b22d6fa0ce
feat(gateway): include audio + web_search in system.services
2026-02-14 09:27:42 -08:00
4bb4ad4fba
fix(ui): show services in settings page
2026-02-14 09:19:57 -08:00
6212603821
fix(models): tighten audio capability + correct openai oauth content
2026-02-14 00:43:48 -08:00
4bb8c88fbe
feat(auth): add anthropic api key storage and cli auth
2026-02-14 00:43:12 -08:00
0493660e7d
feat(gateway): add system.services and dashboard services grid
2026-02-14 00:42:41 -08:00
151b48310e
orchestrator: recover from context overflow on fallback
2026-02-13 21:19:02 -08:00
944b2c916a
routing: fast-path voice when transcription not configured
2026-02-13 18:35:04 -08:00
7df0569a39
feat(models): add Z.AI (GLM) credential integration and setup flow
...
Implement first-class Z.AI credential storage and authentication:
- New auth provider: src/auth/zai.ts for Z.AI API key management
- New CLI command: flynn zai-auth to store Z.AI API keys
- New TUI command: /login zai for interactive credential entry
- Modified src/auth/index.ts to register zai provider
- Modified src/cli/index.ts to register zai-auth command
- Modified src/cli/setup/providers.ts to include Z.AI in setup wizard
- Modified src/daemon/models.ts to support zhipuai use_oauth flag
- Modified src/daemon/clientFactory.test.ts to add Z.AI tests
- Modified src/frontends/tui/commands.ts to add login command
- Modified src/frontends/tui/minimal.ts to support credential prompts
This allows users to authenticate with Z.AI (GLM models) without
embedding secrets in config files. Credentials are stored securely in
~/.config/flynn/auth.json and resolved at runtime.
Updated state.json with new feature entry documenting the integration.
2026-02-13 16:23:49 -08:00
cc54b3a10c
feat(webchat): support image attachments
2026-02-13 15:03:48 -08:00
955b9e28e0
feat: add OpenAI OAuth, strict model overrides, and Gmail pull mode
2026-02-13 14:55:40 -08:00
8f644d5e25
feat(skills): add rollout promotion contract and sync planning state
2026-02-13 08:51:19 -08:00
9f81c01603
feat(session): persist model tier overrides per session
...
Store per-session config in SQLite and route /model and /reset through command fast-paths so channel sessions keep independent model selection across reconnects and restarts.
2026-02-13 01:04:26 -08:00
7ae0fb51c2
feat(skills): add rollout status governance and promotion policy checks
2026-02-12 22:43:46 -08:00
43b584257f
feat(skills): hash installer audit commands for shell runner telemetry
2026-02-12 22:20:14 -08:00
d3647567ee
test(skills): add edge-case receipt tests for partial/missing runner results
2026-02-12 21:12:15 -08:00
8c4ac2cb00
fix(skills): reject execute without explicit confirm
2026-02-12 20:59:11 -08:00
81d5c4d730
test(skills): cover install and execute option parsing
2026-02-12 19:38:16 -08:00
8affe8bea9
feat(skills): add execute command opt-in runner flow
2026-02-12 19:28:44 -08:00
3272387eaa
feat(skills): wire opt-in execution runner selection
2026-02-12 19:23:30 -08:00
30fcccd05a
feat(skills): add optional shell command runner
2026-02-12 19:18:20 -08:00
3a1bac0891
feat(skills): map runner outcomes into step receipts
2026-02-12 19:07:13 -08:00
5e5d96523e
feat(skills): add per-step no-op execution envelopes
2026-02-12 19:03:27 -08:00
0d324886eb
feat(skills): add pluggable no-op runner interface
2026-02-12 18:50:28 -08:00
a983e01db7
feat(skills): gate execution receipts with policy checks
2026-02-12 18:48:08 -08:00
1159fac640
feat(skills): add confirmed no-op execution receipts
2026-02-12 18:44:13 -08:00
f0fc806f95
refactor(skills): centralize install action modes
2026-02-12 18:36:09 -08:00
e8d5d01d4d
feat(skills): add installer execution stub command
2026-02-12 18:26:09 -08:00
1bb791c7dd
feat(skills): support install preflight-only mode
2026-02-12 18:17:46 -08:00
601844c50e
feat(skills): preview installer plan during install
2026-02-12 18:15:42 -08:00
d3ba1328f2
feat(skills): add installer plan command output
2026-02-12 18:11:38 -08:00
bd754d520e
feat(skills): add dry-run installer planning surface
2026-02-12 17:56:51 -08:00
81d04357a1
feat(skills): validate manifest installer specs
2026-02-12 17:52:53 -08:00
bd29afeaff
chore(skills): improve watcher event observability
2026-02-12 17:40:41 -08:00
333e33f30f
feat(skills): target watcher updates with safe fallback
2026-02-12 17:36:32 -08:00
2fb5c9adab
feat(skills): reload registry on watcher change events
2026-02-12 17:30:23 -08:00
b773e2bbf3
feat(skills): enable watcher wiring through daemon lifecycle
2026-02-12 17:18:22 -08:00
95091cc198
feat(skills): add debounced watcher foundation for phase 2
2026-02-12 17:15:46 -08:00
0a19f01639
feat(doctor): surface skill directory health in diagnostics
2026-02-12 17:05:04 -08:00
fc3d2ab4d8
feat(skills): add refresh summary for discovery health
2026-02-12 17:02:23 -08:00
2d753321b3
feat(skills): guard uninstall with explicit confirmation
2026-02-12 16:59:50 -08:00
d5b7d72e5d
feat(skills): add install dispatch for local skill setup
2026-02-12 16:50:25 -08:00
0d84a6bccc
feat(skills): add info command for skill inspection
2026-02-12 16:44:46 -08:00
b3e5aee333
feat(skills): expose list command for skill visibility
2026-02-12 16:42:00 -08:00
90ce622080
feat(policy): enforce truthfulness and autonomy guardrails
...
Add runtime truthfulness modes and autonomy-level tool gating with audit metadata for overrides/denials.
Wire policy through prompt assembly, tool execution context, and daemon/gateway agent paths; update tests and planning state for Phase 3 PR #2 completion.
2026-02-12 16:06:45 -08:00
c62dad2e2e
docs: update state.json with native audio support feature and test count (1369)
2026-02-11 18:27:50 -08:00
fae3565480
docs(skills): add skills infrastructure plan
...
- Three-phase plan for skills system improvements
- Phase 1: Command Dispatch (flynn skills CLI commands)
- Phase 2: Skills Watcher (auto-reload with chokidar)
- Phase 3: Installer Specs (auto-install brew/node/go/download)
- Model strategy: glm-4.7-flash for mechanical, glm-4.7 for complex
- Estimated 8-11 hours total
2026-02-11 14:48:21 -08:00
85d7a6bfec
test: add stopReason edge case tests; update state.json with recent fixes
...
- Added tests for finish_reason 'tool_calls' with empty array → 'end_turn'
- Added test for finish_reason 'length' → 'max_tokens'
- Updated state.json with 4 new entries for today's fixes (SOUL.md, message
normalization, agent loop resilience, stopReason normalization)
- Test count: 1329 → 1331
2026-02-11 09:51:19 -08:00
5270234bbb
feat: improve tool usage guidance in SOUL.md and add cron.create/cron.delete tools
...
- SOUL.md: list all available tools (web.search, memory.*, cron.*, etc.)
and add Tool Usage Rules section enforcing 'act, don't narrate'
- cron.ts: add getJob(), addJob(), removeJob() to CronScheduler for
runtime (ephemeral) cron job management
- cron tools: add cron.create and cron.delete tools, enhance cron.list
to show schedule/output/message details
- policy.ts: add cron tools to messaging and coding profiles, add
group:cron to tool groups
Fixes issue where models would narrate tool intent ('let me search...')
then stop without actually calling tools.
2026-02-11 09:32:36 -08:00
27ee3b2c10
feat(webchat): add copy and edit buttons on chat messages
...
Copy button on all messages (clipboard API with checkmark feedback).
Edit button on user messages populates the input textarea.
Buttons appear on hover (desktop) or always visible (mobile).
2026-02-10 20:53:49 -08:00
4c8ba3f20c
feat(webchat): add slash commands, autocomplete popup, and web search button
...
Add 6 slash commands (/help, /reset, /compact, /usage, /status, /model)
with autocomplete popup (arrow keys, Enter/Tab/Escape navigation).
Search button toggles web search mode by prepending instruction to message.
Backend agent.send extended with metadata for server-side command routing.
2026-02-10 20:45:14 -08:00
William Valentin