agent/pi
1
0
Fork 0
mirror of https://github.com/earendil-works/pi.git synced 2026-06-18 15:54:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,878 Commits 32 Branches 288 Tags
070ef9c771ddfa625c5df438479deea00f9be708
Commit Graph

43 Commits

  • fix(ai): clean up openai-codex models and token limits 
    - Remove model aliases (gpt-5, gpt-5-mini, gpt-5-nano, codex-mini-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-chat-latest)
- Fix context window from 400k to 272k tokens to match Codex CLI defaults
- Keep maxTokens at 128k (original value)
- Simplify reasoning effort clamping

closes #536
    Mario Zechner · 2026-01-07 20:39:46 +01:00
    39fa25eb67
  • fix(ai): clean up openai-codex models and token limits
    Zhou Rui · 2026-01-07 23:09:20 +08:00
    d893ba7f20
  • fix: add accurate pricing for openai-codex OAuth models (#501) 
    Previously all openai-codex models had pricing set to 0, causing the
TUI to always show $0.00 for cost tracking.

Updated pricing based on OpenAI Standard tier rates:
- gpt-5.2/gpt-5.2-codex: $1.75/$14.00 per 1M tokens
- gpt-5.1/gpt-5.1-codex/gpt-5.1-codex-max: $1.25/$10.00 per 1M tokens
- gpt-5/gpt-5-codex: $1.25/$10.00 per 1M tokens
- codex-mini-latest: $1.50/$6.00 per 1M tokens
- gpt-5-mini/gpt-5.1-codex-mini/gpt-5-codex-mini: $0.25/$2.00 per 1M tokens
- gpt-5-nano: $0.05/$0.40 per 1M tokens

Source: https://platform.openai.com/docs/pricing
    Ben Vargas · 2026-01-06 17:45:09 +01:00
    e80a924292
  • fix: clean up Codex thinking level handling 
    - Remove per-thinking-level model variants (gpt-5.2-codex-high, etc.)
- Remove thinkingLevels from Model type
- Provider clamps reasoning effort internally
- Omit reasoning field when thinking is off

fixes #472
    Mario Zechner · 2026-01-05 21:58:26 +01:00
    0b9e3ada0c
  • fix: codex thinking handling
    Ben Vargas · 2026-01-05 21:55:47 +01:00
    02b72b49d5
  • feat(ai): add OpenAI Codex OAuth + responses provider
    Ahmed Kamal · 2026-01-04 21:11:19 +02:00
    1650041a63
  • fix: update cost values for input, output, and cacheRead in model configs
    Anton Kuzmenko · 2026-01-03 01:11:03 +01:00
    6467e70995
  • 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
    Anton Kuzmenko · 2026-01-03 01:11:03 +01:00
    214e7dae15
  • Update ai package CHANGELOG.md for v0.30.2+ changes 
    Part of #378
    Mario Zechner · 2025-12-30 23:09:13 +01:00
    9b2d22d26d
  • Migrate zai provider from Anthropic to OpenAI-compatible API 
    - Migrate glm-4.5, glm-4.5-air, glm-4.5-flash, glm-4.6, glm-4.7 from anthropic-messages to openai-completions API
- Updated baseUrl from https://api.z.ai/api/anthropic to https://api.z.ai/api/coding/paas/v4
- Added compat setting to disable developer role for zai models
- Filter empty text blocks in openai-completions to avoid zai API validation errors
- Fixed zai provider tests to use OpenAI-style options (reasoningEffort)
    Anton Kuzmenko · 2025-12-29 11:54:10 -08:00
    0250b7ac03
  • fix: update zAI models to use anthropic API and filter empty thinking blocks in messages
    Anton Kuzmenko · 2025-12-28 16:31:32 -08:00
    31cbbd211c
  • fix: update zai model API and baseUrl in generate-models script
    Anton Kuzmenko · 2025-12-28 13:29:36 -08:00
    93ea8298ab
  • Make model generation deterministic by sorting providers and models
    Duncan Ogilvie · 2025-12-27 13:58:51 +01:00
    bf6da8c72f
  • Add Gemini 3 preview models to google-gemini-cli provider 
    - Add gemini-3-pro-preview and gemini-3-flash-preview to Cloud Code Assist
- Handle thinkingLevel config for Gemini 3 (vs thinkingBudget for Gemini 2.x)
- Gemini 3 Pro: LOW/HIGH levels only
- Gemini 3 Flash: all four levels (MINIMAL/LOW/MEDIUM/HIGH)
    Luke Foster · 2025-12-20 22:10:47 -06:00
    ee9b498380
  • 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
    Mario Zechner · 2025-12-20 21:34:18 +01:00
    c359023c3f
  • 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.
    Mario Zechner · 2025-12-20 10:20:30 +01:00
    36e17933d5
  • feat: implement thinking for some more copilot models (#234) 
    Signed-off-by: StarLight842 <mail@aadishv.dev>
    Aadish Verma · 2025-12-19 04:42:23 +01:00
    314ef34ebc
  • GitHub Copilot: auto-enable models, fix gpt-5 API, normalize tool call IDs 
    - Auto-enable all models after /login via POST /models/{model}/policy
- Use openai-responses API for gpt-5/o3/o4 models (not accessible via completions)
- Normalize tool call IDs when switching between github-copilot models with different APIs
  (fixes #198: openai-responses generates 450+ char IDs with special chars that break other models)
- Update README with streamlined GitHub Copilot docs
    Mario Zechner · 2025-12-15 20:06:11 +01:00
    c5543f7586
  • Add GitHub Copilot support (#191) 
    - OAuth login for GitHub Copilot via /login command
- Support for github.com and GitHub Enterprise
- Models sourced from models.dev (Claude, GPT, Gemini, Grok, etc.)
- Dynamic base URL from token's proxy-ep field
- Use vscode-chat integration ID for API compatibility
- Documentation for model enablement at github.com/settings/copilot/features

Co-authored-by: cau1k <cau1k@users.noreply.github.com>
    Mario Zechner · 2025-12-15 19:05:17 +01:00
    b66157c649
  • fix: model context windows
    cau1k · 2025-12-15 00:17:59 -05:00
    1871962e2e
  • feat: added filter for generate-models and regenerated 
    - blacklisted gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-3.5-turbo-0613,
gpt-4, gpt-4-0613
    cau1k · 2025-12-14 22:26:43 -05:00
    7d4cdd09c3
  • feat: generate models base on copilot /models endpoint, requires GH token
    cau1k · 2025-12-14 18:42:57 -05:00
    5f590b7c53
  • feat: models.dev in generate models - too many deprecated models 
    could have opted for a whitelist but we'll just fetch from the copilot
/models endpoint
    cau1k · 2025-12-14 17:47:42 -05:00
    17ebb9a19d
  • feat: initial impl 
    - add GitHub Copilot model discovery (env token fallback, headers,
compat) plus fallback list and quoted provider keys in generated map
- surface Copilot provider end-to-end (KnownProvider/default, env+OAuth
token refresh/save, enterprise base URL swap, available only when
creds/env exist)
- tweak interactive OAuth UI to render instruction text and prompt
placeholders

gpt-5.2-high took about 35 minutes. It had a lot of trouble with `npm
check`  and went off on a "let's adjust every tsconfig" side quest.
Device code flow works, but the ai/scripts/generate-models.ts impl is
wrong as models from months ago are missing and only those deprecated
are accessible in the /models picker.
    cau1k · 2025-12-14 17:18:13 -05:00
    ccae7a4e0e
  • Add Mistral as AI provider 
    - Add Mistral to KnownProvider type and model generation
- Implement Mistral-specific compat handling in openai-completions:
  - requiresToolResultName: tool results need name field
  - requiresAssistantAfterToolResult: synthetic assistant message between tool/user
  - requiresThinkingAsText: thinking blocks as <thinking> text
  - requiresMistralToolIds: tool IDs must be exactly 9 alphanumeric chars
- Add MISTRAL_API_KEY environment variable support
- Add Mistral tests across all test files
- Update documentation (README, CHANGELOG) for both ai and coding-agent packages
- Remove client IDs from gemini.md, reference upstream source instead

Closes #165
    Mario Zechner · 2025-12-10 20:36:19 +01:00
    99b4b1aca0
  • Release v0.12.10
    Mario Zechner · 2025-12-04 20:51:57 +01:00
    c7585e37c9
  • mom: add centralized logging, usage tracking, and improve prompt caching 
    Major improvements to mom's logging and cost reporting:

Centralized Logging System:
- Add src/log.ts with type-safe logging functions
- Colored console output (green=user, yellow=mom, dim=details)
- Consistent format: [HH:MM:SS] [context] message
- Replace scattered console.log/error calls throughout codebase

Usage Tracking & Cost Reporting:
- Track tokens (input, output, cache read/write) and costs per run
- Display summary at end of each run in console and Slack thread
- Example: 💰 Usage: 12,543 in + 847 out (5,234 cache read) = $0.0234

Prompt Caching Optimization:
- Move recent messages from system prompt to user message
- System prompt now mostly static (only changes with memory files)
- Enables effective use of Anthropic's prompt caching
- Significantly reduces costs on subsequent requests

Model & Cost Improvements:
- Switch from Claude Opus 4.5 to Sonnet 4.5 (~40% cost reduction)
- Fix Claude Opus 4.5 cache pricing in ai package (was 3x too expensive)
- Add manual override in generate-models.ts until upstream fix merges
- Submitted PR to models.dev: https://github.com/sst/models.dev/pull/439

UI/UX Improvements:
- Extract actual text from tool results instead of JSON wrapper
- Cleaner Slack thread formatting with duration and labels
- Tool args formatting shows paths with offset:limit notation
- Add chalk for colored terminal output

Dependencies:
- Add chalk package for terminal colors
    Mario Zechner · 2025-11-26 18:04:16 +01:00
    213bc4df1c
  • Add ANSI-aware word wrapping to TUI components 
    - Created shared wrapTextWithAnsi() function in utils.ts
- Handles word-based wrapping while preserving ANSI escape codes
- Properly tracks active ANSI codes across wrapped lines
- Supports multi-byte characters (emoji, surrogate pairs)
- Updated Markdown and Text components to use shared wrapping
- Removed duplicate wrapping logic (158 lines total)
    Mario Zechner · 2025-11-18 22:26:24 +01:00
    38ac29acfb
  • feat(coding-agent): add OAuth authentication for Claude Pro/Max 
    - Add /login and /logout commands for OAuth flow
- OAuth tokens stored in ~/.pi/agent/oauth.json with 0600 permissions
- Auto-refresh tokens when expired (5min buffer)
- Priority: OAuth > ANTHROPIC_OAUTH_TOKEN env > ANTHROPIC_API_KEY env
- Fix model selector async loading and re-render
- Add bracketed paste support to Input component for long codes
- Update README.md with OAuth documentation
- Add implementation docs and testing checklist
    Mario Zechner · 2025-11-18 17:33:33 +01:00
    587d7c39a4
  • Add gpt-5.1-codex to model list
    Mario Zechner · 2025-11-16 22:35:09 +01:00
    e0c2745989
  • regen models and openrouter auto
    Denis Badurina · 2025-11-13 10:20:38 +01:00
    1ecf02020d
  • Don't dedup models across providers.
    Mario Zechner · 2025-10-29 20:36:54 +01:00
    129ec6063b
  • feat(ai): Add zAI provider support 
    - Add 'zai' as a KnownProvider type
- Add ZAI_API_KEY environment variable mapping
- Generate 4 zAI models (glm-4.5-air, glm-4.5v, etc.) using anthropic-messages API
- Add comprehensive test coverage for zAI provider in generate.test.ts and empty.test.ts
- Models support reasoning/thinking capabilities and tool calling
    Mario Zechner · 2025-09-07 00:09:15 +02:00
    d073953ef7
  • 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
    Mario Zechner · 2025-09-03 01:25:19 +02:00
    4cee070bdd
  • Massive refactor of API 
    - Switch to function based API
- Anthropic SDK style async generator
- Fully typed with escape hatches for custom models
    Mario Zechner · 2025-09-02 23:59:36 +02:00
    66cefb236e
  • feat(ai): Add gpt-5-chat-latest model to generated models 
    - Added hardcoded gpt-5-chat-latest model since it's not in models.dev yet
- Model has image input support and proper pricing configuration
    Mario Zechner · 2025-09-02 01:32:26 +02:00
    0fbb0921bb
  • feat(ai): Fetch Anthropic, Google, and OpenAI models from models.dev instead of OpenRouter 
    - Updated generate-models.ts to fetch these providers directly from models.dev API
- OpenRouter now only used for xAI and other third-party providers
- Fixed test model IDs to match new model names from models.dev
- Removed unused import from google.ts
    Mario Zechner · 2025-09-02 01:18:59 +02:00
    efaa5cdb39
  • feat(ai): Rename package to @mariozechner/pi-ai and improve documentation 
    - Changed package name from @mariozechner/ai to @mariozechner/pi-ai
- Fixed generate-models.ts to fetch from models.dev API instead of local file
- Completely rewrote README with practical examples:
  - Image input with base64 encoding
  - Proper tool calling with context management
  - Streaming with completion indicators
  - Abort signal usage
  - Provider-specific options (reasoning/thinking)
  - Custom model definitions for local/self-hosted LLMs
  - Environment variables explanation
- Bumped version to 0.5.9 and published
    Mario Zechner · 2025-08-30 21:41:22 +02:00
    d46a98ec10
  • feat(ai): Add image input tests for vision-capable models 
    - Added image tests to OpenAI Completions (gpt-4o-mini)
- Added image tests to Anthropic (claude-sonnet-4-0)
- Added image tests to Google (gemini-2.5-flash)
- Tests verify models can process and describe the red circle test image
    Mario Zechner · 2025-08-30 18:37:17 +02:00
    796e48b80e
  • refactor(ai): Update LLM implementations to use Model objects 
    - LLM constructors now take Model objects instead of string IDs
- Added provider field to AssistantMessage interface
- Updated getModel function with type-safe model ID autocomplete
- Fixed Anthropic model ID mapping for proper API aliases
- Added baseUrl to Model interface for provider-specific endpoints
- Updated all tests to use getModel for model instantiation
- Removed deprecated models.json in favor of generated models
    Mario Zechner · 2025-08-30 00:21:03 +02:00
    f9d688d577
  • fix(ai): Deduplicate models and add Anthropic aliases 
    - Add proper Anthropic model aliases (claude-opus-4-1, claude-sonnet-4-0, etc.)
- Deduplicate models when same ID appears in both models.dev and OpenRouter
- models.dev takes priority over OpenRouter for duplicate IDs
- Fix test to use correct claude-3-5-haiku-latest alias
- Reduces Anthropic models from 11 to 10 (removed duplicate)
    Mario Zechner · 2025-08-29 23:34:01 +02:00
    d61d09b88d
  • refactor(ai): Implement unified model system with type-safe createLLM 
    - Add Model interface to types.ts with normalized structure
- Create type-safe generic createLLM function with provider-specific model constraints
- Generate models from OpenRouter API and models.dev data
- Strip provider prefixes for direct providers (google, openai, anthropic, xai)
- Keep full model IDs for OpenRouter-proxied models
- Clean separation: types.ts (Model interface), models.ts (factory logic), models.generated.ts (data)
- Remove old model scripts and unused dependencies
- Rename GeminiLLM to GoogleLLM for consistency
- Add tests for new providers (xAI, Groq, Cerebras, OpenRouter)
- Support 181 tool-capable models across 7 providers with full type safety
    Mario Zechner · 2025-08-29 23:19:47 +02:00
    c7618db3f7
  • feat(ai): Add auto-generated TypeScript models with factory function 
    - Generate models.generated.ts from models.json with proper types
- Categorize providers: OpenAI (Responses), OpenAI-compatible, Anthropic, Gemini
- Create createLLM() factory with TypeScript overloads for type safety
- Auto-detect base URLs and environment variables for providers
- Support 353 models across 39 providers with full autocompletion
- Exclude generated file from git (rebuilt on npm build)
    Mario Zechner · 2025-08-25 21:31:29 +02:00
    da66a97ea7