Commit Graph

57 Commits

Author SHA1 Message Date
Mario Zechner f78b163713 fix(ai): revert minimax max token clamp 2026-06-25 13:36:04 +02:00
Mario Zechner b940c52e7e fix(ai): clamp MiniMax shared budget max tokens
closes #6061
2026-06-25 12:00:37 +02:00
Armin Ronacher 371adcf371 fix(coding-agent): retry explicit provider retry errors
closes #6019
2026-06-24 18:14:06 +02:00
Mario Zechner 827fe1e2c4 feat(ai): ImagesModels collections mirroring the chat-side design
createImagesModels()/ImagesProvider/createImagesProvider() give image
generation the same shape as chat: sync model reads, explicit async
refresh(provider?) with in-flight dedupe, provider-resolved auth, and
never-rejecting generateImages() (failures return AssistantImages with
stopReason error). Auth resolution is shared with the chat side via the
free-standing resolveProviderAuth() in auth/resolve.ts, which also owns
ModelsError; both collections pass their store/context as arguments.

The OpenRouter implementation moves to api/openrouter-images.ts with a
lazy wrapper; openrouterImagesProvider() factory plus
builtinImagesProviders()/builtinImagesModels() land in providers/all.
The ImagesProvider id type alias is renamed to ImagesProviderId
(mirror of Provider -> ProviderId). The old global image API
(getImageModel*, generateImages, registerImagesApiProvider) stays on
/compat, its registration shim repointed at the moved implementation.

README: Quick Start uses builtinModels(), the full streaming event
switch, image generation and the development checklist are restored in
full, image generation documents the new collections with compat noted
for the old API, plus the review fixes (builtinModels options,
credential-store mention for browsers, ImagesModels notes).
2026-06-11 00:27:43 +02:00
Mario Zechner 8a0903ebf2 feat(ai): compat entrypoint, core-only root barrel (phase 5)
The root barrel is now core-only and side-effect free: types,
createModels/createProvider, auth substrate, lazyStream/lazyApi, faux,
utils. Generated catalogs, api-registry, env-api-keys, images, global
stream functions, and per-API lazy wrappers leave the root.

New @earendil-works/pi-ai/compat preserves the old surface verbatim as
a strict superset of the root: api-dispatch stream/complete with env
key injection, the builtin registration side effect (skip-if-present so
it cannot clobber earlier overrides), deprecated getModel/getModels/
getProviders aliases of the new getBuiltin* reads in providers/all,
lazy api wrappers + setBedrockProviderModule, and image generation.
Compat dies with the coding-agent ModelManager migration.

Packaging: exports map gains ./compat, ./providers/*, ./api/*;
sideEffects array lists only the effectful modules.

Old-global imports across agent/coding-agent/examples and pi-ai tests
switch to /compat (path-only; compat is a superset). The coding-agent
extension loader resolves the pi-ai ROOT specifier to compat, so
existing user extensions using the old global API keep working at
runtime until compat is removed. vitest configs alias /compat to src;
browser smoke imports old globals from /compat.
2026-06-10 21:17:12 +02:00
Mario Zechner fec0c3d12f feat(ai): provider factories, per-provider catalogs, createProvider (phase 3)
Auth helpers in src/auth/helpers.ts: envApiKeyAuth() (stored key wins,
then env vars in order, with secret-prompt login) and lazyOAuth()
(flow loads on first use through bundler-opaque dynamic imports in
utils/oauth/load.ts; the OAuthAuth flow exports land in phase 4).
There is no OAuth factory toggle: providers that support OAuth always
attach it, advertising costs nothing until login/refresh runs.

createProvider() in models.ts builds providers from parts: single API
implementation or a map dispatched on model.api (mixed-API providers
like opencode and github-copilot); unknown api yields a stream error.

generate-models.ts now emits one providers/<id>.models.ts catalog per
provider (35 files, biome-excluded like models.generated.ts) and
models.generated.ts becomes a generated aggregator, so importing one
provider factory pulls one catalog. Typed getModel globals unchanged.

One factory per built-in provider under src/providers/: envApiKeyAuth
for standard providers, OAuth for anthropic/openai-codex/github-copilot,
ambient ApiKeyAuth for amazon-bedrock (AWS env/profile/IAM) and
google-vertex (explicit key or ADC+project+location).

providers/all.ts: builtinProviders(), builtinModels(), getBuiltin*
re-exports. fauxProvider() factory returns a real Provider for tests;
legacy registerFauxProvider() unchanged.
2026-06-10 20:33:20 +02:00
Mario Zechner ba93da9a93 feat(ai): move API implementations to src/api with lazy wrappers (phase 2)
Stream implementations move from src/providers/ to src/api/, renamed by
API id (anthropic.ts -> anthropic-messages.ts, google.ts ->
google-generative-ai.ts, mistral.ts -> mistral-conversations.ts,
amazon-bedrock.ts -> bedrock-converse-stream.ts). Every module now
exports exactly stream/streamSimple; shared helpers move alongside.

New ProviderStreams dispatch contract in types.ts, lazyApi() wrapper in
api/lazy.ts, and one .lazy.ts wrapper per API. Bedrock's wrapper keeps
the node-only variable-specifier import and setBedrockProviderModule()
(now taking ProviderStreams).

providers/register-builtins.ts deleted; interim until the compat
entrypoint lands, builtin api-registry registration lives in stream.ts
and lazy wrappers are exported from the root barrel. Old per-API lazy
exports (streamAnthropic, ...) are gone; package.json subpaths retarget
to dist/api/.
2026-06-10 20:08:59 +02:00
Mario Zechner f63095cfff feat(ai): add Models runtime with provider-owned auth (phase 1)
New Models/MutableModels/createModels collection: provider map, async
model listing (best-effort aggregation), getAuth decision tree with
double-checked locked OAuth refresh, stream/complete with per-field
auth merge over lazyStream.

Auth substrate: ProviderAuth { apiKey?, oauth? }, one type-tagged
credential per provider, CredentialStore (read/modify/delete; modify
is the only write path, serialized RMW), OAuthAuth login/refresh/toAuth
split, prompt()/notify() login callbacks, browser-safe default
AuthContext.

types.ts: Provider alias renamed to ProviderId; ApiOptionsMap and
ApiStreamOptions<TApi> for typed per-API stream options; hasApi()
runtime narrowing guard.
2026-06-10 18:49:10 +02:00
Vegard Stikbakke c554364c2a feat(ai): refactor device code login for copilot 2026-05-22 08:54:18 +02:00
Armin Ronacher ae9450dc51 chore(ts): use source import extensions 2026-05-20 00:04:03 +02:00
Cristina Poncela Cubeiro ffdf426e33 Merge remote-tracking branch 'upstream/main' into feat/image-outputs 2026-05-07 16:46:17 +02:00
Armin Ronacher b5755fd27d feat(oauth): support interactive login selection (#4190) 2026-05-05 13:16:56 +02:00
Cristina Poncela Cubeiro 60e885f985 refactor: image providers into subfolder 2026-05-05 09:30:15 +02:00
Cristina Poncela Cubeiro 5731e13a61 Merge branch 'main' into feat/image-outputs 2026-05-04 16:42:51 +01:00
Cristina Poncela Cubeiro 63c61aac6f feat: image models 2026-05-04 17:07:02 +02:00
Cristina Poncela Cubeiro d9adc536f5 feat: openrouter images 2026-05-04 17:00:58 +02:00
Mario Zechner 23420012ab fix(coding-agent): decouple codex session cleanup 2026-05-04 00:45:56 +02:00
Armin Ronacher 370fdae6fa fix(ai): fall back from codex websocket to sse (#4133) 2026-05-03 22:51:42 +02:00
Mario Zechner 4745a95898 feat(ai): add cached codex websocket transport 2026-05-01 13:07:40 +02:00
Mario Zechner fe66edd943 remove gemini cli and antigravity support 2026-04-30 21:24:36 +02:00
Armin Ronacher 35ff2689ee fix(typebox): migrate to v1 with extension compat (#3474)
* fix(typebox): migrate to v1 with extension compat

Replace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.

This change closes #3112.

* fix(typebox): use canonical imports and harden coercion

Switch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.

Remove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.

Fixes #3112.

---------

Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
2026-04-22 19:59:33 +02:00
Mario Zechner acbf8eca06 feat(ai): add thinkingDisplay option for Anthropic and Bedrock Claude
Exposes the new ThinkingConfig.display field on Anthropic and Bedrock
Claude providers. Defaults to 'summarized' so Claude Opus 4.7 and Mythos
Preview keep returning thinking text despite Anthropic's silent default
change to 'omitted'. Set to 'omitted' explicitly to skip thinking
streaming for faster time-to-first-text-token.
2026-04-16 22:12:06 +02:00
Mario Zechner ef6af5ebbd feat(ai,coding-agent): add faux provider and ModelRegistry factories 2026-03-29 21:08:50 +02:00
wjonaskr 3bcbae490c feat(ai): add requestMetadata support to BedrockOptions for cost allocation tagging (#2511)
Add an optional requestMetadata field to BedrockOptions that forwards
key-value pairs to the Bedrock Converse API ConverseStreamCommand. Tags
appear in AWS Cost Explorer split cost allocation data, enabling callers
to attribute inference costs to specific applications or contexts.

Changes:
- Add requestMetadata?: Record<string, string> to BedrockOptions with
  JSDoc documenting AWS constraints (max 50 pairs, key 64 chars, value
  256 chars, no aws: prefix)
- Pass requestMetadata to commandInput via conditional spread to avoid
  sending undefined when omitted
- Export BedrockOptions from package root (consistent with other
  provider option types)
- Add E2E tests: metadata forwarded to SDK payload, and omitted when
  not provided

closes #2510
2026-03-22 19:05:55 +01:00
Mario Zechner a7559f01e9 feat(ai): lazy-load provider modules for faster startup fixes #2297 2026-03-17 18:03:24 +01:00
Mario Zechner a31065166d Merge branch 'feat/use-mistral-sdk' 2026-03-05 23:49:29 +01:00
Mario Zechner e0754fdbb3 fix(ai,coding-agent): make pi-ai browser-safe and move OAuth runtime exports
- add browser smoke bundling check to root check + pre-commit

- lazy-load Bedrock provider registration to avoid browser graph traversal

- remove top-level OAuth runtime exports from @mariozechner/pi-ai

- add @mariozechner/pi-ai/oauth subpath export and update coding-agent imports

- move proxy dispatcher init to coding-agent CLI (Node-only)

- document Bedrock/OAuth browser limitations

closes #1814
2026-03-04 20:21:25 +01:00
Abdeslam Yassine Agmar eb9f1183ad refactor(ai): migrate mistral provider to conversations sdk 2026-03-03 17:25:50 +00:00
Mario Zechner 0232c44064 fix(ai,coding-agent): re-export typebox symbols and align docs closes #1338 2026-02-06 18:34:25 +01:00
Mario Zechner 177c694406 feat: custom provider support with streamSimple
- Add resetApiProviders() to clear and re-register built-in providers
- Add createAssistantMessageEventStream() factory for extensions
- Add streamSimple support in ProviderConfig for custom API implementations
- Call resetApiProviders() on /reload to clean up extension providers
- Add custom-provider.md documentation
- Add custom-provider.ts example with full Anthropic implementation
- Update extensions.md with streamSimple config option
2026-01-24 23:15:11 +01:00
Mario Zechner c725135a76 refactor(ai): register api providers 2026-01-24 23:15:11 +01:00
Markus Ylisiurunen 856012296b add Azure OpenAI Responses provider with deployment-aware model mapping 2026-01-24 12:04:34 +01:00
Mario Zechner 4068bc556a chore: simplify codex prompt handling 2026-01-17 21:53:01 +01:00
Mario Zechner 6484ae279d Finalize OpenAI Codex compatibility (#737)
- align Codex Responses provider with Pi static instructions
- simplify Codex request/stream handling and cleanup exports
- keep legacy OpenCode Codex prompt for testing until Pi prompt is allowlisted
2026-01-16 00:58:36 +01:00
Mario Zechner 2b75948c2e fix(ai): export parseStreamingJson from main package for tsx compatibility 2026-01-13 22:08:19 +01:00
Armin Ronacher 6a5f04ce1f Add the codex bridge prompt in the html export 2026-01-06 14:21:34 +01:00
Anton Kuzmenko 214e7dae15 Add Vertex AI provider with ADC support
- Implement google-vertex provider in packages/ai
- Support ADC (Application Default Credentials) via @google/generative-ai
- Add Gemini model catalog for Vertex AI
- Update packages/coding-agent to handle google-vertex provider
2026-01-03 01:11:03 +01:00
Mario Zechner a055fd4481 WIP: Refactor agent package - not compiling
- Renamed AppMessage to AgentMessage throughout
- New agent-loop.ts with AgentLoopContext, AgentLoopConfig
- Removed transport abstraction, Agent now takes streamFn directly
- Extracted streamProxy to proxy.ts utility
- Removed agent-loop from pi-ai (now in agent package)
- Updated consumers (coding-agent, mom) for AgentMessage rename
- Tests updated but some consumers still need migration

Known issues:
- AgentTool, AgentToolResult not exported from pi-ai
- Attachment not exported from pi-agent-core
- ProviderTransport removed but still referenced
- messageTransformer -> convertToLlm migration incomplete
- CustomMessages declaration merging not working properly
2025-12-30 22:42:20 +01:00
Mario Zechner c359023c3f Add Google Gemini CLI and Antigravity OAuth providers
- Add google-gemini-cli provider: free Gemini 2.0/2.5 via Cloud Code Assist
- Add google-antigravity provider: free Gemini 3, Claude, GPT-OSS via sandbox
- Move OAuth infrastructure from coding-agent to ai package
- Fix thinking signature handling for cross-model handoff
- Fix OpenAI message ID length limit (max 64 chars)
- Add GitHub Copilot overflow pattern detection
- Add OAuth provider tests for context overflow and streaming
2025-12-20 21:34:18 +01:00
Mario Zechner 36e17933d5 feat(ai): add Google Cloud Code Assist provider
- Add new API type 'google-cloud-code-assist' for Gemini CLI / Antigravity auth
- Extract shared Google utilities to google-shared.ts
- Implement streaming provider for Cloud Code Assist endpoint
- Add 7 models: gemini-3-pro-high/low, gemini-3-flash, claude-sonnet/opus, gpt-oss

Models use OAuth authentication and have sh cost (uses Google account quota).
OAuth flow will be implemented in coding-agent in a follow-up.
2025-12-20 10:20:30 +01:00
Mario Zechner 8bec289dc6 Remove provider-level tool validation, add validateToolCall helper 2025-12-08 18:04:33 +01:00
Mario Zechner a325c1c7d1 Add context overflow detection utilities
Extract overflow detection logic into reusable utilities:
- isContextOverflowError() to detect overflow from error messages
- isContextOverflowFromUsage() to detect overflow from token usage
- Patterns for Anthropic, OpenAI, Google, xAI, Groq, OpenRouter, llama.cpp, LM Studio

Fixes #129
2025-12-06 21:24:15 +01:00
Mario Zechner 2296dc4052 refactor(ai): improve error handling and stop reason types
- Add 'aborted' as a distinct stop reason separate from 'error'
- Change AssistantMessage.error to errorMessage for clarity
- Update error event to include reason field ('error' | 'aborted')
- Map provider-specific safety/refusal reasons to 'error' stop reason
- Reorganize utility functions into utils/ directory
- Rename agent.ts to agent-loop.ts for better clarity
- Fix error handling in all providers to properly distinguish abort from error
2025-09-18 19:57:13 +02:00
Mario Zechner e2d23a5abb Update AI models and index exports 2025-09-16 01:29:44 +02:00
Mario Zechner e8370436d7 Replace Zod with TypeBox for schema validation
- Switch from Zod to TypeBox for tool parameter schemas
- TypeBox schemas can be serialized/deserialized as JSON
- Use AJV for runtime validation instead of Zod's parse
- Add StringEnum helper for Google API compatibility (avoids anyOf/const patterns)
- Export Type and Static from main package for convenience
- Update all tests and documentation to reflect TypeBox usage
2025-09-16 01:10:40 +02:00
Mario Zechner 35fe8f21e9 feat(ai): Implement Zod-based tool validation and improve Agent API
- Replace JSON Schema with Zod schemas for tool parameter definitions
- Add runtime validation for all tool calls at provider level
- Create shared validation module with detailed error formatting
- Update Agent API with comprehensive event system
- Add agent tests with calculator tool for multi-turn execution
- Add abort test to verify proper handling of aborted requests
- Update documentation with detailed event flow examples
- Rename generate.ts to stream.ts for clarity
2025-09-09 14:58:54 +02:00
Mario Zechner 98a876f3a0 Fix streaming for z-ai in anthropic provider, add preliminary support for tool call streaming. Only reporting argument string deltas, not partial JSON objects 2025-09-09 04:26:56 +02:00
Mario Zechner 4cee070bdd refactor(ai): Simplify API with new streaming interface and model management
- Replace createLLM with getModel/getModels/getProviders functions
- Rename PROVIDERS to MODELS (internal only, not exposed)
- Add streamSimple/completeSimple for unified reasoning interface
- Update README with new API examples and comprehensive documentation
- Remove model registration (models are now fixed from build time)
- Add proper TypeScript typing for provider-specific options
- Document context serialization, cross-provider handoffs, and browser usage
2025-09-03 01:25:19 +02:00
Mario Zechner 66cefb236e Massive refactor of API
- Switch to function based API
- Anthropic SDK style async generator
- Fully typed with escape hatches for custom models
2025-09-02 23:59:36 +02:00
Mario Zechner 004de3c9d0 feat(ai): Add new streaming generate API with AsyncIterable interface
- Implement QueuedGenerateStream class that extends AsyncIterable with finalMessage() method
- Add new types: GenerateStream, GenerateOptions, GenerateOptionsUnified, GenerateFunction
- Create generateAnthropic function-based implementation replacing class-based approach
- Add comprehensive test suite for the new generate API
- Support streaming events with text, thinking, and tool call deltas
- Map ReasoningEffort to provider-specific options
- Include apiKey in options instead of constructor parameter
2025-09-02 18:07:46 +02:00