Commit Graph

1426 Commits

Author SHA1 Message Date
Andy Lo-A-Foe 5a997a86f0 fix(bedrock): drop temperature for models that deprecate it
Claude Opus 4.8 on Bedrock rejects the temperature inference parameter
with a ValidationException ("temperature is deprecated for this model").
buildConverseParams now takes the model id and omits temperature for
claude-opus-4-8* (matching both bare model ids and region-prefixed
inference profiles), logging when it does so. max_tokens and all other
models are unaffected.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-01 08:59:15 +02:00
肆月 d2c0b69243 feat(web,api): provider selection and model form foundation (#2831)
* feat: improve model configuration workflows

Add model catalog browsing, provider registry with form validation,
model fetch/test dialogs, and enhanced model management UI.

- Add model catalog API and catalog-dialog component for browsing saved models
- Add provider-registry with auto-populated form fields per provider
- Add provider-combobox, fetch-models-dialog, test-model-dialog components
- Add model-validation for provider-aware model ID validation
- Add command and popover UI components
- Enhance edit-model-sheet with tool schema transform support
- Add anthropic to protocolMetaByName for correct default API base
- Apply NormalizeBaseURL to anthropic provider for consistent URL handling
- Add i18n keys for new model management features (en/zh)

* fix(web): prevent auto-fetch when API key is missing in fetch models dialog

When a provider requires an API key but none is set, the dialog now shows
the warning without triggering a doomed fetch attempt. Fetch is deferred
until the user provides a key.

* fix(web): add credential warning for catalog imports from remote providers

When importing models from a catalog entry whose provider requires an API
key, a yellow warning banner now informs users that credentials will need
to be configured after import.

* feat(web,api): test connection with real connectivity verification and unsaved form values

Add POST /api/models/test-inline endpoint that performs actual network
probes (GET /models) instead of just checking config. Frontend Test
Connection now uses current form values (not saved state) and is
available in both Add and Edit model flows.

* style(web): apply linter formatting across model config components

Normalize quote style, import ordering, and class name ordering as
reported by the project linter.

* fix(web,api): fix edit test connection false negative and gate fetch for unsupported providers

- handleTestInlineModel now accepts optional model_index to fall back to stored credentials when api_key is empty, fixing false negatives when testing edited models
- Add supportsFetch to provider registry and FETCHABLE_PROVIDER_KEYS derived set
- Gate Fetch Models button to only show for OpenAI-compatible and Ollama providers
- Add backend guard in handleFetchModels to reject unsupported providers with clear error

* fix: address review feedback on model config workflow

- Send explicit {} for empty extra_body/custom_headers fields so the
  backend clears stored values instead of preserving them
- Merge backend provider_options with frontend PROVIDERS registry so
  the provider picker reflects backend-supported providers and policy
  fields (create_allowed, default_auth_method, auth_method_locked)
- Render provider combobox popover inside the sheet scroll container
  to fix wheel events scrolling the sheet instead of the provider list

* feat(web,api): add provider selection, model form foundation, and validation

Split from PR #2752 (part 1 of 3).

Backend:
- CRUD model endpoints (list/add/update/delete/set-default)
- Provider metadata with default API bases and model provider options
- Model ID validation and normalization
- Anthropic default API base normalization

Frontend:
- Provider registry with metadata, labels, icons, and aliases
- Provider combobox with backend option merging
- Model field validation with provider-aware checks
- Redesigned add/edit model sheets with provider selection
- Dynamic imports for fetch/catalog/test dialogs (coming in PR2/PR3)
- i18n support for model configuration UI
2026-05-11 16:57:37 +08:00
美電球 7dc78425d1 Merge pull request #2719 from loafoe/feat/slack-webhook-channel
feat(channels): add slack_webhook output-only channel
2026-05-11 16:22:27 +08:00
lxowalle b3a7b7ad64 feat: agent self evolution (#2847)
* feat: add agent self-evolution

* fix ci

* delete unused doc

* fix lint

* fix evolution review issues
2026-05-11 16:13:27 +08:00
Andy Lo-A-Foe b12f03be2e feat(channels): add slack_webhook channel
Add an output-only channel that sends messages to Slack via Incoming
Webhooks using Block Kit formatting.

Features:
- Multiple webhook targets with named routing (requires "default" target)
- Markdown to Slack mrkdwn conversion (bold, italic, strikethrough, links, lists)
- Code block handling with proper fence preservation across chunk splits
- Table rendering with aligned columns in code blocks
- Automatic text chunking at 3000 chars (Slack's text block limit)
- HTTPS-only webhook URL validation

Configuration example:
  channels:
    slack_webhook:
      webhooks:
        default:
          webhook_url: "https://hooks.slack.com/services/..."
          username: "PicoClaw"
          icon_emoji: ":robot_face:"

Co-Authored-By: Claude <noreply@anthropic.com>
2026-05-11 09:54:04 +02:00
美電球 894c6251c5 Merge pull request #2783 from zhangxinping666/codex/fix-reload-voice-media-store
fix(gateway): keep media store aligned after reload
2026-05-11 15:44:38 +08:00
美電球 306f96cfe3 Merge pull request #2645 from loafoe/feat/bedrock-streaming
feat(bedrock): implement StreamingProvider for real-time token streaming
2026-05-11 15:08:43 +08:00
xp 91f024eb1d fix(gateway): keep media store aligned after reload 2026-05-10 10:26:57 +08:00
Mauro 6e6293e596 Merge pull request #2158 from afjcjsbx/feat/agent-discovery-prompt
feat(agent): Multi-agent discovery prompt
2026-05-09 13:56:19 +02:00
Mauro f571a142bf Merge pull request #2823 from bogdanovich/fix/parent-session-tool-feedback-cleanup
fix(agent): dismiss tool feedback when outbound is skipped
2026-05-09 11:09:10 +02:00
afjcjsbx 2ae25b1038 fix(agent): treat empty AGENT.md tools as allow none 2026-05-09 10:35:13 +02:00
Anton Bogdanovich e1ed47b0ff fix(agent): remove unused scheduled helper 2026-05-09 00:53:23 -07:00
Anton Bogdanovich 8362203631 fix(agent): transcribe queued voice follow-ups 2026-05-08 13:50:14 -07:00
afjcjsbx 148583e7bb fix(agent): hide discovery when spawn is unavailable 2026-05-08 22:23:50 +02:00
Anton Bogdanovich a3edbcd05e test(agent): satisfy lint for tool feedback cleanup 2026-05-08 10:33:16 -07:00
afjcjsbx c6a09a35e2 fix(agent): suppress MCP discovery when no servers are selectable 2026-05-08 13:48:47 +02:00
afjcjsbx ffa184d183 fix(agent): resolve primary provider from frontmatter model 2026-05-08 13:43:21 +02:00
美電球 8508f80608 Merge pull request #2705 from hehaijunandhenry/main
add MQTT channel support
2026-05-08 18:50:08 +08:00
hehaijunandhenry 569939a7b3 Fix stop_mqtt_channel 2026-05-08 17:21:25 +08:00
hehaijunandhenry 2287de521e Linter fixed 2026-05-08 15:49:28 +08:00
afjcjsbx 871892ff15 fix(tools): exempt MCP discovery tools from agent allowlists 2026-05-08 09:18:14 +02:00
hehaijunandhenry f062cb41d7 1 2026-05-08 14:48:43 +08:00
Anton Bogdanovich 610e9e3fe8 fix(agent): dismiss session tool feedback on skipped outbound 2026-05-07 23:10:56 -07:00
ex-takashima bacb9aba7c fix(line): close response body on successful SendMedia calls
Always route through classifySDKError to ensure resp.Body is
closed even when the API call succeeds.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-08 14:11:15 +09:00
ex-takashima 6d7d1b0909 fix(line): capture QuoteToken for all message types and handle location
- Store QuoteToken for image, video, and sticker messages (not just text)
- Add webhook.LocationMessageContent case to forward as [location] placeholder

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-08 14:05:58 +09:00
afjcjsbx b8f4257cee fix(agent): filter discovery by spawn permissions 2026-05-07 18:26:09 +02:00
afjcjsbx 96fd887cad fix(agent): match MCP server allowlists case-insensitively 2026-05-07 18:17:37 +02:00
afjcjsbx dd8e247550 fix(agent): align MCP prompt registration with tool allowlist 2026-05-07 14:01:43 +02:00
afjcjsbx 27bd816b1c fix(agent): validate AGENT tool declarations from registry 2026-05-07 13:49:23 +02:00
afjcjsbx f1f6e1131b removed unused code 2026-05-07 13:20:39 +02:00
afjcjsbx 6f6270b39d Merge upstream/main into feat/agent-discovery-prompt 2026-05-07 13:16:30 +02:00
ex-takashima 41d6156dce style(line): shorten long line for golines linter
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-07 16:48:45 +09:00
ex-takashima ad78ba06ea fix(line): close HTTP response body from WithHttpInfo calls
Fix bodyclose linter errors by ensuring resp.Body is closed
after all *WithHttpInfo SDK calls.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-07 16:41:19 +09:00
ex-takashima 9b7fc7aa6c fix(line): classify SDK errors with HTTP status and add client timeout
Address review feedback:
- Use *WithHttpInfo SDK variants to get HTTP response status codes
- Map status codes via ClassifySendError (429→ErrRateLimit, 5xx→ErrTemporary, 4xx→ErrSendFailed)
- Fall back to ClassifyNetError for network-level failures
- Configure SDK with 30s timeout HTTP client

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-07 16:23:33 +09:00
hehaijunandhenry e7c0dc821a Merge remote-tracking branch 'remotes/upstream/main' 2026-05-07 14:39:29 +08:00
美電球 658961b728 Merge pull request #2531 from is-Xiaoen/feat/delegate-tool
feat(tools): add delegate tool for cross-agent task handoff
2026-05-07 11:25:41 +08:00
Mauro 788cda5c7a Merge pull request #2762 from afjcjsbx/feat/stop-command
feat(agent): stop command
2026-05-06 18:19:14 +02:00
LC 81a050555d feat(provider,web,asr): enhance model management with explicit provider metadata (#2701)
* feat(provider,web): enhance model management with provider options

* fix(asr): enhance compatibility for ElevenLabs transcription model

* fix(provider,web): align provider availability predicates and add flow gating

* fix(web,asr): preserve legacy elevenlabs transcription configs

* fix(provider,web,asr): normalize elevenlabs configs and gate default chat models

* fix: tighten provider catalog and elevenlabs compatibility
2026-05-06 16:06:49 +08:00
afjcjsbx a7e52e8a25 fix(agent): drain scoped follow-up queue when pending stop skips turn startup 2026-05-05 19:24:15 +02:00
Mauro eb4e187550 Merge pull request #2767 from afjcjsbx/fix/leaf-summary-target-validation
fix(seahorse): enforce target token thresholds for leaf summaries
2026-05-05 19:09:06 +02:00
xp d601b75268 fix(agent): send SVG attachments as files 2026-05-05 19:36:09 +08:00
Mauro ba4abff4a4 Merge pull request #2670 from david1gp/fix/tool-feedback-pretty-print
feat(agent): add pretty_print and disable_escape_html options for tool feedback
2026-05-04 21:47:32 +02:00
afjcjsbx a1b55fd4f9 fix(seahorse): enforce target token thresholds for leaf summaries 2026-05-04 14:10:42 +02:00
afjcjsbx d63430ab33 fix(agent): don't arm pending stop when /stop targets idle session 2026-05-04 13:10:02 +02:00
afjcjsbx 7a1f5fe8b9 fix test 2026-05-04 09:06:39 +02:00
Hoshina 057683d94c fix(agent): use runtime event kind for LLM retry 2026-05-04 15:06:34 +08:00
afjcjsbx a0245c7b02 feat(agent): stop command 2026-05-04 08:41:29 +02:00
afjcjsbx f3ef7090c5 feat(agent): stop command 2026-05-04 08:41:17 +02:00
Mauro be67aed4dc Merge pull request #2677 from alexhoshina/feat/runtime-events-plan
Feat/runtime events
2026-05-03 23:15:25 +02:00
Mauro 828a7cba70 Merge pull request #2681 from afjcjsbx/fix/gemini-mcp-schema-sanitization
fix(mcp): sanitize MCP tool schemas for Gemini function calling
2026-05-03 20:25:35 +02:00