b9601b50ab
feat(daemon): wire tool registry and executor into agent
2026-02-05 17:49:32 -08:00
4f87643341
feat(agent): add iterative tool use loop with max iterations
...
Rewrites NativeAgent.process() from single-turn to an iterative tool
loop. When toolRegistry and toolExecutor are provided, the agent calls
the model, executes any requested tool calls, feeds results back, and
loops until the model returns a text response or max iterations hit.
- Backward compatible: works exactly as before without tools
- Supports onToolUse callback for frontend status display
- Max iterations (default 10) prevents infinite loops
- Handles multiple tool calls per model response
- 5 new tests (8 total)
2026-02-05 17:48:38 -08:00
96ade25e98
feat(models): add tool use support to OpenAIClient
2026-02-05 17:44:04 -08:00
36c1cfc768
feat(models): add tool use support to AnthropicClient
2026-02-05 17:44:00 -08:00
c96165fb2f
feat(tools): add barrel exports and allBuiltinTools list
2026-02-05 17:40:13 -08:00
b00706325b
feat: add tool framework foundation (types, registry, executor, shell tool, model types, SOUL.md)
...
- Task 0: SOUL.md + loadSystemPrompt() in daemon
- Task 1: Tool type definitions (Tool, ToolCall, ToolResult, etc.)
- Task 2: ToolRegistry with Anthropic/OpenAI serialization
- Task 3: ToolExecutor with hooks, timeout, truncation
- Task 4: shell.exec builtin tool
- Task 8: Model types updated for tool use (ToolDefinition, ModelToolCall, etc.)
- Task 15: Model index exports for tool types
2026-02-05 17:39:40 -08:00
32dd3ad728
feat(tools): add file read/write/edit/list builtin tools
2026-02-05 17:39:20 -08:00
d2a597d49d
fix: add model parameter to LlamaCppClient requests
2026-02-05 15:51:33 -08:00
2fc07b4bca
feat: add timestamps to session messages
2026-02-05 15:51:32 -08:00
5558687ab9
feat: wire up num_gpu config and updated clients to daemon and TUI
2026-02-05 15:51:30 -08:00
c1f64d6ded
feat: enhance TUI with colors, command hints, and improved rendering
2026-02-05 15:51:29 -08:00
dbf1acd822
feat: add streaming support and num_gpu option to Ollama client
2026-02-05 15:51:28 -08:00
a2e1f73493
feat: wire up localProviders config to TUI
...
Add LlamaCppClient to imports and handle llamacpp provider in createModelRouter.
Pass localProviders and currentLocalProvider configuration to MinimalTui to enable
the /backend command to access alternate provider configs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 13:37:26 -08:00
f722cf2bf0
feat: add /backend command handler to MinimalTui
2026-02-05 13:36:36 -08:00
465b4a0c3c
feat: add /backend command parsing
...
Add support for /backend command to show or switch local backend providers. Follows the same pattern as /model command with optional argument support.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 13:35:10 -08:00
dbeaa78e2c
feat: add setLocalClient and getLocalProviderName to ModelRouter
2026-02-05 13:34:25 -08:00
0528b895b0
feat: add local_providers to config schema
2026-02-05 13:33:50 -08:00
d86710577d
feat: wire up LlamaCppClient to model router
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 13:20:20 -08:00
8e7fa24fd6
feat: add clear error message when llama-server not running
2026-02-05 13:17:56 -08:00
e8079347c7
feat: add streaming support to LlamaCppClient
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 13:15:18 -08:00
a20156f8db
feat: add LlamaCppClient with basic chat support
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 13:11:56 -08:00
f891c7aee8
fix: add API key/auth token support across all model clients
2026-02-05 10:56:40 -08:00
747a7f44a2
feat(tui): add streaming, scroll, and model switching to fullscreen App
2026-02-05 10:56:27 -08:00
0490d2fe39
feat(tui): add markdown rendering and scroll support to MessageList
2026-02-05 10:56:23 -08:00
7391b50d6d
feat(tui): enhance StatusBar with token usage and streaming indicator
2026-02-05 10:56:19 -08:00
83a750f484
feat(tui): update fullscreen config for model router
2026-02-05 10:56:16 -08:00
d1d6054deb
feat(tui): pass modelRouter to both TUI modes
2026-02-05 10:56:11 -08:00
f115407af3
feat(tui): add streaming and model switching to minimal mode
2026-02-05 10:53:41 -08:00
435146344e
feat(tui): add unified command parser with model switching
2026-02-05 10:52:49 -08:00
da2bb57488
feat(tui): add markdown rendering utility
2026-02-05 10:52:00 -08:00
9a48c39b07
feat(models): add streaming and tier switching to ModelRouter
2026-02-05 10:48:41 -08:00
896a0da10e
feat(models): add streaming support to AnthropicClient
2026-02-05 10:47:42 -08:00
1f0cf28d1f
feat(models): add streaming types for chat responses
2026-02-05 10:46:53 -08:00
fb7575f850
refactor: integrate SessionManager into daemon and agent
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 00:43:09 -08:00
f671ea5ab5
feat: add fullscreen TUI mode with Ink React components
2026-02-05 00:41:17 -08:00
53a8bd97eb
feat: add Ink-based fullscreen TUI components
2026-02-05 00:39:53 -08:00
c0deeb5cf0
feat: add TUI entry point with minimal readline mode
2026-02-05 00:37:40 -08:00
f792f8407a
feat: add minimal TUI with readline interface
2026-02-05 00:36:16 -08:00
2f1c302d85
feat: add SessionManager for multi-frontend session handling
2026-02-05 00:34:25 -08:00
6e6c263e14
feat: integrate model router, session persistence, and hook engine
...
- NativeAgent now loads/saves messages to SessionStore
- Daemon creates ModelRouter with fallback chain support
- Telegram bot handles confirmation callbacks from HookEngine
- Session data stored in ~/.local/share/flynn/sessions.db
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-05 00:05:42 -08:00
26bd6ce65d
feat: add model router with fallback chain support
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 00:29:52 -08:00
298f87615d
feat: add Telegram confirmation UI components
...
Implements Phase 2 Task 7 - Telegram Confirmation UI:
- formatConfirmationMessage(): formats tool and args into readable message
- createConfirmationKeyboard(): creates approve/deny inline keyboard
- parseConfirmationCallback(): parses callback data from button clicks
- Full test coverage with vitest
All tests passing.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 00:29:32 -08:00
782163cda6
feat: add hook engine for sensitive operation confirmation
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 00:28:18 -08:00
10c848ca2a
feat: add SQLite session persistence
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 00:27:12 -08:00
bb16732562
feat: add Ollama client for local LLM support
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-03 00:27:09 -08:00
633cfcf713
feat: add OpenAI client for fallback support
...
Implements ModelClient interface with OpenAI SDK to support GPT models
as fallback when local inference is unavailable. Includes tests with
mocked OpenAI API responses.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-02 21:10:46 -08:00
b6b85f07d0
feat: wire daemon, agent, and telegram bot together
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-02 21:02:50 -08:00
d0fe4c5b35
feat: add Telegram bot frontend with message handling
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-02 20:59:17 -08:00
69309e58bc
feat: add native agent with conversation history
2026-02-02 20:56:46 -08:00
70c3960527
feat: add daemon skeleton with lifecycle management
...
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-02 20:56:45 -08:00
William Valentin