, so the module itself doesn't need to be public. Reduces unnecessary API surface. Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address serrrfirat review feedback on embedding cache - Add TODO comment for O(n) LRU eviction scalability - Add thundering herd note at lock release in embed() - Warn when cache max_entries exceeds 100k - Use with_embeddings_uncached() in integration test - Add tests: error_does_not_pollute_cache, embed_batch_empty_input - Update README with cache-aware with_embeddings() docs Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: prevent u32 wrapping in FailThenSucceedMock failure counter fetch_sub(1) wraps to u32::MAX when called past zero, silently breaking the mock for 3+ calls. Switch to load-then-store to avoid the wrapping bug in both embed() and embed_batch(). Co-Authored-By: Claude Opus 4.6 <[email protected]> * fix: address Copilot and serrrfirat review findings on embedding cache - Switch tokio::sync::Mutex to std::sync::Mutex (lock never held across .await — cheaper synchronous lock) - Extract DEFAULT_EMBEDDING_CACHE_SIZE constant to avoid 10_000 duplication between EmbeddingCacheConfig and EmbeddingsConfig Co-Authored-By: Claude Opus 4.6 <[email protected]> * test: add all-misses batch test for embedding cache Adds embed_batch_all_misses test covering the case where every text in a batch is a cache miss — fulfilling the commitment from serrrfirat's review. Co-Authored-By: Claude Opus 4.6 <[email protected]> * chore: trigger CI re-check after rebase * fix: use raw [u8;32] cache keys and pre-allocate HashMap capacity Address Copilot review findings: - cache_key() now returns [u8; 32] instead of hex String, avoiding a 64-byte allocation per lookup - HashMap::with_capacity(max_entries) avoids incremental reallocation - Fix pre-existing staging compilation error in cli/routines.rs (missing max_tool_rounds/use_tools fields) [skip-regression-check] * fix: make cache accessors sync and update doc for [u8;32] keys Address Copilot review: - len(), is_empty(), clear() are now sync since they only take a std::sync::Mutex lock with no .await points - Update cache_size doc comment to reflect [u8;32] keys instead of String keys [skip-regression-check] * fix: remove clone_on_copy for [u8; 32] cache keys [skip-regression-check] * ci: add safety comments to test code for no-panics check The CI no-panics grep check cannot distinguish test code inside src/ files from production code. Add // safety: test annotations to .unwrap(), .expect(), and assert!() calls in #[cfg(test)] modules. * fix: correct cache doc and demote hit/miss logs to trace - Fix misleading "String keys" in memory comment (cache uses [u8; 32]) - Demote per-request hit/miss logs from debug to trace to reduce noise on hot paths (batch summary stays at trace too) * docs: add missing Arc import in workspace README example * perf: batch eviction in embed_batch to avoid O(n×m) cost Replace per-insert evict_lru call with a single evict_k_oldest pass that computes eviction count upfront and removes the k oldest entries in one O(n) scan. Avoids O(n×m) HashMap iterations while holding the mutex during batch inserts. * fix: cap batch cache inserts at max_entries and use O(n) selection - evict_k_oldest now uses select_nth_unstable_by_key for O(n) average partial selection instead of O(n log n) full sort - embed_batch caps cached entries at max_entries when misses exceed capacity, preventing the cache from growing unbounded - Added test: batch_exceeding_capacity_respects_max_entries * fix: flatten test assert for fmt compatibility Shorten assert message to fit single line so cargo fmt doesn't split the safety annotation onto a separate line. * fix: address review feedback and improve embedding cache (takeover #235) - Fix merge conflict: add missing allow_always field in PendingApproval - Thread EmbeddingCacheConfig through CLI memory commands so they respect EMBEDDING_CACHE_SIZE instead of silently using default (fixes #235 review) - Cap HashMap pre-allocation at min(max_entries, 1024) to avoid upfront memory waste at large cache sizes - Fix FailThenSucceedMock race: replace load+store with atomic fetch_update - Remove noisy '// safety: test' comments (40+ lines of diff noise) - Fix collapsed lines from comment removal - Simplify redundant Ok(...collect()?) to just collect() Co-Authored-By: ztsalexey <[email protected]> Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix(embedding-cache): skip eviction on concurrent duplicate insert When the lock is released for the HTTP call, another caller may insert the same key. Re-check under lock and just update the existing entry without evicting, avoiding unnecessary cache churn under concurrency. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: ztsalexey <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]> Co-authored-by: ztsalexey <[email protected]>	2026-03-19 13:37:55 -07:00
4 people	52ca9d6588	feat: receive relay events via webhook callbacks (#1254) ... * feat: receive relay events via webhook callbacks instead of SSE Replace the SSE pull model with push-based webhook callbacks from channel-relay. Eliminates the reconnect loop, stream token auth, and SSE parser — events arrive via HTTP POST to /relay/events. - Add webhook handler with HMAC signature verification - Simplify RelayChannel to use mpsc from webhook handler - Remove SSE connect/reconnect/parse logic from RelayClient - Add register_callback() to RelayClient for callback URL registration - Update activation flow to create event channel and register callback - Wire relay webhook endpoint into web gateway * fix: address review feedback on webhook callback PR - Return 503 when relay event channel is full/closed (enables retry) - Reject malformed timestamps with 400 instead of proceeding - Allow relay activation without settings store (no-store/ephemeral mode) - Check installed_relay_extensions set in is_relay_channel for no-db mode - Fix staging test constructors for new RelayChannel signature * security: adapt relay client to new channel-relay auth model Adapts the relay integration to the hardened channel-relay security model: - Switch from X-API-Key header to Authorization: Bearer sk-agent-* for all relay API calls (chat-api token verification) - Remove register_callback() — PUT /callbacks endpoint removed - Remove event_callback_url from initiate_oauth() — parameter removed - Make signing_secret a required field in RelayConfig (new env var: CHANNEL_RELAY_SIGNING_SECRET) - Update integration tests for Bearer auth and removed endpoints Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: use server-side approval tokens, remove caller-supplied routing - Approval flow now calls POST /approvals to register server-side record, then embeds only the opaque approval_token in button value - Remove instance_id parameter from proxy_provider() — channel-relay no longer accepts it (uses verified identity) - Remove instance_id and user_id from initiate_oauth() — channel-relay derives them from the Bearer token - Add create_approval() to RelayClient Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: pass webhook_url during OAuth so callback_url is set on connection The channel-relay OAuth flow now accepts webhook_url to set the callback_url during connection creation. IronClaw computes its webhook URL from callback_base + webhook_path and passes it during initiate_oauth. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: remove webhook_url from OAuth initiation Channel-relay now derives the callback URL from chat-api's instance_url. IronClaw no longer supplies webhook_url during OAuth — the relay is the authority on where events get delivered. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * chore: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: remove all URL params from OAuth initiation IronClaw no longer supplies any URLs to channel-relay. The relay derives all URLs from the trusted instance_url in chat-api. initiate_oauth() takes no parameters. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: restore CSRF nonce for OAuth callback validation Re-add nonce generation and secret storage in auth_channel_relay. The nonce is passed to channel-relay as state_nonce param (not a URL). Channel-relay embeds it in the signed state and appends it to the redirect URL so IronClaw's callback handler can validate and activate. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: per-instance callback signing secrets relay_signing_secret() now prefers OPENCLAW_GATEWAY_TOKEN (per-instance) over the shared CHANNEL_RELAY_SIGNING_SECRET. A compromised instance can no longer forge callbacks to other instances on the same relay. CHANNEL_RELAY_SIGNING_SECRET is now optional in RelayConfig. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: clean per-instance callback secrets, no shared secrets, no fallbacks Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: pass team_id to get_signing_secret for workspace-scoped lookup Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * security: remove sender_id from create_approval — relay derives it Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: remove stale relay sender_id validation * fix: harden relay webhook activation lifecycle --------- Co-authored-by: Pierre <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 11:53:46 -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
4 people	71f41dd123	fix(feishu): parse flat token response from tenant_access_token API (#1419) ... * fix(feishu): parse flat token response from tenant_access_token API The Feishu /auth/v3/tenant_access_token/internal endpoint returns a flat JSON response with tenant_access_token and expire at the top level, not nested under a "data" field. The previous code used FeishuApiResponse<T> which expects a "data" wrapper, causing all token exchanges to fail with "Token response missing data" despite receiving a valid HTTP 200 response. - Replace TenantAccessTokenData with TenantAccessTokenResponse that includes code/msg/tenant_access_token/expire at the top level - Deserialize token response directly instead of via FeishuApiResponse<T> wrapper - Add empty-token guard to catch malformed responses - No changes to FeishuApiResponse<T> or other API call paths Fixes #1391 * fix(feishu): address review feedback on token response parsing - Remove #[serde(default)] from tenant_access_token and expire fields so deserialization fails explicitly when critical fields are missing - Add expire > 0 validation guard to prevent refresh loops or overflow - Use saturating_add/saturating_mul for expiry calculation - Add 5 regression tests for TenantAccessTokenResponse deserialization Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: reidliu <[email protected]> Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 10:33:58 -07:00
4 people	71f9012de3	fix: skip NEAR AI session check when backend is not nearai (#1413) ... * fix: skip NEAR AI session check when backend is not nearai When a user configures a non-NEAR AI backend (e.g. Anthropic), the doctor command was incorrectly failing with "session file not found" even though no NEAR AI session is needed. The check now skips with a descriptive message when LLM_BACKEND is not nearai/near_ai/near. Co-Authored-By: Claude Sonnet 4.6 <[email protected]> * fix(ci): avoid holding sync MutexGuard across await in doctor test Convert check_nearai_session_skips_for_non_nearai_backend from #[tokio::test] to #[test] with block_on, matching the pattern used by all other ENV_MUTEX tests. Fixes clippy::await_holding_lock error. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Kristian Glass <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]>	2026-03-19 10:10:08 -07:00
3 people	38dafb96b1	chore: bump telegram channel version to 0.2.5 (#1410) ... Bump registry version to pass check-version-bumps.sh after channels-src/telegram/ changes. Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 09:47:40 -07:00
CPU-216andGitHub	9c34fe90f4	chore(ci): enforce test requirement for state machine and resilience changes (#1230) (#1304)	2026-03-19 09:35:37 -07:00
3 people	07c6ca72e9	fix: navigate telegram E2E tests to channels subtab (#1408) ... * fix: navigate telegram E2E tests to channels subtab wasm_channel extensions (like telegram) are now rendered in the Settings → Channels subtab, not the Extensions subtab. Update test_telegram_hot_activation to navigate there and use the correct card selector. Also mock /api/gateway/status which loadChannelsStatus fetches. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * fix: select telegram card by name, not first card in channels subtab Built-in channel cards (Web Gateway, HTTP, etc.) render first in the channels subtab content, so .first matches them instead of the telegram extension card. Select by has_text="Telegram" to target the correct card. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> * refactor: make gateway_status_handler parameterizable in mock helper Address review feedback: extract default gateway status handler and accept an optional gateway_status_handler kwarg in mock_extension_lists for test flexibility. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-19 08:11:15 -07:00
3 people	b9e5acf66e	fix: add missing builder field and update E2E extensions tab navigation (#1400) ... - Add `builder: None` to AgentDeps initializer in e2e_telegram_message_routing test (field added in #712 but test not updated) - Update go_to_extensions() in test_telegram_hot_activation to navigate via settings tab -> extensions subtab (extensions tab was moved to settings) Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>	2026-03-18 23:38:33 -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