chore: promote staging to staging-promote/71f41dd1-23309993684 (2026-03-19 19:18 UTC) by ironclaw-ci[bot] · Pull Request #1425 · nearai/ironclaw

ironclaw-ci · 2026-03-19T19:18:45Z

Auto-promotion from staging CI

Batch range: 71f41dd12363497372864bc6eb3f7c334e05fd52..52ca9d6588f31fc9b6007c56ed7cd1995d5ad0df
Promotion branch: staging-promote/52ca9d65-23312673755
Base: staging-promote/71f41dd1-23309993684
Triggered by: Staging CI batch at 2026-03-19 19:18 UTC

Commits in this batch (2):

09e1c97 fix(approval): make "always" auto-approve work for credentialed HTTP requests (fix(approval): make "always" auto-approve work for credentialed HTTP requests #1257)
52ca9d6 feat: receive relay events via webhook callbacks (feat: receive relay events via webhook callbacks #1254)

Current commits in this promotion (5)

Current base: staging-promote/71f41dd1-23309993684
Current head: staging-promote/52ca9d65-23312673755
Current range: origin/staging-promote/71f41dd1-23309993684..origin/staging-promote/52ca9d65-23312673755

09e1c97 fix(approval): make "always" auto-approve work for credentialed HTTP requests (fix(approval): make "always" auto-approve work for credentialed HTTP requests #1257)
52ca9d6 feat: receive relay events via webhook callbacks (feat: receive relay events via webhook callbacks #1254)
86ae127 feat: LRU embedding cache for workspace search (feat: LRU embedding cache for workspace search #1423)
65062f3 feat: structured fallback deliverables for failed/stuck jobs (feat: structured fallback deliverables for failed/stuck jobs #236)
c4ab382 Make hosted OAuth and MCP auth generic (Make hosted OAuth and MCP auth generic #1375)

Auto-updated by staging promotion metadata workflow

Waiting for gates:

Tests: pending
E2E: pending
Claude Code review: pending (will post comments on this PR)

Auto-created by staging-ci workflow

…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 <tbond@tbond-m5.local>

* 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) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * chore: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * 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) <noreply@anthropic.com> * security: clean per-instance callback secrets, no shared secrets, no fallbacks Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: pass team_id to get_signing_secret for workspace-scoped lookup Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * security: remove sender_id from create_approval — relay derives it Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: remove stale relay sender_id validation * fix: harden relay webhook activation lifecycle --------- Co-authored-by: Pierre <pierre@near.ai> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

claude · 2026-03-19T19:22:00Z

Code review

No issues found.

This PR implements two well-integrated changes:

Relay webhook refactoring (feat: receive relay events via webhook callbacks feat: receive relay events via webhook callbacks #1254): Cleanly transitions from SSE long-polling to webhook callbacks with proper HMAC-SHA256 signature verification, timestamp freshness validation (5-min window), and correct hex decoding + 32-byte length validation of signing secrets. The webhook handler at POST /relay/events is well-designed with proper error responses at each validation step.
Approval system enhancement (fix: make "always" auto-approve work for credentialed HTTP requests fix(approval): make "always" auto-approve work for credentialed HTTP requests #1257): Correctly changes ApprovalRequirement::Always → UnlessAutoApproved for credentialed HTTP requests, allowing the session-wide "always" setting to apply. The allow_always field is properly threaded through PendingApproval, SubmissionResult, and all approval handlers (dispatcher, thread_ops, channel), with regression tests verifying the behavior.

All code follows CLAUDE.md guidelines: no unwrap()/expect() in production code, proper error context mapping, and strong type usage. Configuration simplification removes SSE polling parameters cleanly. Test cases are comprehensive and updated appropriately.

claude · 2026-03-19T19:22:17Z

Code review - Architecture findings

Found 7 architectural improvement opportunities (non-blocking):

[MEDIUM:75] Stringly-typed approval flag logic instead of enum method
- File: src/agent/dispatcher.rs:590, src/agent/thread_ops.rs:1090
- The allow_always = !matches!(requirement, ApprovalRequirement::Always) pattern is duplicated across 3+ places. Should extract as ApprovalRequirement::allows_always() method to follow DRY principle and CLAUDE.md preference for strong types over computed booleans.
[MEDIUM:65] Optional state accessed via match/if-let chains in relay webhook handler
- File: src/channels/web/server.rs:765-820
- Multiple guard clauses return HTTP errors inline. Consider extracting a RelayCallbackError type with thiserror to centralize validation logic and make it testable.
[MEDIUM:60] Inconsistent error handling for mutex lock failures
- File: src/extensions/manager.rs:597 (relay_signing_secret_cache)
- Using lock().ok()? conflates lock failure (poison) with cache miss. Lock failure should panic/expect; cache miss is normal. Consider: self.relay_signing_secret_cache.lock().expect("lock poisoned").clone()
[MEDIUM:65] API leaks internal Arc/Mutex types
- File: src/extensions/manager.rs:578-587 (relay_event_tx getter)
- Returns Arc<tokio::sync::Mutex<Option<...>>> directly, coupling callers to internal sync strategy. Consider offering a higher-level abstraction (e.g., get_relay_event_tx() that returns sender directly).
[LOW:55] Duplicated allow_always computation
- File: src/agent/dispatcher.rs:553-591, src/agent/thread_ops.rs:1072-1099
- Same logic appears in both approval flows. Extract as helper to ensure consistency.
[LOW:50] Stringly-typed state keys without constants
- File: src/extensions/manager.rs (throughout)
- Keys like "relay:{}:team_id" and "relay:{}:oauth_state" are hard-coded. Define as module constants to prevent typos and enable refactoring.
[LOW:45] Error context not propagated in relay initialization
- File: src/extensions/manager.rs:4007-4014
- client.get_signing_secret() errors are wrapped as ExtensionError::Config without preserving the error chain. Use .map_err() to add context for better debuggability.

Non-issues: No production .unwrap()/.expect() violations. All error types use thiserror. Bearer auth strategy is consistent.

claude · 2026-03-19T19:22:37Z

Code review - Security & Safety findings

Completed security analysis. No critical vulnerabilities found.

[MEDIUM:65] Timestamp replay window for webhook callbacks

File: src/channels/web/server.rs:1854-1864
The webhook signature verification checks timestamp freshness (5-minute window) but does not implement replay protection. An attacker could capture a valid signed webhook and replay it multiple times within the window. The HMAC signature includes the timestamp, preventing trivial replay, but distributed replay within the window is theoretically possible. Recommend: Consider adding a nonce cache or sequence number tracking if high-value operations depend on webhook uniqueness.

[MEDIUM:50] Race condition window in relay event sender access

File: src/channels/web/server.rs:1886-1898
Between checking if relay channel is active and sending the event, a concurrent deactivate_relay_channel() could remove the sender. Mitigation: Code already handles this via try_send() error return and responds with 503. This is acceptable.

[LOW:40] Sensitive bytes in Arc could expose in debug panics

File: src/extensions/manager.rs:relay_signing_secret_cache
The 32-byte signing secret is stored in Arc<Mutex<Option<Vec>>>. While unlikely to be logged, consider using zeroize crate for sensitive byte arrays to prevent accidental memory exposure on panic.

[MEDIUM:50] Validation assumption on cached signing secret

File: src/extensions/manager.rs:relay_signing_secret()
The cached secret is assumed valid because it was validated by get_signing_secret() at fetch time. Since the cache is only populated by this method, invariant holds, but the assumption is implicit. Adding a comment explaining this invariant would clarify intent.

Verified Strengths:
✅ HMAC-SHA256 signature verification uses constant-time comparison (subtle::ConstantTimeEq)
✅ Bearer token auth properly used (not API keys in headers)
✅ No .unwrap()/.expect() in production webhook code
✅ Proper error handling on all validation steps

Conclusion: Webhook refactoring is well-implemented with no blocking security issues. Replay protection is a design consideration rather than a bug.

claude · 2026-03-19T19:23:02Z

Code review - Performance & Production findings

Found 6 performance/production considerations:

[HIGH:80] Synchronous mutex in async hot path

File: src/channels/web/server.rs:771 (relay_events_handler)
The webhook handler calls ext_mgr.relay_signing_secret() which uses std::sync::Mutex::lock() on every incoming event. This is a blocking synchronous lock acquired in an async context, which can block the tokio runtime under contention. Recommendation: Use Arc<tokio::sync::Mutex<_>> instead of Arc<std::sync::Mutex<_>> for relay_signing_secret_cache.

[HIGH:75] Lock contention on event sender per-request

File: src/channels/web/server.rs:831 (relay_events_handler)
Every webhook event acquires async lock on relay_event_tx via ext_mgr.relay_event_tx().lock().await. Under sustained webhook traffic, this per-request lock becomes a serialization bottleneck. Recommendation: Clone sender once at activation and store in lock-free cell (e.g., AtomicOption<Arc<Sender>>) to avoid repeated lock acquisitions.

[MEDIUM:65] Channel capacity mismatch between test and production

File: src/extensions/manager.rs:6435 (test setup vs production)
Test creates mpsc::channel(1) but production uses mpsc::channel(64). This capacity-1 test channel will cause try_send() to fail immediately under load, triggering 503 responses. Test doesn't validate the queue backpressure behavior that production encounters. Recommendation: Update test to capacity 64 to match production, or document intentional difference.

[MEDIUM:50] Unnecessary cloning of 32-byte signing secret

File: src/extensions/manager.rs (activation and verification paths)
The signing secret is cloned during cache storage (*cache = Some(signing_secret)) and again on retrieval (.clone()). While 32 bytes is small, under high webhook volume this adds allocations in the hot path. Recommendation: Use Arc<[u8; 32]> instead of Vec<u8> to eliminate allocations.

[LOW:60] Lost resilience in relay service recovery

File: src/channels/relay/channel.rs (removed ~200 lines of SSE reconnection logic)
Old SSE implementation had exponential backoff (1s→60s) and token renewal. New webhook approach has no recovery if relay service is temporarily unavailable. Webhook events fail with "event queue full" until manual restart. Recommendation: Add periodic health checks (e.g., list_connections()) to detect relay service degradation.

[LOW:40] Approval tuple repeatedly extracted for channel updates

File: src/agent/thread_ops.rs:507-527
The approval request is extracted multiple times for channel status broadcasts, causing repeated field access. Recommendation: Extract tool_name/description once and reuse.

Positive notes: No unbounded loops, missing timeouts, or resource leaks detected. Event channel sized appropriately at 64-event buffer. Bearer auth prevents token injection attacks in headers.

Summary: 2 high-priority async/concurrency improvements recommended to prevent bottlenecks under sustained webhook traffic. Remaining findings are minor optimizations.

* 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <ztsalexey@users.noreply.github.com> Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 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) <noreply@anthropic.com> --------- Co-authored-by: ztsalexey <alexthebuildr@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: ztsalexey <ztsalexey@users.noreply.github.com>

* 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com> * 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 <noreply@anthropic.com>

* 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

…4063 chore: promote staging to staging-promote/65062f3c-23317058602 (2026-03-19 23:06 UTC)

…8602 chore: promote staging to staging-promote/52ca9d65-23312673755 (2026-03-19 21:10 UTC)

nearfamiliarcow and others added 2 commits March 19, 2026 11:45

ironclaw-ci bot added the staging-promotion label Mar 19, 2026

ilblackdragon and others added 5 commits March 19, 2026 13:37

Merge pull request #1439 from nearai/staging-promote/c4ab3825-2332116…

d5e08b9

…4063 chore: promote staging to staging-promote/65062f3c-23317058602 (2026-03-19 23:06 UTC)

Merge pull request #1428 from nearai/staging-promote/65062f3c-2331705…

2326302

…8602 chore: promote staging to staging-promote/52ca9d65-23312673755 (2026-03-19 21:10 UTC)

github-actions bot added scope: channel/cli TUI / CLI channel scope: llm LLM integration scope: workspace Persistent memory / workspace scope: orchestrator Container orchestrator scope: worker Container worker scope: docs Documentation labels Mar 20, 2026

henrypark133 merged commit e031d82 into staging-promote/71f41dd1-23309993684 Mar 20, 2026
13 checks passed

henrypark133 deleted the staging-promote/52ca9d65-23312673755 branch March 20, 2026 17:11

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

chore: promote staging to staging-promote/71f41dd1-23309993684 (2026-03-19 19:18 UTC)#1425

chore: promote staging to staging-promote/71f41dd1-23309993684 (2026-03-19 19:18 UTC)#1425
henrypark133 merged 7 commits intostaging-promote/71f41dd1-23309993684from
staging-promote/52ca9d65-23312673755

ironclaw-ci bot commented Mar 19, 2026 •

edited by github-actions bot

Loading

Uh oh!

claude bot commented Mar 19, 2026

Uh oh!

claude bot commented Mar 19, 2026

Uh oh!

claude bot commented Mar 19, 2026

Uh oh!

claude bot commented Mar 19, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Conversation

ironclaw-ci bot commented Mar 19, 2026 • edited by github-actions bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Auto-promotion from staging CI

Commits in this batch (2):

Current commits in this promotion (5)

Uh oh!

claude bot commented Mar 19, 2026

Code review

Uh oh!

claude bot commented Mar 19, 2026

Code review - Architecture findings

Uh oh!

claude bot commented Mar 19, 2026

Code review - Security & Safety findings

Uh oh!

claude bot commented Mar 19, 2026

Code review - Performance & Production findings

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

ironclaw-ci bot commented Mar 19, 2026 •

edited by github-actions bot

Loading