- Deleted tsconfig.build.json and tsconfig.check.json files that only extended the base tsconfig.json without adding configuration.
- Updated check:ts script to remove the unused packages/stats/tsconfig.client.json reference.
- Replaced vi.spyOn fetch mocking pattern with hookFetch utility across 5 test files.
- Migrated fetch mocks to use resource management with 'using' keyword for automatic cleanup.
- Removed @ts-expect-error comments related to fetch.preconnect type issues.
- Updated ts-hook-fetch rule documentation with expanded patterns and clearer lifecycle guidance.
- Fixed API key credential matching to compare by type and identity key instead of object identity.
- Fixed credential deduplication to preserve existing credentials when replacement key matches.
- Fixed auth schema version preservation by conditionally writing schema version only on initial setup.
- Added test coverage for API key reuse, email deduplication, and schema version preservation.
- Extracted fetch mocking logic into reusable `hookFetch()` utility function with middleware-style handler pattern.
- Replaced manual `globalThis.fetch` assignment and restoration across 10 test files with `hookFetch()` calls using `using` statement for automatic cleanup.
- Implemented Disposable pattern with Symbol.dispose for fetch hook resource management, eliminating try-finally blocks.
- Exported `hookFetch` from utils public API to enable consistent fetch mocking across packages.
- Added `identity_key` column to auth credentials storage for improved credential deduplication.
- Added schema versioning system to auth credentials database for safer migrations.
- Changed credential deduplication logic to use single identity key instead of multiple identifiers for better performance.
- Fixed credential deduplication to correctly handle OAuth accounts with matching emails but different account IDs.
- Implemented automatic backfilling of identity keys during database schema migrations.
- Added 5 test cases for schema migration and identity key backfilling scenarios.
- Extracted OAuth identifier logic into public functions extractOAuthCredentialIdentifiers and extractOAuthTokenIdentifiers.
- Replaced single credentialIdentity string with multi-identifier resolveCredentialIdentifiers returning string[] for flexible matching.
- Changed credential deduplication from email-based to accountId-based matching in replaceAuthCredentialsForProvider.
- Updated auth-storage tests to verify accountId-prioritized deduplication behavior across soft-disable and hard-delete scenarios.
- Added documentation comments in coding-agent modules explaining partial JSON preservation for streaming tool previews.
- Documented streaming tool preview requirements and render paths in AGENTS.md.
- Added `env` parameter to bash tool for safe environment variable passing without shell re-parsing.
- Added support for rendering partial environment variable assignments in command preview during streaming.
- Updated bash tool prompt to recommend `env` parameter for multiline, quote-heavy, and untrusted values.
- Refactored tool execution component to conditionally merge partial JSON arguments during streaming.
- Added helper functions for environment variable normalization, escaping, and formatting.
- Fixed WebSocket stream fallback logic to safely replay buffered output over SSE when WebSocket fails after partial content has been streamed.
- Added tracking flag to prevent unsafe replays of tool calls and terminal events during fallback transitions.
- Enhanced error recovery to reset output state when replaying buffered content over SSE connection.
- Added docs.rs scraper for extracting Rust crate documentation from rustdoc JSON, supporting modules, functions, structs, traits, enums, and other Rust items with intelligent caching.
- Implemented rustdoc JSON parsing with type rendering for complex Rust types including generics, lifetimes, trait bounds, and qualified paths.
- Added caching layer for rustdoc JSON with date-based versioning for 'latest' releases to reduce repeated fetches.
- Added fallback search strategies in librarian and explore agent prompts for handling empty results.
- Clarified task completion priority in system prompt by prohibiting premature tool call cessation.
- Consolidated and simplified 'Giving Up' guidance in subagent prompt with clearer uncertainty handling.
- Removed duplicate instructions and redundant phrasing to improve prompt clarity and conciseness.
- Added skipPostPromptRecoveryWait option to HandoffOptions for deferring recovery work in handoff operations.
- Added deferred auto-compaction scheduling for threshold-triggered handoffs via post-prompt task queue.
- Extracted handoff document template to dedicated system prompt file for improved maintainability and reusability.
- Changed handoff prompt generation to use template rendering with custom focus instructions support.
- Refactored prompt-in-flight tracking from boolean flag to counter for proper nested operation handling.
- Moved llms.txt endpoint discovery to fallback strategy when rendered page content is low quality, prioritizing page-specific content over site-wide files.
- Enhanced llms.txt endpoint detection to scope candidates to the requested URL path, searching section-specific files before site-wide ones.
- Replaced getOrigin() with buildLlmEndpointCandidates() to generate path-scoped endpoint candidates with depth-based fallback strategy.
- Updated tryLlmEndpoints() to accept full URL and return endpoint metadata alongside content for better fallback tracking.
- Added 2 integration tests validating section-scoped llms.txt discovery and preference for rendered content over site-wide files.
- Clarified contextual pattern mode behavior in ast-grep and ast-edit documentation to explain that results target the selected node, not the outer wrapper.
- Enhanced TypeScript pattern examples to include class method matching syntax with `class $_ { method(...) }` wrapper pattern.
- Removed redundant class method examples that were superseded by improved documentation of contextual pattern mode.
- Renamed parameter names in ast-grep and ast-edit tools from `patterns`/`selector` to `pat`/`sel` for brevity across schema, implementation, and tests.
- Expanded ast-grep and ast-edit tool documentation with 12+ new usage guidelines, examples, and critical notes on pattern syntax, metavariable placement, and error handling.
- Updated CHANGELOG.md to document parameter renames and expanded tool guidance for AST pattern syntax and metavariable usage.
- Reformatted test assertions and type annotations across ast-edit and ast-grep test files for improved readability.
- Added `glob` parameter to `ast_grep`, `ast_edit`, and `grep` tools for filtering files relative to `path`.
- Implemented `combineSearchGlobs()` utility to merge glob patterns from multiple sources instead of throwing errors.
- Changed `grep` tool to combine glob patterns when both `path` and `glob` parameters are provided.
- Updated tool documentation to recommend pairing `path`, `glob`, and `lang` for language-scoped search in mixed repositories.
- Added comprehensive test coverage for combined path and glob parameter handling across grep, ast_grep, and ast_edit tools.
- Removed space in empty catch block to match linting rules.
- Simplified ternary operator precedence in thinkingFormat assignment.
- Added missing newline at end of test file.
- Add detection for qwen models in detectCompat() via model ID check
- Set supportsDeveloperRole: false for qwen models (prevents 'developer role is not valid' error)
- Set thinkingFormat: 'qwen' for qwen models to enable correct reasoning mode
- Export detectCompat for testing
- Add comprehensive tests for qwen model detection
Fixes issue where qwen3.5 models served via ollama would fail with
'developer role is not valid' error because they don't support the
developer role in the OpenAI API.
Models affected: qwen3.5:397b-cloud, qwen2.5-coder, qwen3-coder, etc.
- Removed three @ts-expect-error comments that are no longer needed for fetch.preconnect mocking.
- The test mocks now work without requiring type suppression.
- Added automatic Ollama model capability detection via /api/show endpoint to discover reasoning and input modality support.
- Improved Kagi API error handling with structured error parsing for JSON and plain text response formats.
- Fixed Cerebras streaming compatibility by omitting stream_options.include_usage parameter.
- Simplified API key credential storage to always replace credentials instead of merging for non-minimax providers.
- Updated Kagi Search API key format from 'kagi_...' to 'KG_...' and clarified beta access requirement in provider description.
Fixes#326.
Fixes#321.
Fixes#298.
- Added checks to filter out Kitty release events (event_type 3) in both matches_key_inner and parse_key_inner functions. Added comprehensive tests for both key matching and input handling to verify release events are ignored while press and repeat events are still processed correctly.
Fixes#325
The context fullness gauge was driven by output token count, causing
erratic jumps between turns (e.g. 84% -> 64%) with no compaction.
Status bar and estimateContextTokens now use calculatePromptTokens()
which returns input + cacheRead + cacheWrite — the actual input context
size. Previously both used a formula that included the final output token
count, which fluctuates with response length and is not part of the
context window for the current request.
isContextOverflow's usage-based fallback (z.ai silent overflow) was
also missing cacheWrite (cache_creation_input_tokens). Per Anthropic
docs the threshold is input + cache_read + cache_creation — all three.
Ref: https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing
google.ts and google-vertex.ts were double-counting cached tokens.
Gemini's promptTokenCount already includes cachedContentTokenCount, so
assigning input = promptTokenCount and cacheRead = cachedContentTokenCount
overcounted by cachedContentTokenCount on every cached request. Fixed
by subtracting first, matching the OpenAI convention:
input = promptTokenCount - cachedContentTokenCount
cacheRead = cachedContentTokenCount
=> input + cacheRead = promptTokenCount (total prompt, no double-count)
Ref: https://ai.google.dev/api/generate-content#v1beta.GenerateContentResponse.UsageMetadata
All other providers validated: amazon-bedrock (inputTokens is uncached
by API contract), openai-completions/responses/azure (already subtract
cached), kimi/gitlab-duo (delegate to correct implementations), cursor
(API exposes output tokens only — input stays 0 by design).
Co-authored-by: Miroslav Drbal <miroslav.drbal@gendigital.com>
Two deviations from the actual Antigravity client protocol:
1. User-Agent was hardcoded as darwin/arm64 regardless of host platform.
Antigravity format is {os}/{arch} using windows/amd64, darwin/arm64,
linux/amd64. Map from Node.js process.platform / process.arch at
startup.
2. ANTIGRAVITY_STREAMING_HEADERS was missing X-Goog-Api-Client and
Client-Metadata. The API spec requires all three headers on every
request, not just on auth/discovery calls. Requests without them do
not match the fingerprint of a real Antigravity client.
Client-Metadata ideType is ANTIGRAVITY (not IDE_UNSPECIFIED) and
platform reflects the actual host (WINDOWS/MACOS/LINUX).
Co-authored-by: Miroslav Drbal <miroslav.drbal@gendigital.com>
* fix(ai): preserve deepseek compatibility while adding alibaba coding plan
* feat(ai): add alibaba coding plan provider with deepseek compatibility fix
* feat(ai): update contextWindow and maxTokens for alibaba coding plan models
* fix(ai): restore Anthropic OAuth exports and add Alibaba env mapping
* fix(ai): set thinkingFormat to qwen for alibaba-coding-plan provider
* fix(ai): preserve bundled limits when fetching Alibaba models
* fix(ai): correct alibaba-coding-plan model limits and reasoning flags
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
* Add PUPPETEER_PROXY and PUPPETEER_PROXY_IGNORE_CERT_ERRORS env vars
- PUPPETEER_PROXY: routes browser traffic through specified proxy
- PUPPETEER_PROXY_IGNORE_CERT_ERRORS: ignore HTTPS cert errors when set
Made-with: Cursor
* fix(browser): gate PUPPETEER_PROXY_IGNORE_CERT_ERRORS on explicit truthy parse
Previously any non-empty value (including 'false', '0') enabled
--ignore-certificate-errors, silently disabling TLS verification when
operators intended to keep it on. Now only 'true', '1', 'yes', 'on'
(case-insensitive) enable the flag.
Made-with: Cursor
- Added `disabledCause` parameter to credential deletion methods to track reason credentials are disabled.
- Changed credential disabling mechanism from boolean `disabled` flag to `disabled_cause` text field for better auditability.
- Fixed credential purging to respect disabled credentials during email deduplication operations.
- Refactored `replaceAuthCredentialsForProvider()` to update matching credentials instead of deleting all, preserving credential history.
- Added incremental history mode to OpenAI responses .
- Changed OpenAI Codex to exclusively use websockets v2 protocol with fatal error detection for automatic SSE fallback.
- Fixed Gemini model parsing to strip `-preview` suffix for consistent model identification across API calls.
- Improved websocket error handling to extract and report detailed error messages from error events.
- Removed deprecated BETA_RESPONSES_WEBSOCKETS constant and websocket v2 feature flag branching logic.
- Introduced Effort enum and ThinkingConfig metadata for per-model reasoning capabilities with min/max effort levels.
- Migrated thinking level API from string-based ThinkingLevel to structured Effort enum across agent and AI packages.
- Added model-thinking module with effort mapping, policy application, and semantic versioning utilities for provider-specific thinking modes.
- Removed supportsXhigh() function and replaced effort clamping with model-aware validation using ThinkingConfig metadata.
- Expanded models.json with thinking configuration objects for 50+ models including Claude, Gemini, and OpenAI variants.
- Added Python analysis scripts for edit tool usage patterns and tool invocation stream processing.
- Added serviceTier option to OpenAI providers for controlling processing priority and cost across agent, completions, responses, and codex APIs.
- Added providerPayload field to messages for transport-native history reconstruction in OpenAI Responses and Codex APIs.
- Added /fast slash command and serviceTier setting to coding-agent for toggling OpenAI priority mode with fast mode indicator.
- Added remote compaction support with encrypted reasoning preservation for OpenAI models in coding-agent.
- Removed usage caching layer across all providers and refactored UsageFetchContext to eliminate cache and now dependencies.
- Fixed OpenAI Codex streaming service_tier inclusion, provider retry logic with exponential backoff, and email-based credential deduplication.
* idiomatic rust fixes
* idiomatic rust fixes
* display an image if we are fetching an image
* MIME type strictness
* codex nagging me
* codex nagging
* handoff instead of compaction as context filled strategy and surfacing
* handoff instead of compaction as context filled strategy and surfacing p2
* handoff instead of compaction as context filled strategy and surfacing p3
* handoff instead of compaction as context filled strategy and surfacing p4
* handoff instead of compaction as context filled strategy and surfacing p5
* handoff instead of compaction as context filled strategy and surfacing, fixes
* failing fetch test from the fetch tool updates
* handoff focus prompt skeleton
* handoff focus prompt skeleton p2
* fetch bugs
* further codex improvements
* further codex improvements
---------
Co-authored-by: Brit <lol@no.com>
can1357