- Added `google-interactions.ts` streaming the Gemini Interactions API (model-mode steps, thought/tool/text deltas, usage, `previous_interaction_id` lineage) shared by the direct Google and Vertex providers.
- Routed `streamGoogle` and `streamGoogleVertex` through `resolveInteractionDispatch`, defaulting Gemini 3+ onto Interactions (official endpoint for direct Google, bearer/ADC for Vertex) with transparent `:streamGenerateContent` fallback and a `useInteractionsApi: false` opt-out.
- Added explicit Vertex bearer support in `google-auth.ts` via `GOOGLE_CLOUD_ACCESS_TOKEN`/`CLOUDSDK_AUTH_ACCESS_TOKEN` plus a `hasVertexBearerCredentialsHint` probe gating the auto-default.
- Added `useInteractionsApi`/`storeInteraction`/`previousInteractionId` to `StreamOptions` and `GoogleSharedStreamOptions`, threading them through `mapOptionsForApi`.
- Added `google-interactions` coverage and pinned the existing generateContent assertions with `useInteractionsApi: false`.
- Introduce `fallbackUrl` to allow retrying requests on the global Vertex endpoint when a 404 is encountered on a regional endpoint.
- Correctly track tool call names to facilitate accurate function response mapping.
- Update `serviceTier` type definitions to accurately reflect allowed values.
- Refine vertex endpoint location resolution to ensure better compatibility with ambient regional settings.
- Migrated global service tier settings to a per-model-family architecture (OpenAI, Anthropic, Google).
- Implemented `ServiceTierByFamily` mapping to allow independent configuration and resolution per provider.
- Added automatic migration logic for legacy service tier and fast-mode application settings.
- Updated telemetry, session management, and task execution to support provider-specific tier resolution.
- Migrated internal streaming state from string-based properties to symbol-keyed properties for improved data isolation and safety.
- Replaced the deprecated `stripVariant` utility with centralized `clearStreamingPartialJson` and symbol-specific helper methods across all provider implementations.
- Implemented `stripStreamingBlockSymbols` and updated deep equality checks to ensure metadata does not interfere with content comparisons.
- Standardized streaming metadata access through a new `block-symbols` utility module.
- Migrated 288 lines of scattered error classification logic from `utils/error-id.ts` into a cohesive `packages/ai/src/error/` module with 13 specialized submodules covering flags, classes, OAuth, providers, rate-limiting, and finalization.
- Replaced 100+ generic `Error` throws across 60+ provider and registry files with semantic `AIError.*` classes (e.g., `AIError.MissingApiKeyError`, `AIError.OAuthError`, `AIError.ProviderResponseError`), improving error diagnostics and retry logic.
- Consolidated error utility imports from `pi-utils` and scattered classification functions into a single `AIError` namespace, reducing coupling and simplifying error handling across all packages.
`delete` on object properties degrades V8 hidden class optimization; the new `stripVariant` util sets the property to `undefined` instead, keeping the object shape stable.
`performance.now()` is used in place of `Date.now()` for duration and TTFT measurements to get a monotonic, high-resolution clock that is unaffected by system clock adjustments.
- Centralized thinking block demotion logic using `renderDemotedThinking` across all model providers.
- Updated `transformMessages` to default to text-based demotion for foreign thinking content.
- Restricted foreign thinking preservation to explicitly supported targets with `zai` thinking formats.
- Refactored message transformations and updated test suites to validate standardized demotion outcomes.
Stopped serializing explicit AUTO toolConfig for Google Gemini toolChoice auto so Gemini defaults apply without triggering upstream planning JSON leaks.\n\nAdded a regression test for auto toolChoice while preserving explicit ANY and named-tool routing.\n\nFixes #2776
- agent-loop: raise repetition-detection floor to 180 chars and clear thinking
replay anchors when collapsing a detected loop.
- providers/google: ignore empty text parts, retain terminal thoughtSignatures,
and stop function-call signatures clobbering the prior block.
- autolearn: capture goal-mode at the turn boundary; harden managed-skill writes
against hard-links/symlinks (O_NOFOLLOW + nlink); refuse minting managed skills
whose name an authored skill already claims.
- eager tasks: thread agentKind through the session so a custom top-level agentId
still gets always-mode delegation; split Eager Tasks prompt into hard vs soft.
- title-generator: race the online title model against a local tiny-model fallback.
- eager-todo: keep the soft reminder aligned with the todo init schema.
- mcp/stdio: keep close() detaching the read loop instead of awaiting it.
- stream loop: fix collapsing and tool-call thought-signature handling.
- Added shared Google empty-stream retry constants and reused them in CLI.
- Replaced local content checks with hasMeaningfulGoogleContent for retry gating.
- Refactored streamGoogleGenAI to bound empty STOP retries with state reset and reopen.
- Moved stream start emission before retry loops to avoid duplicate start events.
Move bundled models, model cache/manager, thinking metadata, effort helpers,
provider descriptors/discovery, wire constants, and model identity utilities
into the new @oh-my-pi/pi-catalog package.
Update pi-ai to keep provider runtime/auth concerns, move catalog provider
metadata into CATALOG_PROVIDERS, and migrate coding-agent, agent, stats, docs,
and tests to import catalog values from pi-catalog.
Split coding-agent model registry helpers into discovery, roles, and models
config modules while preserving registry orchestration.
BREAKING CHANGE: @oh-my-pi/pi-ai no longer exports catalog subpaths such as
/models, /model-cache, /model-manager, /model-thinking, /effort,
/provider-models*, discovery helpers, and provider wire constants; use the
matching @oh-my-pi/pi-catalog subpaths instead.
in-band Gemini errors, promptFeedback blocks, and missing finishReason no longer report success; toolUse override stops masking SAFETY/MALFORMED finishes; schema normalization keeps DAG-shared subtrees while detecting true cycles; Google/AWS shared credential resolution detached from first caller's signal and bounded by own timeout; Bedrock keeps toolConfig under toolChoice none; eventstream cancels body on abnormal exit.
F1 (coding-agent): close the withFileLock mkdir-vs-writeLockInfo race that
let a losing contender wipe the winner's freshly-created lock directory.
Every lock now carries a per-process UUID token; releaseLock verifies the
token before fs.rm, and isLockStale no longer treats an info-less but
fresh dir (or a dir that vanished mid-check) as stale.
F4 (coding-agent): sanitize tabs and truncate oversized error strings in
formatErrorMessage so error renderings that embed file content
(apply_patch, hashline, etc.) cannot break terminal alignment or
overflow the line width.
F7 (ai): support named-tool routing on Google providers. Widens
GoogleSharedStreamOptions.toolChoice and GoogleGeminiCliOptions.toolChoice
to accept { mode: 'ANY'; allowedFunctionNames }. mapGoogleToolChoice
now converts ToolChoice { type: 'tool'|'function', name } to the wire
shape (mirroring mapAnthropicToolChoice). buildGoogleGenerateContentParams
and the gemini-cli request serializer honor the allow-list.
- Buffered `start` events until after the first replay-unsafe event and replayed them on auth failure.
- Retried stream requests with refreshed credentials when `onAuthError` returned a new key for gateway and pi-native.
- Added 401 error-status parsing for assistant errors and updated stream-auth tests for start+401 retry behavior.
- Added `AuthRetryFailure` helpers and status extraction types to propagate auth-retry metadata through stream attempts.
- Removed deprecated AWS/Google client and proxy dependencies from root and AI package manifests.
- Added AWS credential chaining, SigV4 signing, and Bedrock stream decoding with region fallback and CRC checks.
- Added local Google type mirrors and migrated providers to request plans with SSE fetch and token-based auth.
- Updated AI changelog with auth/stream fixes, and added fetch-stub and SigV4/event-stream tests.
- Implemented a unified normalization flow by switching Google/CCA handling to normalizeSchemaForGoogle/CCA.
- Added normalize.ts with recursive node normalization, nullable-union checks, and combiner collapsing.
- Removed sanitize-google.ts and normalize-cca.ts, replacing them with normalize exports in schema indexes.
- Added spill-to-description utilities with spill/paren modes and `$defs` exclusion for unsupported fields.
- Updated MCP bridge and schema tests to use normalizeSchemaFor* APIs with expanded compatibility checks.
- Documented normalization behavior changes and breaking rename in constraints and package changelog files.
- Added canonical `pi.zod` schema API exports and removed TypeBox package exports/imports.
- Migrated Tool schema typing from TypeBox to shared `TSchema`/Zod flow with legacy TypeBox compatibility.
- Updated AI provider adapters and MCP/agent builders to convert tool params through `toolWireSchema()`.
- Reworked schema validation from AJV to Zod-safe parsing with `fromTypeBox`, `toolWireSchema`, and meta schema checks.
- Removed export leakage by demoting many helper and const symbols to module-local scope.
- Renamed underscore-prefixed internals and cache fields, then updated related references and `satisfies never` checks.
- Deleted obsolete logic branches and helpers, including harmony-stream interruption flow and unused benchmark runtime helpers.
- Updated Biome config and manifests by broadening lint coverage and removing an unused `@napi-rs/cli` dev dependency.
- Adjusted tests and utilities to use renamed test helpers and remove redundant private test-only helpers/locals.
- Image blocks sent to models without vision support now emit `[image omitted: model does not support vision]` instead of being silently dropped, preventing opaque 404 errors.
- Fix applies to user messages and tool-result payloads across Anthropic, OpenAI completions/responses, Codex, and Google providers.
- Extracted shared `vision-guard.ts` with `partitionVisionContent`, `joinTextWithImagePlaceholder`, and `NON_VISION_IMAGE_PLACEHOLDER`.
- Added regression tests covering all five provider paths.
Fixes#967Fixes#968
- Replaced custom `sanitizeSurrogates()` utility with native `String.prototype.toWellFormed()` across all provider implementations.
- Removed `sanitize-unicode.ts` utility module and all imports of `sanitizeSurrogates` function from 10 provider files.
- Updated Unicode surrogate handling in message conversion, response processing, and system prompt handling to use built-in JavaScript API.
- Documented removal of `sanitizeSurrogates()` utility and migration to native `toWellFormed()` in CHANGELOG.
## 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.
- Normalized Claude schemas by stripping `nullable` and collapsing combiners.
- Parallelized Codex usage report fetching for ranking efficiency.
- Improved Codex credential ranking logic, prioritizing fresh usage and handling failures.
- Refactored `tryOAuthCredential` for improved readability and type safety
Fixes three issues with Claude via Cloud Code Assist (Antigravity):
1. collapseMixedTypeCombinerVariants produced type arrays (e.g.
["array", "string", "null"]) which break Google's protobuf API
(type is a scalar enum, not a repeated field). Now picks the first
non-null type as a scalar.
2. sanitizeSchemaForCloudCodeAssistClaude had normalizeTypeArrayToNullable
set to false, so type arrays from other sources were not collapsed.
3. mergeObjectCombinerVariants creates new anyOf in merged properties
(e.g. todo_write's content field gets anyOf with two string variants
with different descriptions). These were never collapsed because the
recursive normalization already processed children before the merge.
Added collapseSameTypeCombinerVariants to handle same-type unions and
stripResidualCombiners as a second pass to catch newly-created anyOf.
Tested with omp v13.3.12 + Claude Opus 4.6 (Thinking) via Antigravity.
All 36 tools pass schema validation.
Fixes#201
- 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.
- Fixed schema normalization in Google provider to handle array-valued type fields by converting them to single type with nullable flag.
- Refactored version parsing in install script to use bash parameter expansion instead of IFS field splitting.
- Changed variable declarations from let to var in theme module global scope.
- Migrated historical tool call context to an XML-like structure.
- Clarified the message to explicitly warn models against mimicking tool calls.
- Enhanced context interpretation for Gemini 3 models.
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
- Removed WASM generation script; use Bun `wasm?raw` loader for imports.
- Added bunfig.toml with loaders for `.md`, `.py`, and `.wasm?raw` text imports.
- Added types/assets/index.d.ts for global TypeScript module declarations.
- Unified TypeScript configuration with tsgo-based checking across monorepo.
- Removed build and WASM steps from install and publish pipelines.
- Added tsconfig.publish.json files to all packages with optimized publish-time configuration.
- Updated all package.json scripts with prepublishOnly hooks for correct type checking during publish.
- Added @oh-my-pi/omp-stats path mappings to root tsconfig.json for consistent imports.
- Added WASM generation script for photon module and integrated into install:dev script.
- converted relative imports to path aliases ($c/*, $ai/*, $tui/*, etc.) across all packages
- added per-package tsconfig.json with complete path mappings for runtime resolution
- set importModuleSpecifier to non-relative for IDE auto-import preferences
- updated dev script to run from monorepo root for consistent path resolution
cagedbird043