Classifier-refusal failures end a turn with stopReason === "error" but
get pruned from the active context (agent-session.ts's
#removeAssistantMessageFromActiveContext) before agent_end fires.
sendErrorNotification() read viewSession.getLastAssistantMessage(),
which reflects that mutated context and silently missed the
notification for exactly the turns it should fire on.
Thread the agent_end event through #handleAgentEnd -> #finishAgentEnd
so sendErrorNotification reads the turn's own outcome from
agent_end.messages instead.
- Upgraded puppeteer-core to version 25.3.0 to resolve stealth patch deactivation.
- Enabled main world execution support via the `!world=main` directive for frames and element handles.
- Improved handle management by updating disposal logic to track and clear main world handles.
- Optimized web worker communication by removing redundant Runtime.enable calls.
claude-sonnet-4-5's bundled context window grew to 1M in the catalog regen, so the fixed 191k high-usage turn no longer crossed the ~85% auto-compaction threshold. The auto-continuation never fired and the three re-injection tests hung to their 5s timeout, failing the coding-agent runtime/session CI bucket and blocking the release.
Pin the harness model to a 200k window (mirrors agent-session-eager-compaction / -auto-compaction-queue), keeping the trigger stable across future catalog regenerations.
The 16.3.7 bump pulled arktype 2.2.2, which pins @ark/schema to 0.56.1. The patch was keyed to 0.56.0, so Bun silently skipped it and the arktype constraint keys reverted to hash/alphabetical order. Tool wire schemas then lost authored declaration order, failing packages/ai schema-wire tests and blocking the release pipeline.
Regenerated the patch against 0.56.1 (flattenConstraints shifted, so the old hunk offsets no longer applied) and re-pointed patchedDependencies.
- Mark demoted thinking blocks with a symbol to decouple paragraph separators from the raw text content.
- Update `openai-completions` to conditionally insert a newline only when a demoted thinking block is followed by other content.
- Ensure terminal demoted thinking blocks are trimmed to prevent trailing whitespace that causes rejection by the Anthropic API.
- Added scripts/fix-dts-extensions.test.ts to the test:scripts npm script.
- Included the .d.ts extension rewrite test in the CI workspace test suite.
- Updated repoScriptTests list in scripts/ci-test-ts.ts to ensure consistent tracking.
- Updated event controller fixture to include requestComponentRender mock.
- Added test case for resolving deferred role-alias model patterns.
- Added test case for parsing and falling back comma-delimited model patterns.
- Implemented a 2-second timeout for `workspace/didChangeWatchedFiles` notifications to prevent agent stalls during server congestion.
- Updated `runLspWritethrough` to gracefully reset notification state when the internal watchdog triggers but the primary operation remains active.
- Added explicit abort signal checks in `acp-bridge` to prevent initiation of file writes after tool cancellation.
- Refactored `notifyWorkspaceWatchedFiles` to use `AbortSignal.any` for unified signaling across timeout and caller-provided triggers.
- Added a test case to ensure brace-prefixed chunks remain with their original sibling tool call.
- Validated that parallel function call arguments are correctly routed to their respective tool call blocks.
- Enabled comma-separated string splitting within array-based model patterns.
- Expanded deferred model patterns before registration to align with immediate resolution behavior.
- Unified resolution logic to ensure deferred patterns support the same role aliases and chaining as the standard path.
- Implemented classifyJsonPrefix validation to determine when tool-call JSON chunks are complete.
- Updated delta processing logic to prevent premature chunk advancement by checking if a continuation remains valid or if it forms a distinct sibling call.
- Implemented classifyJsonPrefix to categorize buffers as complete, valid prefix, or invalid based on RFC 8259 strictness.
- Added utility to support disambiguation of identifierless streaming tool-call deltas during model response processing.
- Validated classifier logic with comprehensive suite covering nested structures, escape sequences, and strict formatting rules.
- Extracted gunzipRustdocJson() with overridable maxOutputLength so the cap contract is testable with real gzip payloads instead of the banned mock.module().
Mathews-Tom