- 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.
- Removed normativeRewrite setting and buildNormativeUpdateInput() function from public API.
- Removed $normative property and TNormative generic parameter from ToolResultMessage and AgentToolResult interfaces.
- Deleted normative.ts patch normalization module and related helper functions for diff anchor processing.
- Removed rewriteAssistantToolCallArgs() and #rewriteToolCallArgs() methods that modified tool call arguments.
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
providers/anthropic:
- Bump claudeCodeVersion to 2.1.63; system instruction identifies as Claude Agent SDK
- X-Stainless-Os and X-Stainless-Arch now runtime-computed via mapStainlessOs/mapStainlessArch
- Remove X-Stainless-Helper-Method; update package version to 0.74.0, runtime to v24.3.0
- Remove fine-grained-tool-streaming-2025-05-14 from default beta set; add
context-management-2025-06-27 and prompt-caching-scope-2026-01-05
- Accept-Encoding updated to 'gzip, deflate, br, zstd'
- Inject x-anthropic-billing-header block (SHA-256 payload fingerprint) and
Claude Agent SDK identity block with ephemeral 1h cache-control for OAuth requests
- Auto-generate cloaking user IDs for OAuth metadata.user_id when absent/invalid
- applyClaudeToolPrefix / stripClaudeToolPrefix skip Anthropic built-in tool names
- buildClaudeCodeTlsFetchOptions attaches SNI + default TLS ciphers for api.anthropic.com
- Non-Anthropic base URLs now use Bearer auth regardless of OAuth status
- Prompt-caching no longer strips then re-applies; skips if blocks already have cache_control
oauth/anthropic:
- Token URL changed from platform.claude.com to api.anthropic.com
- OAuth scopes trimmed to org:create_api_key user:profile user:inference
- Code exchange strips URL fragment from callback code (fragment used as state override)
- AnthropicOAuthFlow exported
- OAuth callback server timeout extended from 2 min to 5 min
usage/claude:
- user-agent updated to claude-cli/2.1.63 (external, cli)
- anthropic-beta header extended with full production beta set
coding-agent web search:
- Anthropic provider uses buildAnthropicSearchHeaders instead of buildAnthropicHeaders
Tests: anthropic-alignment, anthropic-oauth, claude-usage-headers, web-search-anthropic
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
## New: schema compatibility validation API
Add `validateSchemaCompatibility(schema, provider)` in
`packages/ai/src/utils/schema/compatibility.ts` that performs a static
audit of a JSON Schema against three provider targets:
- `openai-strict`: checks forbidden keys, required/properties symmetry,
additionalProperties constraint, and that every node declares a type,
combinator, or $ref
- `google`: checks unsupported keyword set and array-valued type
- `cloud-code-assist-claude`: checks forbidden keywords, array type,
null type, nullable keyword, and combiner presence; also validates via
AJV 2020 draft
Add `validateStrictSchemaEnforcement(original, result)` to assert the
fail-open contract: when strict enforcement succeeds the output must pass
openai-strict validation; when it fails the output must be the original
schema object (same reference).
Export both functions and their types from `./utils/schema/index.ts`.
## New: shared constants in fields.ts
Extract `COMBINATOR_KEYS` (`anyOf`, `allOf`, `oneOf`) and add
`CCA_UNSUPPORTED_SCHEMA_FIELDS` as exported constants, eliminating the
local duplicate in `strict-mode.ts` and providing a canonical field set
for Cloud Code Assist (much narrower than the Google set — CCA supports
validation keywords like `additionalProperties`, `minLength`,
`pattern`, etc.).
## Fix: cycle detection in all recursive schema traversals
All recursive walkers now carry a `WeakSet<object>` guard. Previously any
schema with a reference cycle (or a schema object that appears at two
nodes in the tree) would cause an infinite loop or a stack overflow:
- `sanitizeSchemaForStrictMode` / `enforceStrictSchema`
- `normalizeSchemaForCloudCodeAssistClaude`
- `normalizeNullablePropertiesForCloudCodeAssist`
- `stripResidualCombiners`
- `sanitizeSchemaImpl` (Google sanitizer)
- `hasResidualCloudCodeAssistIncompatibilities`
`hasResidualCloudCodeAssistIncompatibilities` previously returned `true`
for already-visited nodes, producing false positives that forced the CCA
fallback schema on valid (but multiply-referenced) schemas. It now
correctly returns `false`.
## Fix: stripResidualCombiners iterates to fixpoint
The previous single-pass approach missed chained combiner reductions
where one collapsed variant exposed another reducible combiner. The
rewriter now loops until no further reduction occurs.
## Fix: mergeObjectCombinerVariants required-field computation
The merged object schema now takes the intersection of all variants'
`required` arrays, then unions in own-level required properties that
exist in the merged schema. Previously the `required` field was silently
dropped from the flattened schema, making all properties effectively
optional.
## Fix: sanitizeSchemaForGoogle improvements
- Type inference for const-collapsed enums: type is derived from all
variants (must unanimously agree), falling back to inference from enum
values; mixed null/non-null infers the non-null scalar type and sets
`nullable: true`
- Const→enum deduplication now uses deep structural equality instead of
`Object.is`
- Recursion spreads the full options object so new fields (`unsupportedFields`,
`seen`) are not silently dropped when descending into sub-schemas
- Array-valued `type` is filtered to strings before processing
- Removed incorrect stripping of `additionalProperties: false` (the
field is valid and should be preserved)
- Parameterized `unsupportedFields` in `SanitizeSchemaOptions` enables
code reuse between the Google and CCA sanitizers
## Fix: sanitizeSchemaForStrictMode / enforceStrictSchema
- `nullable: true` is now stripped during sanitization and expanded into
`anyOf: [schema, {type: "null"}]` in the enforcer output, matching
what OpenAI strict mode requires
- Type inference: `type: "array"` is inferred when `items` is present;
a scalar type is inferred from uniform `enum` values
- Const→enum merge uses deep equality to avoid duplicate entries when
both `const` and `enum` exist with the same value
- `additionalProperties` is now dropped unconditionally in sanitization
(previously only object-valued `additionalProperties` was recursed;
non-object values were passed through)
- `enforceStrictSchema` recurses into `$defs` and `definitions` blocks
- `enforceStrictSchema` handles tuple-style `items` arrays
- `enforceStrictSchema` skips double-wrapping: optional properties
already expressed as `anyOf: [..., {type: "null"}]` are not wrapped again
- `tryEnforceStrictSchema` now caches results in a `WeakMap` keyed on
the input schema object to avoid redundant work on repeated calls
## Fix: mergeCompatibleEnumSchemas deep equality
Uses `areJsonValuesEqual` instead of `Object.is` when deduplicating
enum members, so structurally equal objects are not duplicated.
## New: test coverage
- `packages/ai/test/schema-normalization.test.ts`: comprehensive unit
tests for strict mode, Google, and Cloud Code Assist normalization
- `packages/ai/test/schema-compatibility.test.ts`: unit tests for all
three provider targets in the new compatibility validator
- `packages/coding-agent/test/tools/provider-schema-compatibility.test.ts`:
integration test that instantiates every builtin and hidden tool, runs
their parameter schemas through all three provider pipelines, and
asserts zero compatibility violations
- 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.
- Extracted prompt formatting logic into reusable `formatPromptContent()` utility function with configurable render phases.
- Removed 166 lines of duplicate formatting code from scripts and config modules by centralizing regex patterns and helper functions.
- Updated prompt template rendering to use unified `formatPromptContent()` instead of inline `optimizePromptLayout()` implementation.
- Added comprehensive test coverage for prompt formatting with pre-render and post-render mode validation.
- Added `occurrence` parameter to symbol resolution for disambiguating repeated matches on the same line.
- Fixed code action application to execute command-based actions via `workspace/executeCommand` protocol.
- Fixed diagnostics glob pattern detection to recognize bracket character class patterns.
- Fixed LSP render metadata sanitization to prevent tab and newline characters from breaking layout.
- Refactored symbol resolution and code action handling into reusable utility functions with improved error handling.
- Added comprehensive regression test suite covering glob patterns, symbol resolution, code actions, and text sanitization.
- Added public `waitForIdle()` and `getLastAssistantMessage()` APIs to AgentSession for deterministic session state access.
- Refactored deferred continuation scheduling from raw `setTimeout()` to centralized post-prompt task tracking system for concurrent recovery operations.
- Fixed race conditions between deferred TTSR/context-promotion continuations and `prompt()` completion via shared recovery orchestrator.
- Replaced `#waitForRetry()` with `#waitForPostPromptRecovery()` to unify retry and TTSR resume gate handling.
- Fixed TTSR violations during subagent execution aborting the entire subagent run; `#waitForPostPromptRecovery()` now awaits agent idle after TTSR/retry gates resolve, preventing `prompt()` from returning while fire-and-forget `agent.continue()` is still streaming.
- Added comprehensive test case verifying `prompt()` blocks until TTSR continuation with tool calls completes, preventing premature session disposal.
- Implemented TTSR resume gate to ensure `prompt()` blocks until TTSR interrupt continuations complete, preventing race conditions between TTSR injections and subsequent prompts.
- Replaced `#waitForRetry()` with `#waitForPostPromptRecovery()` to handle both retry and TTSR resume gates, ensuring prompt completion waits for all post-prompt recovery operations.
- Added comprehensive test coverage for TTSR resume gate behavior under interrupt and deferred injection modes.
- Renamed intent field from `agent__intent` to `intent` in tool schemas for cleaner API contracts.
- Refined intent parameter guidance to require concise 2-6 word present participle sentences.
- Updated intentTracing documentation and test fixtures to reflect the new field naming convention.
- 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.
- Removed per-task skill pinning feature; subagents now inherit session skill set instead of per-task selection.
- Removed `preloadedSkills` option from `CreateAgentSessionOptions` interface and related system prompt plumbing.
- Removed `skills` field from Task schema; task execution now passes available session skills directly to subagents.
- Simplified task execution pipeline by removing skill resolution logic and preloaded skills handling from system prompt templates.
- 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 support for setting array and record configuration values using JSON syntax.
- Implemented JSON parsing and validation for array and record types in config CLI.
- Added 2 integration tests covering array and record configuration workflows.
- Enhanced test setup with temporary directory management and settings reset for isolation.
- Improved config display formatting to properly render arrays and objects as JSON instead of `[object Object]`.
- Enhanced type display in config list output to show correct type indicators for number, array, and record settings.
- Added test coverage for record settings rendering in config list output.
- Fixed skill discovery to continue loading project skills when user skills directory is missing.
- Added error handling in scanSkillsFromDir to gracefully handle ENOENT and log other read failures.
- Added test case verifying project skills load successfully despite missing user skills directory.
Validate report_finding details before extraction and normalize findings before task rendering to avoid crashes when tool errors emit empty details.
Fixes#173
Clarify inclusive end semantics in the hashline prompt with bad/good examples.
Add range-replace duplicate-boundary auto-correction with a safety guard so correction only triggers for off-by-one ends.
Expand hashline heuristics tests to cover brace/); correction, blank-line guard, and boundary-already-in-range false-positive prevention.
Request contents.summary from Exa /search API and combine up to
3 non-empty summaries into SearchResponse.answer, replacing the
previous 'No answer text returned' output.
Changes:
- Add contents.summary to every Exa search request body
- Add summary field to ExaSearchResult interface
- Export synthesizeAnswer() to build combined answer from summaries
- Export buildExaRequestBody() for testability
- Export normalizeSearchType() (was private)
- Prefer summary over text/highlights for snippet field (falsy check)
- Only synthesize answer from results that have a URL (mirrors sources filter)
Tests: 37 new tests covering normalizeSearchType, buildExaRequestBody,
synthesizeAnswer (pure unit tests) and searchExa (mocked fetch)
can1357