- Downloaded config.json with tokenizer sidecars when repairing stale fastembed model caches.\n- Treated fastembed Config file missing errors as repairable initializer failures.\n- Extended cache repair coverage for the missing-config state.\n\nFixes #3054
The PR fixed the -32601 hang for the defined server->client refresh
requests but missed two real spec methods of the identical class:
workspace/inlineValue/refresh (LSP 3.17) and workspace/foldingRange/refresh.
A server emitting either still received Method not found and could stall.
Add both to the void-ack chain and extend the regression test.
- Preserved fastembed's transitive ONNX Runtime instead of forcing an ABI-mismatched runtime cache install.\n- Repaired stale fastembed model caches by downloading missing tokenizer sidecars from the matching Hugging Face model repo.\n- Added regression coverage for the runtime install plan and tokenizer sidecar repair.\n\nFixes #3054
- Implement JSON repair and strict argument validation to sanitize raw payloads and redact sensitive information from agent event logs.
- Add automatic authentication fallback for benchmark model resolution to ensure consistent performance testing across providers.
- Refactor search tool API parameters by replacing `i` with a case-sensitive `case` boolean flag for clarity.
- Update session history formatting to ensure empty objects are consistently serialized as `{}` instead of empty strings.
- Renamed the global `INTENT_FIELD` constant from `_i` to `i`.
- Updated documentation strings, type annotations, and test expectations across packages to reflect the new field name.
- Ensured consistent usage of the constant in tool schema construction and intent serialization.
- Fixed `SYSTEM.md` integration to correctly include custom-rendered sections like rules and skills.
- Consolidated system prompt validation by requiring `<skills>` tag presence instead of specific prose.
- Removed redundant system prompt math-formatting tests and orphaned task batch documentation tests.
- Replaced regex-based markdown detection with a stateful parser in `detectLiveReflowingMarkdown`.
- Correctly ignore table delimiters and mermaid markers when they appear inside fenced code blocks.
- Added tests to verify that code blocks containing markdown-like syntax do not prevent commit stability.
- Prevent object reference sharing between agent snapshots and stream events by deep-cloning tool-call arguments.
- Stabilize GFM tables and Mermaid diagrams during streaming by delaying transcript block commits until content finalization.
- Implement session resume safety to prevent crashes when working directories are missing.
- Add comprehensive test suites to verify streaming commit stability and immutable snapshot isolation.
- Shortened language in `browser.md`, `eval.md`, and `prompt.md` to improve clarity and reduce token consumption.
- Refined instructional phrasing throughout the tool documentation for better readability.
- Introduced `abortableSource` as a lighter, direct-reader async generator.
- Removed the `createAbortableStream` public API to eliminate unnecessary stream wrapper layers.
- Updated internal stream processing to use `abortableSource` for improved memory and performance.
- Optimized `snapshotAssistantMessageEvent` to accept an optional pre-computed partial snapshot.
- Eliminated redundant deep-clones of `partialMessage` during streaming updates by sharing a single immutable snapshot between the message and the event.
- Replaced O(n) `Array.shift()` calls with O(1) head-index tracking in `RawSseDebugBuffer`.
- Implemented lazy compaction to reclaim the dead-prefix memory only when the leading window grows sufficiently large.
- Added comprehensive tests to verify ordering, dropped count accuracy, and buffer limits under heavy load.
- Add `onFirstChatDispatch` hook to `CreateAgentSessionOptions` to track the boundary between session creation and the initial model request.
- Update `runSubprocess` and `TaskTool` to measure and log detailed latency metrics across the subagent lifecycle, including semaphore queue wait, setup time, and dispatch latency.
- Added weighted selection logic to bias discovery toward "[NEW]" tips.
- Updated the tip marker regex to allow trailing whitespace.
- Migrated tip selection to use the new biased distribution algorithm.
- Delay the creation of the extension context until a relevant handler is identified.
- Avoid unnecessary performance overhead for events that have no registered handlers, such as frequent streaming updates.
- Added an early return to stop event propagation if no handlers are registered for the event type.
- Updated the `agent_start` logic to return early, ensuring consistent flow control.
- Introduced a "[NEW]" marker in tip text that triggers an animated rainbow-colored tag in the welcome component.
- Implemented `renderNewTag` to calculate cyclic HSL hue offsets based on render timing.
- Updated `renderWelcomeTip` to intelligently wrap the tag at the end of the last line or on a new line to prevent layout overflow.
- Simplified system and personality prompts for improved conciseness and clarity.
- Streamlined tool instruction sets and parameter descriptions across all agent modules.
- Refactored prompt documentation in `hashline` to clarify terminology and task-specific constraints.
- Updated tool metadata in TypeScript service definitions to align with reduced documentation verbosity.
- Removed internal `cloneUnknown` and `cloneToolArguments` functions.
- Switched to `structuredCloneJSON` from shared utils for snapshotting tool call arguments.
- Refactor GLM-5.2 effort mapping to accommodate specific requirements for Z.ai, OpenRouter, and general OpenAI-compatible hosts.
- Apply host-specific logic to ensure `xhigh` UI tiers are correctly resolved to the required `max` budget for supported providers.
- Add test coverage verifying expected effort mappings across different model hosts.
- Removed the customizable `timeout` parameter from the tool schema and implementation.
- Fixed the timeout duration to 5 seconds to simplify tool usage.
- Updated documentation and error messages to advise narrowing search patterns instead of adjusting timeouts.
- Introduced a centralized `discoverAuthStorage` mechanism across packages to unify credential retrieval and configuration resolution.
- Added support for new Gemini and Moonshot model variants while updating context window and effort configuration for existing models.
- Resolved provider-specific 400 errors for OpenRouter and GLM models by refining reasoning effort mapping and retry logic.
- Standardized credential management in both the coding-agent and model catalog by migrating to the unified authentication broker.
- Update fallback selection to prefer higher effort tiers when distance is equal.
- Add test case verifying fallback from unsupported "medium" effort to "high".
- Implemented an automatic retry and fallback mechanism for invalid reasoning effort parameters in OpenAI-compatible providers.
- Created a dedicated utility module to parse error messages and resolve valid reasoning effort values dynamically.
- Integrated fallback state management into existing provider sessions to ensure persistence and request reliability.
- Verified fallback logic and retry behavior through comprehensive new integration tests.
- Consolidated redundant effort maps into a single GLM 5.2 shared map.
- Updated logic to identify GLM 5.2 models based on ID regardless of the host provider to ensure consistent API behavior and prevent request errors.
- Updated the system schema and prompt options to disable inline tool descriptors by default.
- Modified the build system prompt logic to reflect the new default fallback value.
can1357