- Added pluggable code search provider system supporting Exa and grep.app with provider selection via `providers.codeSearch` setting.
- Removed Exa-specific tools (`exa_linkedin`, `exa_company`, `exa_search_deep`, `exa_crawl`) and simplified web search tools to focus on core functionality.
- Refactored code search from Exa-only to provider-agnostic architecture with new `code_search` tool supporting context-aware grep.app queries and Exa fallback.
- Removed `exa.enableLinkedin` and `exa.enableCompany` configuration settings in favor of provider-based architecture.
- Added comprehensive test coverage for code search functionality including grep.app result normalization and provider fallback behavior.
- Added Parallel AI provider integration for web search with fast and research modes.
- Added Parallel extract API for URL content and YouTube video extraction with fallback support.
- Added /login parallel command and PARALLEL_API_KEY environment variable authentication.
- Added providers.parallelFetch configuration setting to control Parallel extract usage.
- Integrated Parallel provider into web search priority order between Exa and Kagi.
- Updated HTML-to-text and YouTube scrapers to prefer Parallel extract over fallback providers.
- Added optional `details` field to TodoItem type for storing implementation specifics, file paths, and edge cases.
- Enhanced todo item display to show multi-line details with automatic indentation in interactive and reminder modes.
- Updated eager-todo system prompt to enforce separation of short task content (5-10 words) from detailed implementation information.
- Extended TodoWriteTool to support creating and updating tasks with details field via add_task and update operations.
- Added comprehensive test coverage for details field handling across todo operations (replace, add_task, update).
* Add OAuth token refresh for MCP connections
Proactive refresh with 5-minute buffer before token expiry, plus
retry on 401/403 with automatic token refresh for HTTP transports.
Persist tokenUrl, clientId, and clientSecret in auth config so
refresh can happen without re-prompting the user.
* docs(coding-agent): updated CHANGELOG for MCP OAuth token refresh
- Added background model discovery with provider status tracking and 24-hour model caching to improve startup performance.
- Changed model discovery timeout from 3000ms to 250ms and deferred blocking refresh to background operations for faster initialization.
- Fixed model discovery to preserve cached models when providers are unavailable or unauthenticated.
- Added validation in Kitty key formatting to reject unsupported modifiers and improved error handling.
- Reorganized CI workflow to run TypeScript linting in check job and conditional Rust checks in native job matrix.
- Updated system prompt and tool guidance to recommend combined investigation-and-edit workflows and maintainable code practices.
- Added Tavily web search provider with API key authentication and credential discovery from environment or database.
- Integrated Tavily as highest-priority search provider in fallback chain with structured response mapping and error handling.
- Added Tavily OAuth login flow in CLI and auth-storage with manual API key input and validation.
- Added comprehensive test suite for Tavily provider covering registration, response mapping, error handling, and credential validation.
Fixes#313
- 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.
- 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.
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>
- 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>
- Removed static thinking mode constant exports (THINKING_LEVELS, ALL_THINKING_LEVELS, ALL_THINKING_MODES, THINKING_MODE_DESCRIPTIONS, THINKING_MODE_LABELS) in favor of dynamic function-based API.
- Renamed formatThinking() to getThinkingMetadata() with return type changed from string to structured ThinkingMetadata object containing value, label, and description.
- Renamed getAvailableThinkingLevel() to getAvailableThinkingLevels() and getAvailableThinkingEffort() to getAvailableThinkingEfforts() with added default parameters for runtime flexibility.
- Updated all consumer modules to use new function-based API instead of static constants, enabling dynamic thinking mode configuration.
- Added `read.defaultLimit` setting to configure default line count for read tool output (default 300 lines).
- Added preset options (200, 300, 500, 1000, 5000 lines) for read default limit in settings UI.
- Updated read tool to distinguish between default and maximum limits per call in prompt documentation.
- Refactored read tool limit logic to use configurable default limit with bounds validation.
- Removed complex fuzzy matching logic including Levenshtein distance calculation and similarity scoring in favor of a simpler glob-based suffix pattern approach. Replaced findReadPathSuggestions with findUniqueSuffixMatch that returns a path only when exactly one candidate matches, eliminating ambiguous suggestions. Removed legacy ttsr_trigger and ttsrTrigger fields from RuleFrontmatter interface.
- Extracted thinking module with ThinkingEffort, ThinkingLevel, and ThinkingMode types to centralize reasoning configuration across packages.
- Migrated ThinkingLevel type from pi-agent-core to pi-ai package with new validation functions parseThinkingLevel() and getAvailableThinkingLevel().
- Consolidated thinking level constants and descriptions into reusable exports (ALL_THINKING_LEVELS, THINKING_MODE_DESCRIPTIONS) for consistent UI display.
- Removed local thinking-effort-label utility and replaced formatThinkingEffortLabel() with centralized formatThinking() function from pi-ai.
- Refactored thinking mode handling to distinguish ThinkingSelector (user-facing with 'off' option) from ThinkingEffort (provider-level).
- Added formatRoleThinkingModeLabel helper to display 'inherit' for default thinking mode, preventing badge ambiguity when multiple roles share the same model. Enhanced role menu labels to include role tags for clarity. Fixed model resolver to avoid substring matching that could incorrectly resolve exact model IDs to similar variants.
- Removed await from stream() calls that return async iterables directly.
- Removed await from synchronous utility functions like findApiKey(), resolvePythonRuntime(), and getToolPath().
- Removed await from prerenderMermaid() and findExaKey() calls that don't require awaiting.
- Applied tab escaping to tool output rendering to prevent display misalignment.
- Imported replaceTabs utility and applied it consistently across 4 output rendering paths.
- Fixed URI template matching to handle empty string expansions in MCP resource queries.
- Fixed LM Studio URL validation to preserve invalid baseUrl instead of applying localhost fallback.
- Fixed MCP notification epoch handling to prevent unsubscribe calls when old subscriptions resolve after re-enabling.
- Extracted hardcoded LM Studio base URL to named constant for improved maintainability.
- Refactored notification epoch check logic for improved code clarity and readability.
- Normalize LM Studio discovery URLs to avoid duplicated /v1 segments
- Harden status-line PR cache with branch+repo context validation and guarded async writes
- Apply Foundry auth precedence correctly and preserve system trust roots when custom CA is provided
- Split Copilot premium multiplier handling by plan tier while preserving agent-initiated zero billing
- Catch MCP notification refresh failures and route read_resource via deterministic full template matching
- Add regression tests for each fix cluster and keep targeted suites green
* Add PR number segment to status bar
Add a new 'pr' status line segment that shows the GitHub PR number
(e.g., #1234) as a clickable OSC 8 hyperlink when the current branch
has an associated pull request.
- Async lookup via 'gh pr view', cached per branch
- Invalidates on branch change via .git/HEAD watcher
- Falls back to hidden segment when no PR exists or gh unavailable
- Supports all theme presets (unicode, nerd font, ascii)
- Added to all preset layouts after the git segment
* Skip PR lookup on default branch, resolve dynamically
* Extract git-utils, add tests for parseGitHubRepo and parseDefaultBranch
* Fix PR lookup race condition, invalidation churn, and dotted repo names
- Guard #cachedPr writes against branch change during in-flight lookup
- Stop clearing PR cache in invalidate() (only .git/HEAD watcher should)
- Allow dots in GitHub repo names in parseGitHubRepo regex
* Simplify PR lookup: use gh pr view, try upstream/HEAD for default branch
- Replace gh pr list --head with gh pr view (requires gh repo set-default)
- Remove manual remote URL resolution — gh handles it
- Default branch detection falls back to upstream/HEAD when origin/HEAD is unset
- Add KagiProvider implementation (Search API v0)
- Register kagi in SearchProviderId type, provider map, and fallback order
- Add kagi to tool schema enum, SearchParams type, and settings UI
- Register KAGI_API_KEY in service provider map
- Update CHANGELOG
- Added `authServerUrl` field to `AuthDetectionResult` to capture MCP OAuth server metadata.
- Added `extractMcpAuthServerUrl()` function to parse and validate `Mcp-Auth-Server` header URLs from OAuth errors.
- Enhanced `discoverOAuthEndpoints()` to accept optional `authServerUrl` parameter and query `/.well-known/oauth-protected-resource` endpoint.
- Improved OAuth metadata extraction to handle multiple `clientId` field variations (`clientId`, `default_client_id`, `public_client_id`).
- Extracted metadata parsing logic into reusable `findEndpoints()` helper function supporting multiple OAuth metadata formats.
- Added comprehensive test coverage for OAuth endpoint discovery, header parsing, and error validation.
Fixes#235
- Added `tools.maxTimeout` setting to enforce global timeout ceiling across all tool calls.
- Centralized per-tool timeout constants and clamping logic into `tool-timeouts.ts` module.
- Extracted `clampTimeout()` function to standardize timeout enforcement across bash, python, browser, ssh, and fetch tools.
* fix: use --no-optional-locks for background git status calls
Prevent index.lock contention by adding --no-optional-locks to all
git status --porcelain calls. This is the same approach VSCode uses
in its built-in git extension (GIT_OPTIONAL_LOCKS=0).
The status-line component polls git status every ~1s to show
staged/unstaged/untracked counts. Without --no-optional-locks,
each call acquires index.lock for an opportunistic index refresh,
which blocks concurrent git operations (pull, rebase, commit) run
by the user or by omp's own tool execution.
The git-status documentation explicitly recommends this:
'Scripts running status in the background should consider
using git --no-optional-locks status'
References:
- git docs: https://git-scm.com/docs/git-status (BACKGROUND REFRESH)
- git commit adding the flag: https://github.com/git/git/commit/27344d6
- VSCode's fix: GIT_OPTIONAL_LOCKS=0 in extensions/git/src/git.ts:2716
- Claude Code same issue: https://github.com/anthropics/claude-code/issues/11005
- GitExtensions same issue: https://github.com/gitextensions/gitextensions/issues/5066
- VSCode issue #31069: https://github.com/microsoft/vscode/issues/31069
* style: fix biome formatting for long lines in worktree.ts
maximhar