- Add MetricsCollector class with counters, model call ring buffer, event ring buffer, and active request tracking
- Add system.metrics, system.events, system.activeRequests RPC handlers
- Add GET /health unauthenticated HTTP endpoint for Docker HEALTHCHECK
- Add totalPending() to LaneQueue for queue depth metrics
- Add 20 tests for MetricsCollector
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
- Import resolveOverlayPath from shared.ts
- Add checkOverlayExists check (skip when no FLYNN_ENV, pass/fail for overlay file)
- Insert after checkConfigExists in allChecks array
- All 1087 tests pass, typecheck clean
- Add resolveOverlayPath() that maps FLYNN_ENV to {configDir}/{env}.yaml
- Update loadConfigSafe to pass overlay path through to loadConfig
- All CLI commands using loadConfigSafe() automatically get overlay support
- No FLYNN_ENV = exact same behavior as before (backward compatible)
- Full test suite passes (1087 tests, zero regressions)
- 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
- Create initAgents() function encapsulating AgentConfigRegistry, AgentRouter, SandboxManager init
- Replace ~26 lines in startDaemon() with single initAgents() call
- Lifecycle shutdown handler for sandbox cleanup included in agents.ts
- Zero type errors, routing tests pass
- Move createMessageRouter function (~220 lines) to dedicated routing module
- Add import from ./routing.js in daemon/index.ts
- routing.test.ts passes without modification
- Zero type errors
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>
Check model capabilities via /api/show before sending tools.
Models without 'tools' capability get requests without tools
(they can still answer, just without tool use). Result is cached
per client instance. Defense-in-depth: 'does not support' added
to retry nonRetryablePatterns to avoid wasting retries on
permanent errors.
- Ollama: pass tools to API, parse tool_calls responses, handle thinking field from reasoning models (deepseek-r1, glm-4.7-flash)
- llama.cpp: pass tools via OpenAI-compatible endpoint, parse tool_calls, accumulate streaming tool call deltas
- Both clients now set stopReason to 'tool_use' when tool calls are present
- Tests: 12 new tests (8 Ollama + 5 llama.cpp, total 983→995)
- assembleSystemPrompt() now injects '# Runtime Context' with current date/time
- New system.info tool: date, time, hostname, platform, arch, uptime, memory, Node.js version
- Tool available in all profiles (minimal/messaging/coding/full)
- 983 tests passing (+7 new)
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.
Implements apply_patch equivalent: a single tool call can make multiple
line-based edits (replacements, insertions, deletions) across one or more
files. Hunks are applied bottom-up to preserve line numbers.
Includes 10 tests covering replacement, multi-hunk, insertion, deletion,
multi-file, overlapping hunks error, OOB error, and edge cases.
Two issues prevented the GitHub Models fallback from working:
1. The X-GitHub-Api-Version: 2022-11-28 header caused '400 invalid
apiVersion' errors. The Copilot chat completions endpoint does not
use this header — removed from both constructor and rebuildClient.
2. The anthropicToGitHubModel mapping was incomplete: it only knew
three models and the generic date-stripping fallback produced wrong
names (e.g. 'claude-sonnet-4-5' instead of 'claude-sonnet-4.5').
GitHub Copilot uses dots for sub-versions, not hyphens.
Updated with explicit mappings for all current models (sonnet 4,
4.5; opus 4, 4.5, 4.6; haiku 4.5) and a smarter generic fallback
that converts digit-hyphen-digit to digit.digit at the end.
3. createClientFromConfig now auto-maps Anthropic-style model names
when the provider is 'github', so users can copy model names from
their Anthropic config into fallback blocks without manual renaming.
The TUI was building its own ModelRouter with a duplicated client factory
that lacked auto same-model fallback, local_providers resolution, retry
config, and per-tier fallback logic. When Anthropic failed, it skipped
GitHub Models and fell straight to the local Ollama model.
Replace the duplicated ~50-line createClient + router setup in tui.ts
with a single call to the daemon's createModelRouter(), which already
handles all of these correctly. This removes ~50 lines of duplicated
code and ensures TUI and daemon have identical fallback behavior.
Previously these tools were only available in daemon mode. Now TUI mode
also registers web search tools (when credentials are configured) and
process management tools with proper cleanup on exit.
When a tier uses the Anthropic provider and has no user-configured inline
fallback, automatically insert a GitHub Models client for the equivalent
model as a tier fallback. This ensures the same model is tried via an
alternative provider before degrading to the global fallback chain (which
may be a much weaker local model).
Mapping: claude-sonnet-4-20250514 → claude-sonnet-4, etc.
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>
Add 8 new agent-callable tools (sessions.list/history/create/delete,
agents.list, message.send, cron.list/trigger) and sanitize tool names
at the API boundary (dots → underscores) to comply with Anthropic's
`^[a-zA-Z0-9_-]{1,128}` requirement. Reverse-maps sanitized names
back to internal names for hook callbacks and tool execution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reads the optional fallback field from each tier's config and builds
a tierFallbacks map passed to ModelRouter at startup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The router now accepts a tierFallbacks map so each model tier can have
its own fallback providers. Tier fallbacks are tried before the global
fallback chain in both chat() and chatStream().
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>
whatsapp-web.js lacks proper ESM named exports, causing SyntaxError on
import. Switch to default import with destructuring, use InstanceType
for the Client type annotation, and update test mock to provide both
default and named exports.
- Add SPA shell with hash-based router, sidebar navigation, and WebSocket RPC client
- Add dashboard page with system health cards, channel status, and auto-refresh
- Add chat page with session selector, streaming tool events, and markdown rendering
- Add sessions page with list, history viewer, and delete functionality
- Add settings page with hook pattern editor, tool list, and config viewer
- Add backend handlers: sessions.delete, sessions.switch, system.channels, system.usage
- Wire channelRegistry into gateway server for channel status reporting
- Extend static file server with .mjs, .png, .ico, .woff2 content types
Extends the gateway wire protocol with GatewayAttachment type and
attachment event. agent.send handler now accepts optional attachments
parameter and converts them for the agent pipeline. Includes 5 new
tests for protocol and handler layers.
Introduces OutboundAttachment type on OutboundMessage, an
OutboundAttachmentCollector (push/drain pattern), and a media.send
tool that queues files for outbound delivery. Each channel adapter
(Telegram, Discord, Slack, WhatsApp) sends attachments after the
text reply. Includes 15 tests for collector and tool.
Provides a factory createImageAnalyzeTool(modelClient) that sends images
to a vision-capable model and returns a textual analysis. Includes 15
tests covering base64, URL, multi-image, error, and edge cases.
GitHubModelsClient now lazily resolves tokens at first API call. If no
token exists (env var, stored OAuth, or config), it triggers the OAuth
device flow automatically via an onLoginRequired callback wired in both
the TUI and daemon entry points.
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
Widen Message.content from string to string | MessageContentPart[] to support
multimodal content. Add Attachment type to channel layer, media conversion
utilities, and image extraction to all channel adapters (Telegram, Discord,
Slack, WhatsApp). Update all model clients (Anthropic, OpenAI, Gemini, Bedrock)
to convert structured content to provider-specific formats. Fix downstream
consumers (tokens, compaction, TUI, local models) to handle the widened type
via getMessageText() helper.
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.
Add BrowserManager (puppeteer-core) with page pool and auto-detection of
Chrome/Chromium. Six tools: browser.navigate, browser.screenshot,
browser.click, browser.type, browser.content, browser.eval. Feature is
opt-in (browser.enabled defaults to false). Add to coding tool profile.
Includes 22 unit tests for manager and all tools.
Slack: add requireMention option, resolve bot user ID on connect.
Telegram: add group chat mention/reply-to-bot detection, strip @mention
from message text, default requireMention=true for groups.
WhatsApp: add allowedGroupIds for group chat support, mention detection
via mentionedIds and body text, strip bot mention from messages.
Support ?token= query parameter as a fallback for WebSocket clients that
cannot set Authorization headers (e.g. browsers). Add authHttp option to
GatewayServer so token auth can be applied to HTTP requests too, returning
401 with WWW-Authenticate header on failure.
Add native GeminiClient using @google/generative-ai SDK and BedrockClient
using @aws-sdk/client-bedrock-runtime. Replace the previous Gemini fallback
(OpenAI-compatible shim) with the real implementation. Add OpenRouter as a
provider option (OpenAI-compatible with custom baseURL). Update model costs,
doctor CLI checks, and client factory tests.
William Valentin