- Changed context promotion to trigger on context overflow errors instead of a configurable threshold percentage.
- Removed the contextPromotion.thresholdPercent configuration setting.
- Updated context promotion to retry immediately on the promoted model without requiring compaction.
- Refactored context promotion logic to attempt promotion before compaction in the overflow handling flow.
- Updated agent session to merge context promotion checks into the compaction method for unified overflow handling.
- Updated tests to reflect overflow-based promotion triggering instead of threshold-based promotion.
ubuntu-latest resolves to 24.04 which links against GLIBC_2.39,
producing native binaries that cannot run on Debian 12 (glibc 2.36).
Ubuntu 22.04 ships glibc 2.35, ensuring compatibility with Debian 12
and other current stable distributions.
- Added abort signal support to LSP file operations (ensureFileOpen, refreshFile) enabling cancellation of long-running file operations.
- Added abort signal propagation through LSP request handlers (definition, references, hover, symbols, rename) with $/cancelRequest notification support.
- Added shouldBypassAutocompleteOnEscape callback to custom editor allowing parent components to override escape key handling behavior.
- Changed escape key handling in custom editor to respect bypass callback, enabling global escape handling during active operations.
- Fixed LSP operations to properly handle abort signals and throw ToolAbortError when operations are cancelled, with input controller bypassing autocomplete during streaming/loading states.
- Added contextPromotionTarget model property to specify preferred fallback model when context promotion is triggered.
- Added automatic context promotion target assignment for Spark models to their base model equivalents.
- Updated Qwen model context window and max token limits for improved accuracy.
- Updated o1 model context window from 256000 to 262144 tokens and max tokens from 64000 to 65536 tokens.
- Implemented context promotion logic to use configured contextPromotionTarget when available instead of role-based model resolution.
- Added effectiveReserveTokens() function to enforce a minimum 15% context window floor for session compaction reserve calculations.
- Updated shouldCompact() to use effectiveReserveTokens() instead of raw configured reserve, ensuring more predictable compaction behavior regardless of configuration.
- Implemented file operation summary limiting to 20 files per category with indication of omitted files when exceeded.
- Added truncateFileList() helper function to limit file arrays and append ellipsis message showing omitted file count.
- Added stripFileOperationTags() helper function to remove XML file operation tags from summary strings.
- Introduced upsertFileOperations() function to merge base summary with file operations by stripping old tags and concatenating new ones.
- Refactored branch-summarization and compaction modules to use new upsertFileOperations() function instead of formatFileOperations().
- Added automatic context promotion feature that switches to larger-context models when approaching context limits.
- Added 'contextPromotion.enabled' setting to control automatic model promotion with default value of enabled.
- Added 'contextPromotion.thresholdPercent' setting to configure context usage threshold for triggering promotion with default value of 90%.
- Implemented context promotion logic in AgentSession that monitors token usage and automatically switches models when threshold is exceeded.
- Added provider session cleanup during model switches to properly handle session state transitions.
- Added comprehensive test coverage for context promotion functionality including threshold-based promotion and non-promotion scenarios.
- Added CPU variant support for x64 native addons with modern (AVX2/x86-64-v3) and baseline (x86-64-v2) variants, enabling automatic fallback when modern variants are unavailable.
- Added automatic AVX2 CPU detection on Linux, macOS, and Windows platforms to select appropriate native addon variant at runtime.
- Updated native addon filename scheme to include CPU variant suffix (e.g., pi_natives.linux-x64-modern.node) for x64 platforms.
- Updated CLI update mechanism to support downloading and installing multiple native addon variants per platform with fallback support.
- Removed fallback untagged pi_natives.node binary creation; platform and variant-tagged binaries are now required.
- Moved documentation files from packages/coding-agent/docs/ to root docs/ directory to flatten the documentation structure.
- Updated all internal documentation links to account for the new file locations, adjusting relative paths to maintain correct references across the monorepo.
- Updated README.md and issue template configuration to reference documentation at the new root docs/ location instead of packages/coding-agent/docs/.
- Added Brave web search provider with support for query, result count, and recency filtering.
- Added BRAVE_API_KEY environment variable configuration for Brave search authentication.
- Updated web search provider priority order to include Brave as second-highest priority after Exa.
- Extended recency filter support to Brave search provider alongside Perplexity.
- Implemented BraveProvider class with API integration, response mapping, and parameter validation.
- Added helper functions for recency mapping, result clamping, and snippet building in Brave provider.
- Restructured documentation from user-facing guides to technical implementation references across 18 files in packages/coding-agent/docs.
- Reorganized compaction.md, config-usage.md, custom-tools.md, and extensions.md to emphasize architecture and integration patterns over step-by-step tutorials.
- Expanded environment-variables.md, extension-loading.md, fs-scan-cache-architecture.md, and python-repl.md with detailed runtime behavior and implementation details.
- Consolidated hooks.md, rpc.md, sdk.md, and theme.md from comprehensive reference documentation to focused technical specifications.
- Refined session.md, session-tree-plan.md, skills.md, tree.md, and tui.md to clarify runtime behavior, discovery mechanisms, and technical contracts.
Patterns like `\${platform}` or `a{b}` contain braces the regex engine
rejects as malformed repetitions. The new sanitize_braces() preprocessor
escapes { and } that do not form valid quantifiers ({N}, {N,}, {N,M})
before compiling, making grep resilient to literal template strings.
- Added pagination support for fetching GitHub issue comments, allowing retrieval of all comments beyond the initial 50-comment limit.
- Added comment count display showing partial results when not all comments could be fetched (e.g., '5 of 10 comments').
- Changed GitHub issue comment fetching to use paginated API requests with 100 comments per page instead of single request with 50-comment limit.
- Extracted comment fetching logic into dedicated fetchGitHubIssueComments function for improved code organization.
- Added GitHubIssueComment interface to provide type safety for comment data structures.
- Updated SMOL_MODEL_PRIORITY to include additional model variants (gpt-5.3-spark, cerebras/zai-glm-4.7, haiku-4-5, haiku-4.5) for improved fast model discovery.
- Updated SLOW_MODEL_PRIORITY to include additional model variants (gpt-5.3-codex, gpt-5.3, gpt-5.1-codex, gpt-5.1, opus-4.6, opus-4-6, opus-4.5, opus-4-5, opus-4.1, opus-4-1) for improved comprehensive model discovery.
- Fixed system prompt to enforce tool calls on every turn until task completion, preventing premature stopping before turn finish.
- Reorganized contract and diligence sections to clarify inviolable rules and completion requirements.
- Consolidated redundant completion guidance and removed duplicate prime directive language.
- Clarified contract rule 2 to explicitly require at least one tool call per turn unless task is complete.
- Added new contract rule 3 forbidding standalone progress updates without task continuation.
- Renumbered subsequent contract rules 3-7 to 4-8 to accommodate new rule.
- Reinforced critical section guidance with same tool call requirement for turn validity.
Hashline prefixes (LINE:HASH|content) in read/grep output exist solely to
support the hashline edit mode. Agents that don't have the edit tool
(e.g. explore, plan, reviewer) gain nothing from them — they just waste
tokens and add noise.
resolveFileDisplayMode now takes a session-like object with an optional
hasEditTool flag. When false, hashlines are suppressed regardless of
settings. ToolSession gains hasEditTool (set from toolNames in the SDK),
and AgentSession exposes it as a getter over the tool registry.
- Restructured execution procedure guidance to emphasize scope assessment and continuous tool-driven progress over planning-first approach.
- Updated task tracking instructions to prohibit metadata-only turns and require immediate completion marking of todo items.
- Clarified parallel execution guidance to distinguish between genuine parallelization and sequential work, with explicit criteria for Task tool usage.
- Modified output style requirements to mandate stating intent before tool calls and reordered style constraints for clarity.
- Reinforced requirement that every turn must include at least one tool call advancing the deliverable, with explicit failure condition for planning-only turns.
- Added prime directive section emphasizing completion of requested output as primary objective.
- Changed release info fetching from GitHub API to npm registry to avoid unauthenticated rate limiting.
- Constructed deterministic GitHub release download URLs instead of relying on API response.
- Added DeepSeek-V3.2 model support via Amazon Bedrock.
- Added GLM-5 model support via OpenCode.
- Added MiniMax M2.5 model support via OpenCode.
- Updated GLM models to use anthropic-messages API instead of openai-completions and changed base URL from https://api.z.ai/api/coding/paas/v4 to https://api.z.ai/api/anthropic.
- Removed compat field with supportsDeveloperRole and thinkingFormat properties from GLM models.
- Updated pricing and context window specifications for multiple models including Mistral, Moonshot, and Qwen variants.
- Added Z.AI web search provider with MCP integration for remote web search capabilities.
- Added 'zai' as a selectable web search provider option in settings and CLI.
- Added Z.AI to the automatic provider fallback chain for web search after Gemini and Codex.
- Implemented ZaiProvider class with support for multiple Z.AI API response formats and retry logic.
- Added comprehensive error handling and response parsing for Z.AI MCP endpoint integration.
- Fixed welcome screen layout to gracefully handle small terminal widths and prevent rendering errors on narrow displays.
- Fixed welcome screen title truncation to prevent overflow when content exceeds available width.
- Improved welcome screen responsiveness to dynamically show or hide the right column based on available terminal width.
- Fixes deferred `--model` resolution to match extension-provided models before fallback
- Fixes CLI `--api-key` handling to support deferred model selection
- Adds OAuth provider support for extensions with source-scoped registration cleanup
- Adds custom API registration helpers with built-in collision checks
- Expands `Api` type to support extension-defined identifiers
- Adds tests for runtime provider registration and model selection
- Removed unnecessary blank lines in glob.rs, glob_util.rs, and grep.rs.
- Reformatted multi-line doc comment in glob_util.rs for consistency.
- Collapsed assert_eq! calls in glob_util.rs tests to single lines.
- Extracted shared glob pattern utilities into a new `glob_util` module to reduce code duplication between `glob` and `grep` modules.
- Moved `build_glob_pattern()` and `compile_glob()` functions from `glob.rs` and `grep.rs` into the centralized `glob_util` module.
- Added `try_compile_glob()` helper function to handle optional glob pattern inputs with proper error handling.
- Implemented `fix_unclosed_braces()` utility to automatically close unmatched opening braces in glob patterns, improving robustness with LLM-generated patterns.
can1357