- Filtered recall, fact, vector, temporal, and polyphonic voices to session-owned or explicitly global memories.
- Implemented graph_query and graph_link MCP tool handlers via EpisodicGraph; wired annotations and graph into Mnemosyne's external-db path.
- Fixed restore to stage and integrity-check before replacing the live database, rolling back on failure.
- Deduped generateId with a per-process nonce to prevent batch duplicate-content collisions.
- Mocked the Vertex stream E2E test to override the home directory and clear GOOGLE_APPLICATION_CREDENTIALS so token resolution uses metadata credentials instead of local ADC files.
- Updated wafer and model-registry test expectations to match current model metadata values (Qwen3.7 Max and claude-opus-4-8).
Treat Synthetic discovery as an authoritative catalog so deprecated bundled IDs are removed from resolved model lists and cache snapshots. Validate Synthetic API keys through the models endpoint instead of a model-specific chat request.\n\nFixes #1417
Threaded cache freshness/authoritativeness through #loadCachedStandardProviderModels so dropProviderModels only fires when the cached Vertex project-catalog row is both fresh and authoritative. A stale or non-authoritative snapshot (e.g. after ADC discovery failure rewrote the row with authoritative=0) now keeps the bundled Gemini fallback in place, which would otherwise be the last working catalog in API-key-only environments.
Refs #1412
Added Google Vertex OpenAI-compatible model discovery with ADC auth and treated authoritative Vertex project catalogs as replacements for bundled Gemini fallbacks in the model registry.
Fixes#1412
Prevent disabled providers from being registered for implicit local discovery and from creating built-in model discovery managers. Added regression coverage for disabled local providers during model registry refresh.
Fixes#1232
- Wrapped initial and subsequent print-mode prompts with `logger.time` for timing instrumentation.
- Printed collected timings after session run when `PI_TIMING` env var is set.
- Added `omp auth-gateway serve/token/status` — a forward-proxy injecting broker credentials for OpenAI Chat, Anthropic Messages, and OpenAI Responses wire formats.
- Added `GET /v1/usage` to auth-broker and auth-gateway; usage cache switched to 5-min per-credential TTL with jitter and last-good fallback on failure.
- Added `AuthStorage.setConfigApiKey/removeConfigApiKey/clearConfigApiKeys` so `models.yml` `apiKey` beats OAuth tokens without overriding `--api-key`.
- Added `omp auth-broker migrate --from-local` for idempotent upload of local SQLite/env credentials to the broker.
- Replaced fromTypeBox conversion with a JSON-schema validator flow in ai tool handling and execution paths.
- Added recursive schema validation and expanded TypeBox checks for refs, enums, uniqueItems, and constraint keywords.
- Sanitized Azure/CCA tool schemas by dropping unsupported fields and rewriting oneOf tool branches as anyOf.
- Tightened argument and model-config validation, preserving unknown tool fields and adding apiKey plus compatibility flags.
Loaded cached standard provider discovery models into ModelRegistry at startup so retry fallback validation can resolve Ollama Cloud models that are already visible through --list-models.
Added regression coverage for cached ollama-cloud fallback selectors and fixed a readonly notices type error exposed by the focused type check.
Fixes#1052
- 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.
When cached or freshly-discovered provider models carry UNK_CONTEXT_WINDOW
(222222) / UNK_MAX_TOKENS (8888) sentinels, #mergeResolvedModels was
replacing the bundled model wholesale — wiping out the correct values.
Switch to a field-level merge that preserves the bundled model's
contextWindow and maxTokens when the replacement only has sentinel
fallbacks. Custom models (via #mergeCustomModels) already had this
protection via ?? fallback; provider discoveries didn't.
Fixes the TUI showing 222222/8888 instead of the real context/token
limits for discovered models.
Exposes model.compat.disableStrictTools (already supported by the anthropic
transport since #826) via models.yml so users can configure it without code
changes.
Set disableStrictTools: true at the provider level to disable strict tool
schemas for third-party Anthropic-compatible endpoints (AWS Bedrock, Vertex
AI proxies, custom gateways) that reject the strict field.
- Add disableStrictTools to ProviderConfigSchema
- Merge { disableStrictTools: true } into provider compat override when set,
flowing through the existing compat pipeline to model.compat.disableStrictTools
- disableStrictTools alone is sufficient for an override-only provider entry
- Update docs/models.md with field reference, Bedrock example, and proxy note
- Add tests covering provider-level propagation, built-in override, and
overlay merge
The helper guarded `model.api === "openai-completions"` and returned undefined
for openai-responses models. The discoverable-custom-compat test sets
`api: "openai-responses"` on a custom model with `compat.extraBody`, so the
post-refresh assertion saw `undefined` instead of the configured proxy hint.
The OpenAICompatSchema gates user-facing custom-model compat regardless of the
underlying api wire format, so reading the field as OpenAICompat for any api
matches what the registry actually stores.
Commit a190397d8 made `Model.compat` resolve to `OpenAICompat | AnthropicCompat`
under the default `TApi = any`. The widened union broke every site that treated
`compat` as openai-shaped: model-registry deep-merge, openai-completions resolved
compat, and ~20 test fixtures. This restores the assumption locally instead of
papering over it with casts.
- getBundledModel is now generic on TApi so test fixtures that spread it into
`Model<"openai-completions">` get the narrow compat back.
- mergeCompat is generic over TBase/TOverride; the schema-driven model-registry
override path keeps its OpenAICompat-shaped merge fields, anthropic overrides
pass through untouched.
- OpenAICompatSchema gains the openai-only fields it was missing
(requiresMistralToolIds, reasoningContentField, requiresReasoningContent*,
thinkingFormat, requiresThinkingAsText, disableReasoningOnForcedToolChoice).
- resolveOpenAICompat fills in disableReasoningOnForcedToolChoice so the
Required<OpenAICompat> shape stays satisfied.
- Anthropic tool-result block id assignment uses the proper unknown double-cast.
- isForcedToolChoice accepts unknown so it can read `params.tool_choice` whose
type comes from the OpenAI SDK ChatCompletionToolChoiceOption (now wider than
our local OpenAICompletionsToolChoice).
- Test fixtures and Required<OpenAICompat> literals updated for the field set.
Fixes CI red on main.
- Added an `isOAuth` model flag and passed it through Anthropic stream calls to force OAuth-shaped request options.
- Extended model-registry config handling with an `auth: oauth` mode and default `isOAuth` resolution for `anthropic-messages` providers while allowing explicit `apiKey` auth to remain unset.
- Added tests covering OAuth defaults and opt-outs for Anthropic and non-Anthropic custom providers.
- Register claude-opus-4-7 model entry in models.json
- Cover adaptive thinking/sampling payload shape in anthropic-alignment test
- Assert Opus 4.7 surfaces in ModelRegistry available models
- Standardized missing-file read errors and now return `File not found: <path>` for absent edit targets.
- Centralized AI provider, usage, and OAuth helpers into shared modules to remove duplicated logic.
- Migrated OAuth/API-key login flows to shared factory helpers and removed inline prompt/token-exchange code.
- Reused shared tools and formatter utilities for discovery, stream tails, LSP batching, and source formatting.
- Consolidated repeated test helpers and fixtures into shared modules, replacing inline helper duplicates.
Three fixes to make CI green after the opus 4.7 and auto-bump landed:
1. github-copilot model mapper: prefer capabilities.limits.max_prompt_tokens
over the root-level context_length field (which mirrors max_context_window_tokens, i.e.
total window). Copilot's real /models response returns both for the gpt-5.x family, and
context_length inflates contextWindow with the output budget. Also restore the bundled
Copilot limits (claude-opus-4.6, gpt-5.2, gpt-5.4, gpt-5.4-mini, grok-code-fast-1) to
the values the fixed mapper produces so tests that depend on truthful offline fallbacks
pass. Update the two Copilot discovery tests whose payloads conflated context_length
with prompt capacity.
2. coding-agent task schema: make the per-task assignment description context-mode-aware.
The previous description unconditionally told agents that 'shared background belongs
in context', which is wrong for independent mode where shared context is disabled.
3. coding-agent model-registry test: update the anthropic-latest canonical collapse case
to claude-opus-4-7 since opus 4.7 is now the newest official opus in models.json.
Add ollama-chat API provider supporting:
- Streaming chat completions via Ollama Cloud (ollama.com) API
- API key authentication via OLLAMA_API_KEY env var
- Thinking/reasoning model support with configurable effort levels
- Tool calling with streaming JSON argument assembly
- Dynamic model discovery via /api/tags and /api/show metadata
- Context window detection from model info
- Login flow via pi login ollama-cloud
- Added `toolStrictMode` support with `all_strict`/`none`/`mixed` options to OpenAI compatibility.
- Fixed OpenAI-completion strict-mode flows by capturing failed HTTP responses and retrying once as non-strict.
- Fixed completion error reporting by surfacing captured status, headers, and JSON `type`/`param`/`code` details.
- Improved strict-schema enforcement with WeakMap memoization and circular-schema detection in sanitization.
- Fixed OpenRouter provider lookup by resolving fallback model IDs for suffix and date variants in registry resolution.
- Refactored benchmark tooling and added async RPC error-window tracking for scheduled run execution.
- Added canonical model equivalence types, cache helpers, and registry APIs for provider variant lookup.
- Changed model resolution to apply canonical ID overrides/excludes with provider order before fallback matching.
- Added canonical and provider model views in list-models and selector UI with canonical sorting/persistence.
- Updated role/model persistence to store selectors while runtime now resolves concrete canonical-backed provider models.
Replace VSCode extension impersonation (client ID Iv1.b507a08c87ecfe98,
User-Agent GitHubCopilotChat/0.35.0) with the opencode OAuth app
(Ov23li8tweQw6odWQebz, User-Agent opencode/1.3.15).
Key changes:
- OAuth device flow now uses JSON body encoding and opencode headers
- GitHub OAuth token is used directly for all API requests; no JWT
exchange or refresh cycle needed
- Base URL changed from api.individual.githubcopilot.com to
api.githubcopilot.com across models.json, openai-compat.ts, and
the oauth module
- Removed proxy-ep JWT base URL extraction from github-copilot-headers.ts
and openai-compat.ts (resolveGitHubCopilotBaseUrl now passes through
the model baseUrl unchanged)
- refreshGitHubCopilotToken is now a synchronous identity return
- All 25 bundled Copilot model definitions updated to new headers/baseUrl
- Tests updated to reflect plain GitHub token format and new base URL
Existing users will need to re-authenticate once with /login github-copilot.
- Applied `disabledProviders` setting to `getAvailable()` and `getDiscoverableProviders()` so `--list-models` and `/model` hide models from disabled providers.
- Initialized settings before model refresh in the `--list-models` code path.
- Added tests verifying disabled providers are excluded from both methods.
Fixes#588
- Updated llama.cpp model discovery to read context window from the `/props` endpoint's `default_generation_settings.n_ctx` field instead of using hardcoded 128000 default.
- Updated llama.cpp model discovery to detect vision capabilities from the `/props` endpoint's `modalities.vision` field instead of defaulting to text-only input.
- Changed llama.cpp `maxTokens` calculation to respect discovered context window limits, capping at 8192 or the server's context window, whichever is smaller.
- Added `#toLlamaCppNativeBaseUrl()` helper to normalize llama.cpp base URLs by stripping `/v1` suffix for native endpoint access.
- Added 3 test cases to verify context window, vision capability, and authorization header handling in llama.cpp discovery.
- Added automatic Ollama model context window discovery from metadata for accurate token limits.
- Added `attribution` option to `PromptOptions` for explicit billing and initiator attribution control.
- Added automatic clearing of completed and abandoned todo tasks after ~1 minute.
- Changed session directory migration to use `-tmp-` prefix instead of double-dash format.
- Updated Ollama model registration to use discovered context window instead of hardcoded 128000 token default.
Fixes#440
- Added support for provider-level OpenAI compatibility configuration enabling reasoning effort mapping and streaming usage fallback across models.
- Added 10 new AI models (DeepSeek V3.2, Llama 3.1 405B, Mistral Large 3, Pixtral Large, and others) with updated pricing and context windows.
- Fixed autocomplete to preserve ./ prefix in relative file/directory path completions and paste marker expansion to handle regex tokens literally.
- Changed system prompt date format to ISO 8601 and tool download timeout from 15s to 120s for improved cross-platform compatibility.
- Refactored OpenAI completions provider to extract token parsing logic and support choice-level usage fallback with improved message serialization.
- Added `close()` method to SessionManager and AuthStorage for proper resource cleanup and finalization of prepared statements.
- Added `initiatorOverride` option support in OpenAI and Anthropic providers for message attribution control.
- Fixed resource leaks in RpcClient timeout handling by centralizing timeout creation with unref() and adding explicit clearTimeout() calls.
- Fixed AgentSession disposal to call SessionManager's `close()` method for guaranteed resource cleanup instead of fallback flush.
- Updated all test suites to properly dispose AuthStorage instances in cleanup hooks to prevent resource leaks between tests.
* add llama.cpp as local provider
* use responses api instead of messages
* use api-keys correctly for llama.cpp provider
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
- 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.
- Reapplied #applyHardcodedModelPolicies method to enforce gpt-5.4 context window policy across all model loading paths.
- Updated model registry to apply hardcoded policies after both initial load and dynamic discovery.
- Adjusted test expectations to reflect the restored policy enforcement behavior.
- Extracted fetch mocking logic into reusable `hookFetch()` utility function with middleware-style handler pattern.
- Replaced manual `globalThis.fetch` assignment and restoration across 10 test files with `hookFetch()` calls using `using` statement for automatic cleanup.
- Implemented Disposable pattern with Symbol.dispose for fetch hook resource management, eliminating try-finally blocks.
- Exported `hookFetch` from utils public API to enable consistent fetch mocking across packages.
- 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.
- 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.
can1357