- Add capabilities.test.ts (18 tests) for supportsAudioInput()
- Add 15 audio tests to media.test.ts (hasAudio, stripAudioParts, attachmentToAudioSource)
- Add estimateAudioTokens() to tokens.ts (base64→bytes→duration→tokens)
- Update estimateMessageTokens() to include audio content parts
- Add 5 audio token tests to tokens.test.ts
- Add supports_audio config override to model schema
- Wire supports_audio from tier config through routing to capability check
Total tests: 1369 (was 1331, +38 audio-related)
- Add createAudioTranscribeTool with OpenAI/Groq/Ollama/llama.cpp provider support
- Refactor audio config schema to nested audio.enabled + audio.provider structure
- Move audio tool registration to initTools() for conditional enablement
- Fix duplication bug in audio-transcribe.ts URL download handler
- Support base64 data and URL-based audio input with format detection
Allow cron jobs to specify a `model_tier` field that controls which LLM
tier handles the job, without needing separate agent configs. Precedence:
cron job model_tier > agent config > global primary_tier > 'default'.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract MODEL_PROVIDERS const from config schema as single source of truth
for provider names. PROVIDER_NAMES in TUI commands now imports from schema
instead of maintaining a hardcoded list. Adds tests verifying sync.
Updates README TUI Commands section with /model hot-swap documentation,
supported providers, and runtime model switching examples.
Local LLMs often get stuck calling the same tool repeatedly because they
lack the sophistication to synthesize results. The agent loop had no
safeguard — it re-executed whatever the model requested up to 10 times.
Add fingerprint-based loop detection: if the same tool+args combination
repeats 3 consecutive times, break the loop and return the last results.
Also add agents.max_iterations to the config schema so the iteration
limit is user-configurable (default: 10).
Add three new Google service integrations following the established
Gmail/GCal pattern:
- Google Docs (docs.list, docs.search, docs.read): list, search, and
read document content as plain text via Docs + Drive APIs
- Google Drive (drive.list, drive.search, drive.read): list, search,
and read files with export support for Workspace files (Docs→text,
Sheets→CSV, Slides→text)
- Google Tasks (tasks.lists, tasks.list): list task lists and tasks
with status, due dates, and notes
Each service has its own config section, OAuth auth command, tool
policy group, and test suite (53 new tests). The setup wizard now
offers to configure all Google services together and run OAuth auth
flows automatically after saving config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add calendar.today, calendar.list, calendar.search tools mirroring the
Gmail tool pattern. Includes gcal-auth CLI command, config schema, tool
policy entries (messaging/coding profiles + group:gcal), and 17 tests.
Also wires up gmail and gcal tool registration in the daemon and TUI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace console.debug/log/warn calls in model router, retry, and daemon
startup with a structured logger that respects a configurable log_level.
Default level is 'info', suppressing verbose fallback debug messages in
the TUI while keeping them available via config when needed.
- Add src/logger.ts with debug/info/warn/error/silent levels
- Wire log_level into config schema (default: 'info')
- Initialize log level in both daemon and TUI startup paths
- Convert all console.debug in router.ts and retry.ts to logger.debug
- Convert console.log/warn in daemon/models.ts to logger.info/warn
- Add deepMerge utility for recursive object merging (arrays replace, not concat)
- Extend loadConfig with optional overlayPath parameter
- Merge happens before env var expansion and Zod validation
- Add 6 deepMerge unit tests and 4 overlay integration tests
- Re-export deepMerge from config/index.ts
- All 1087 existing tests still pass
Adds zhipuai as a new provider using the OpenAI-compatible API at
api.z.ai. Supports api_key config or ZHIPUAI_API_KEY env var, with
optional endpoint override.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New ChannelAdapter that monitors Gmail via Google Cloud Pub/Sub push
notifications with polling fallback. Supports OAuth2 auth, configurable
watch labels, template rendering with email metadata placeholders
(from, to, subject, snippet, date, id, labels).
Wired into daemon lifecycle and gateway (POST /gmail/push endpoint).
Includes 16 tests covering auth, templates, push notifications, and
channel routing.
Five additive features with no breaking changes:
- Tool groups: group:fs, group:runtime, group:web, group:memory syntactic
sugar for allow/deny lists in tool policy config
- Typing indicators: Discord sendTyping() and WhatsApp sendStateTyping()
on message receipt for better UX feedback
- Session pruning: TTL-based auto-cleanup via sessions.ttl config with
hourly daemon timer and SQLite GROUP BY pruning
- /verbose command: TUI command parser toggle for raw streaming display
- !!think prefix: per-message extended thinking mode wired through
Anthropic (budget_tokens), OpenAI/GitHub (reasoning_effort), and
Gemini (thinkingConfig) providers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Each model tier (fast, default, complex, local) can now specify an
optional fallback provider config that the router will try before
falling through to the global fallback chain.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a new 'github' model provider backed by the Copilot API
(api.githubcopilot.com), with OAuth device flow for authentication.
- New src/auth/github.ts: device flow login, token storage at
~/.config/flynn/auth.json with 0600 permissions
- New src/models/github.ts: OpenAI-compatible client with streaming,
tool calling, and Copilot-specific headers
- Add 'github' to provider enum in config schema
- Register provider in daemon factory and TUI client factory
- Refactor TUI to use provider-agnostic client factory (was hardcoded
to AnthropicClient for all tiers)
- Add /login command to TUI for interactive OAuth authorization
- Add Copilot model cost tracking entries
Update config schema with server auth fields (token, tailscale_identity,
auth_http), channel mention settings, browser config, and openrouter/bedrock
provider enum values. Wire GeminiClient, BedrockClient, OpenRouter into
createClientFromConfig. Initialize BrowserManager and register browser tools
in daemon startup. Pass auth config and channel mention settings through to
gateway and adapters. Add puppeteer-core, @google/generative-ai, and
@aws-sdk/client-bedrock-runtime dependencies.
Implement a three-tier skill system (bundled/managed/workspace) that
extends Flynn's abilities via SKILL.md instructions injected into the
system prompt.
- SkillManifest/Skill types with requirements gating (OS, binaries, env)
- Loader: discovers skills from directories, validates manifests,
checks system requirements, infers manifest from SKILL.md if missing
- SkillRegistry: holds skills, generates system prompt additions,
supports override by name (workspace > managed > bundled)
- SkillInstaller: copies/removes skills in managed directory with
upgrade support
- Config: add skills.workspace_dir, managed_dir, bundled_dir options
- Daemon: loads all skills at startup, injects available skill
instructions into the system prompt
- Tests: 45 new tests (loader 22, registry 11, installer 12)
Implement Model Context Protocol (MCP) support so Flynn can spawn MCP
server processes, discover their tools, and make them available to the
agent alongside builtin tools.
- McpClient: wraps @modelcontextprotocol/sdk with StdioClientTransport
for process lifecycle, tool discovery (listTools), and invocation (callTool)
- McpManager: lifecycle management for multiple MCP servers with
startAll/stopAll/restart, tool bridging into ToolRegistry
- Bridge: converts MCP tools to Flynn Tool interface with mcp:<server>:<tool>
namespacing to avoid collisions with builtin tools
- Config: add env and cwd fields to mcp server schema
- ToolRegistry: add unregister() method for MCP server cleanup
- Daemon: wire McpManager into startup and shutdown lifecycle
- Tests: 28 new tests (bridge, manager, registry unregister)
William Valentin