- Added checkpoint and rewind tools to create context checkpoints before exploratory work and rewind to replace exploration messages with concise reports.
- Added checkpoint.enabled setting to control availability of checkpoint and rewind tools in agent sessions.
- Added getCheckpointState() and setCheckpointState() methods to agent session API for checkpoint state management.
- Implemented checkpoint state tracking with message count, entry ID, and timestamp to enable context cost optimization during investigations.
- Added render_mermaid tool to convert Mermaid diagrams to ASCII output with configurable rendering options.
- Added renderMermaid.enabled setting to control availability of the render_mermaid tool.
- Changed Mermaid rendering from PNG terminal graphics to ASCII text format across theme and TUI components.
- Migrated mermaid utilities from pi-tui to pi-utils package with new ASCII rendering functions.
- Removed PNG-based mermaid rendering APIs (getMermaidImage, renderMermaidToPng) in favor of ASCII alternatives.
PendingAction.apply() and reject() now receive the reason string that was
passed to resolve(). This lets custom tools surface the agent's rationale
in their apply/discard output or use it for logging.
- PendingAction interface: apply(reason) and reject?(reason)
- CustomToolPendingAction: same signatures, reject is optional
- CustomToolLoader: threads reject through when building PendingAction
- AstEditTool: accepts _reason (unused, reserved for future tracing)
- resolve.test: covers reason forwarding on apply and reject paths,
and verifies reject return value replaces the default discard message
- docs/resolve-tool-runtime.md: updated interface table, built-in
producer description, usage example, and developer guidance
- Introduce `deferrable?: boolean` on AgentTool, CustomTool, and ToolDefinition.
AstEditTool sets it to true; resolve is now injected only when at least one
active tool is deferrable (previously unconditional).
- Replace single-slot PendingActionStore (set/get/clear) with a LIFO stack
(push/peek/pop/clear). Multiple deferrable tools can stage independent
preview actions; resolve always consumes the topmost one first.
- Wire pendingActionStore through discoverAndLoadCustomTools / loadCustomTools /
CustomToolLoader so custom tools can call pushPendingAction(action) to
register a resolve-compatible pending action with label, apply callback,
optional details, and optional sourceToolName.
- Export HIDDEN_TOOLS and ResolveTool from the SDK for manual tool composition.
- Add CustomToolPendingAction type and pushPendingAction to CustomToolAPI.
- Update createAgentSession to re-inject or remove resolve after the deferrable
audit, consistent with createTools behavior.
- Add LIFO resolve test, update existing tests (set -> push, get -> peek).
- Add docs/resolve-tool-runtime.md covering PendingActionStore internals,
built-in producer example, and custom tool usage guide.
- Simplified resolve tool output rendering from boxed layout to inline highlighted format for cleaner display.
- Updated resolve tool to parse source tool name from label using colon separator instead of separate metadata field.
- Replaced CachedOutputBlock with direct line rendering using padToWidth and inverse styling.
- Removed actionBadge helper function and consolidated action/state logic into single rendering path.
- Updated 1 test to verify inline rendering behavior and label parsing.
- ast_grep: drop include_meta (always true now); update prompt examples
- ast_edit: dry_run -> preview; max_replacements -> limit; max_files
removed from schema, always read from $PI_MAX_AST_FILES (default 1000)
- cap parse errors at PARSE_ERRORS_LIMIT (20) in both text output and
TUI; show 'N / total' summary when over limit
- export PARSE_ERRORS_LIMIT from render-utils, no hardcoded magic numbers
Remove the non-empty validation on `out` in both the TypeScript tool
layer and the Rust native layer. An empty replacement template now
deletes the matched AST node, which is the natural semantics.
Also remove .trim() calls on pattern and rewrite strings — trimming
silently destroys intentional whitespace and serves no purpose since
ast-grep matches on AST structure, not raw text.
providers/google-gemini-cli:
- parseGeminiCliCredentials() handles legacy, alias (project_id/refresh/expires),
and enriched credential JSON formats
- shouldRefreshGeminiCliCredentials() + refreshGeminiCliCredentialsIfNeeded()
proactively refresh OAuth tokens 60s before expiry for both providers
- normalizeAntigravityTools() converts parametersJsonSchema -> parameters
in function declarations for Antigravity compatibility
- VALIDATED tool calling config applied for Antigravity + Claude model combos
- maxOutputTokens removed from generation config for Antigravity non-Claude models
- Antigravity system instruction injection scoped to Claude + gemini-3-pro-high models
- Antigravity session ID: signed decimal int63 derived from SHA-256 of first user
message (or random bounded int63), replacing truncated hex hash
- Antigravity requestId uses agent-{uuid}; non-Antigravity requests omit
requestId/userAgent/requestType from payload
- ANTIGRAVITY_DAILY_ENDPOINT corrected to daily-cloudcode-pa.googleapis.com;
sandbox kept as fallback
- ANTIGRAVITY_SYSTEM_INSTRUCTION exported
oauth/google-antigravity:
- PKCE removed from OAuth flow (no code_challenge)
- loadCodeAssist metadata ideType changed to ANTIGRAVITY
- discoverProject uses single production endpoint; falls back to onboardUser LRO
(up to 5 retries, 2s interval) instead of hardcoded default project ID
- ANTIGRAVITY_LOAD_CODE_ASSIST_METADATA exported
oauth/google-gemini-cli:
- PKCE removed from OAuth flow
oauth/index:
- getOAuthApiKey includes refreshToken, expiresAt, email, accountId in
Gemini/Antigravity JSON payload for proactive refresh support
discovery/antigravity:
- Tries production daily endpoint first, sandbox as fallback
- Removed recommended/agentModelSorts filter; applies denylist instead
- ANTIGRAVITY_DISCOVERY_DENYLIST filters low-quality/internal models
- Request body no longer includes project field
coding-agent:
- gemini_image: corrected responseModalities to uppercase IMAGE/TEXT
- Gemini web search: endpoint fallback (daily->sandbox) with retry on 429/5xx,
aligned Antigravity request metadata, ANTIGRAVITY_SYSTEM_INSTRUCTION injection
- buildGeminiRequestTools() helper for composable googleSearch/codeExecution/urlContext
- Web search schema: expose max_tokens, temperature, num_search_results params
- Web search: explicit provider falls back to auto chain when unavailable
Tests: google-antigravity-auth, google-gemini-cli-alignment, web-search-gemini
BREAKING CHANGE: ast_find parameter 'pattern' (string) is replaced by
'patterns' (string[]). ast_replace parameters 'pattern' + 'rewrite' are
replaced by 'ops: Array<{ pat: string; out: string }>'.
Native (pi-natives / crates/pi-natives):
- astFind accepts patterns[] array; all patterns run per file, results
merged and sorted by path/line/column before offset+limit are applied
- astReplace accepts rewrites Record<string,string>; all patterns compiled
once upfront and applied per file in a single pass
- Deterministic result ordering via BTreeSet/BTreeMap
Coding-agent tools:
- ast_find: multi-pattern deduplication, '>>' prefix on match-start lines,
padded line numbers, directory-tree grouping (# dir / ## └─ file headers),
scopePath/files/fileMatches in tool details
- ast_replace: ops[] interface with duplicate-pattern rejection, diff-style
(-before/+after) previews grouped by directory, parse errors shown on
zero-replacement path, fileReplacements in tool details
- Tool prompts updated to document new interfaces with multi-pattern examples
- Task item id maxLength raised from 32 to 48 characters
- Added ast_replace tool test suite
- Extracted schema utilities from typebox-helpers and google-shared into new modular utils/schema package with 17 exported functions.
- Consolidated OpenAI strict mode schema enforcement across codex, completions, and responses providers using unified adaptSchemaForStrict() helper.
- Refactored credential ranking from hardcoded Codex-specific logic to pluggable CredentialRankingStrategy pattern with provider implementations.
- Migrated 500+ lines of Google schema sanitization and normalization logic from google-shared.ts to dedicated utils/schema modules with expanded functionality.
Rust (crates/pi-natives/src/ast.rs):
- Expand supported languages from 7 to all 25 ast-grep tree-sitter
languages: Bash, C, C++, C#, CSS, Elixir, Go, Haskell, HCL, HTML,
Java, JavaScript, JSON, Kotlin, Lua, Nix, PHP, Python, Ruby, Rust,
Scala, Solidity, Swift, TSX, TypeScript, YAML.
- Pre-filter file candidates by language-resolvable extension before
reading or parsing. Non-code files (.md, .zip, .bin, .gitignore, etc.)
are silently skipped instead of producing misleading parse errors.
- Make canonical_lang_name exhaustive over SupportLang so the compiler
flags new variants on upstream upgrades.
TypeScript (ast-find.ts, ast-replace.ts):
- Format match output with hashline tags (LINE#HASH:content) when
hashline mode is active, consistent with read/grep tool output.
Falls back to plain line numbers when hashline mode is off.
- ast_find now emits all lines of a multiline match instead of a
single truncated preview line.
Prompts:
- Add AST pattern syntax reference (metavariables, wildcards, variadics)
to the system prompt.
- Add examples and scoping guidance to ast-find.md and ast-replace.md.
- Replaced node-html-parser with linkedom library across all web scrapers for improved DOM API compatibility.
- Updated DOM property access from .text to .textContent and .parentNode to .parentElement for linkedom API.
- Refactored extractDocumentLinks() to use regex-based parsing with 20-link limit instead of full DOM traversal.
- Added type assertions and Array.from() wrappers for querySelectorAll() results to ensure proper typing.
- Unified glob pattern handling in ast_find and ast_replace tools by consolidating separate glob parameter into path parameter.
- Added parseSearchPath() utility function to parse glob patterns from file paths and separate base path from glob components.
- Made pattern parameter required in ast_find tool and removed strictness parameter from both ast_find and ast_replace tools.
- Updated tool documentation to clarify that path parameter accepts files, directories, and glob patterns.
- Replaced full-page HTML parsing with bounded head extraction to reduce memory usage and parsing overhead.
- Implemented regex-based attribute extraction to avoid DOM parsing overhead for link discovery.
- Added extractHeadHtml() to limit parsing to first 32KB of head section, preventing expensive whole-page traversal.
- Added ast_find and ast_replace tools for syntax-aware structural code search and rewriting via ast-grep.
- Added astFind.enabled and astReplace.enabled configuration settings to control tool availability.
- Implemented native AST module with pattern matching, language inference, and edit application for 7 languages.
- Added system prompt guidance to prefer AST tools over bash text manipulation for syntax-aware operations.
- 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.
- Added lenientArgValidation option to tools for graceful handling of argument validation errors.
- Refactored schema reference resolution to inline all $ref definitions instead of preserving them at root level.
- Added circular reference detection during schema resolution to prevent infinite loops.
- Added AJV compilation verification to catch unresolved $ref references before tool execution.
- Added graceful schema validation fallback mechanism that degrades to unconstrained schemas on repeated validation failures.
- Enhanced schema enforcement across AI providers to use try-catch pattern with automatic fallback to non-strict mode on validation errors.
- Improved handling of circular, deeply nested, and non-object output schemas with stack overflow prevention and type conversion fallbacks.
- Added `tryEnforceStrictSchema()` utility function providing error-resilient schema validation with strict mode flag tracking.
- Added normalizeMixedSchemaNode() function to recursively convert mixed JTD and JSON Schema definitions into valid JSON Schema.
- Changed output schema validation to gracefully fall back to unconstrained JSON objects when schema is invalid instead of throwing errors.
- Fixed handling of mixed JTD and JSON Schema output definitions by normalizing them during schema conversion.
- Added comprehensive test coverage for JTD-to-JSON Schema conversion and output schema validation edge cases.
- Added `sanitizeSchemaForStrictMode` function to normalize JSON schemas by removing non-structural keys for strict mode compatibility.
- Enhanced `enforceStrictSchema` to handle union types with object variants and type arrays containing object.
- Fixed `enforceStrictSchema` to properly handle malformed object schemas with required keys.
- Integrated schema sanitization in coding-agent submit-result tool with fallback to non-strict mode on validation errors.
- Replaced `Type.Object` with `Type.Record` for more accurate representation of arbitrary JSON output when no specific schema is provided.
- Improved config CLI test assertions for model roles to strip ANSI escape codes, enhancing test robustness.
- Restructured submit_result tool parameter schema to wrap data and error fields in a nested result object.
- Updated all prompt documentation to reference the new result.data and result.error parameter paths.
- Added validation logic to ensure result is an object containing exactly one of data or error.
- Updated test cases to reflect the new nested result object parameter structure.
- Added topP, topK, minP, presencePenalty, and repetitionPenalty sampling control options to StreamOptions and AgentOptions interfaces.
- Implemented getter and setter properties on Agent class for runtime configuration of model sampling parameters.
- Added UI configuration and preset value providers for five new sampling parameters in coding-agent settings schema and components.
- Integrated sampling control parameters through proxy layer and agent session configuration for end-to-end provider support.
Validate report_finding details before extraction and normalize findings before task rendering to avoid crashes when tool errors emit empty details.
Fixes#173
The submit_result tool marked 'data' as optional (Type.Optional) in its
JSON schema, but runtime validation requires it when status is 'success'.
Models that follow the schema literally omit the data parameter, causing
every call to fail with 'data is required when status is success (got
null/undefined)'. The agent then retries indefinitely.
Change data from Type.Optional(dataSchema) to dataSchema so the schema
matches runtime requirements. Models are now forced to include the data
object when calling submit_result with success, resolving the loop.
For aborted status, models can pass data: {}; validation is skipped.
Co-authored-by: Cursor <cursoragent@cursor.com>
The non-interactive environment variables (pager, editor, and prompt
suppression) were only applied in the PTY (interactive) bash path.
The non-PTY executeBash path had no such defaults, so commands could
block on pagers or credential prompts.
- Extract NO_PAGER_ENV from bash-interactive.ts into shared
non-interactive-env.ts module (renamed to NON_INTERACTIVE_ENV)
- Apply it in executeBash (non-PTY) with user overrides taking
precedence
- Fix ordering in interactive PTY path so user env overrides
the defaults (was reversed)
- Add test verifying defaults are applied alongside user env
- Consolidated @oh-my-pi/pi-utils subpath imports into single package root import across 100+ files.
- Moved tryParseJson utility from local web scrapers module to @oh-my-pi/pi-utils package for centralized JSON parsing.
- Renamed loadSkillsFromDir to scanSkillsFromDir and refactored skill discovery to use fs.promises.readdir instead of glob-based approach.
- Replaced custom parseJSON with tryParseJson across discovery modules for consistent error handling.
- Removed emitCustomToolSessionEvent method and cleanupSshResources function, consolidating shutdown logic into dispose method.
- Updated glob pattern construction to use GlobBuilder with literal_separator(true) for improved path handling.
- Added fallback empty string for undefined tool descriptions across all AI providers to prevent runtime errors.
- Made `description` field required in CustomTool interface and normalized tool descriptions in agent-loop.
- Refactored tool normalization in agent-loop by renaming `injectIntentIntoTools()` to `normalizeTools()` with conditional intent injection.
- Added comprehensive description metadata to todo-write tool schema fields for improved clarity.
- Introduced mechanism to suppress future delivery attempts for acknowledged jobs.
- The AwaitTool acknowledges deliveries for jobs it finished awaiting.
- Prevents unnecessary retries and clears delivery queue for handled jobs.
- Added a `display.tabWidth` setting to control default tab rendering.
- Integrated `.editorconfig` resolution for c ontext-aware tab indentation.
- Updated native text processing to use the resolved tab width for calculations.
- Improved tab visualization in diffs and other UI elements for consistency.
- Removed `timeout` parameter from await tool--tool now waits indefinitely until jobs complete or the call is aborted.
- Renamed `job_ids` parameter to `jobs` in await tool schema.
- Removed `timedOut` field from await tool result details.
- Simplified timeout logic by eliminating sleep-based polling in favor of indefinite waiting.
- Renamed `file` parameter to `path` in edit tool schemas and all test cases for consistency.
- Removed `file` property fallback from EditRenderArgs interface and path resolution methods.
- Refactored browser viewport schema to use snake_case `device_scale_factor` with explicit camelCase mapping for Puppeteer API.
- Added hashline edit rule requiring `end` tag to include closing braces/brackets when replacing blocks.
- Refactored INTENT_FIELD injection logic to conditionally reorder schema properties and update required array.
- Added getTodoPhases() and setTodoPhases() methods to ToolSession API for in-memory todo phase management.
- Added getLatestTodoPhasesFromEntries() export to retrieve todo phases from session history entries.
- Changed todo state management from file-based (todos.json) to in-memory session cache with automatic persistence.
- Changed todo phases to sync from session branch history during branching and rewriting operations.
- Removed file-based todo loading logic and replaced with session-based todo phase retrieval throughout codebase.
can1357