* feat(minimax): add image generation and TTS providers, trim TUI model list
Register MiniMax image-01 and speech-2.8 models as plugin providers for
the image_generate and TTS tools. Both resolve CN/global base URLs from
the configured model endpoint origin.
- Image generation: base64 response, aspect-ratio support, image-to-image
via subject_reference, registered for minimax and minimax-portal
- TTS: speech-2.8-turbo (default) and speech-2.8-hd, hex-encoded audio,
voice listing via get_voice API, telephony PCM support
- Add MiniMax to TTS auto-detection cascade (after ElevenLabs, before
Microsoft) and TTS config section
- Remove MiniMax-VL-01, M2, M2.1, M2.5 and variants from TUI picker;
keep M2.7 and M2.7-highspeed only (backend routing unchanged)
* feat(minimax): trim legacy model catalog to M2.7 only
Cherry-picked from temp/feat/minimax-trim-legacy-models (949ed28).
Removes MiniMax-VL-01, M2, M2.1, M2.5 and variants from the model
catalog, model order, modern model matchers, OAuth config, docs, and
tests. Keeps only M2.7 and M2.7-highspeed.
Conflicts resolved:
- provider-catalog.ts: removed MINIMAX_TUI_MODELS filter (no longer
needed since source array is now M2.7-only)
- index.ts: kept image generation + speech provider registrations
(added by this branch), moved media understanding registrations
earlier (as intended by the cherry-picked commit)
* fix(minimax): update discovery contract test to reflect M2.7-only catalog
Cherry-picked from temp/feat/minimax-trim-legacy-models (2c750cb).
* feat(minimax): add web search provider and register in plugin entry
* fix(minimax): resolve OAuth credentials for TTS speech provider
* MiniMax: remove web search and TTS providers
* fix(minimax): throw on empty images array after generation failure
* feat(minimax): add image generation provider and trim catalog to M2.7 (#54487) (thanks @liyuan97)
---------
Co-authored-by: tars90percent <tars@minimaxi.com>
Co-authored-by: George Zhang <georgezhangtj97@gmail.com>
- Add hasAgentReasoningDefault to reasoningExplicitlySet check
This prevents model default from overriding agent's explicit "off"
- Restore !thinkingActive guard for model default fallback
Prevents redundant Reasoning: output alongside internal thinking
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The reasoningDefault was incorrectly skipped when thinking was active.
Thinking controls reasoning depth while reasoning controls visibility -
they should be independent settings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test(memory): lock qmd status counts regression
* feat: make /tools show what the agent can use right now
* fix: sync web ui slash commands with the shared registry
* feat: add profile and unavailable counts to /tools
* refine: keep /tools focused on available tools
* fix: resolve /tools review regressions
* fix: honor model compat in /tools inventory
* fix: sync generated protocol models for /tools
* fix: restore canonical slash command names
* fix: avoid ci lint drift in google helper exports
* perf: stop computing unused /tools unavailable counts
* docs: clarify /tools runtime behavior
- Check routedCounts.final to detect prior delivery
- Skip fallback for ttsMode='all' to avoid duplicate TTS processing
- Use delivery.deliver for proper routing in cross-provider turns
- Fixes#46814 where ACP child run results were not delivered
Root cause: Telegram channel monitor captures config at startup before secrets
are resolved and passes it as configOverride into the reply pipeline. Since
getReplyFromConfig() uses configOverride directly (skipping loadConfig() which
reads the resolved runtime snapshot), the unresolved SecretRef objects propagate
into FollowupRun.run.config and crash runEmbeddedPiAgent().
Fix (defense in depth):
- get-reply.ts: detect unresolved SecretRefs in configOverride and fall back to
loadConfig() which returns the resolved runtime snapshot
- message-tool.ts: try-catch around schema/description building at tool creation
time so channel discovery errors don't crash the agent
- message-tool.ts: detect unresolved SecretRefs in pre-bound config at tool
execution time and fall back to gateway secret resolution
Fixes: https://github.com/openclaw/openclaw/issues/45838
Migrates the Teams extension from @microsoft/agents-hosting to the official Teams SDK (@microsoft/teams.apps + @microsoft/teams.api) and implements Microsoft's AI UX best practices for Teams agents.
- AI-generated label on all bot messages (Teams native badge + thumbs up/down)
- Streaming responses in 1:1 chats via Teams streaminfo protocol
- Welcome card with configurable prompt starters on bot install
- Feedback with reflective learning (negative feedback triggers background reflection)
- Typing indicators for personal + group chats (disabled for channels)
- Informative status updates (progress bar while LLM processes)
- JWT validation via Teams SDK createServiceTokenValidator
- User-Agent: teams.ts[apps]/<sdk-version> OpenClaw/<version> on outbound requests
- Fix copy-pasted image downloads (smba.trafficmanager.net auth allowlist)
- Pre-parse auth gate (reject unauthenticated requests before body parsing)
- Reflection dispatcher lifecycle fix (prevent leaked dispatchers)
- Colon-safe session filenames (Windows compatibility)
- Cooldown cache eviction (prevent unbounded memory growth)
Closes#51806
When a channel plugin lacks a custom buildToolContext (e.g. Telegram),
the fallback path in buildThreadingToolContext did not set currentThreadTs
from the inbound MessageThreadId. This caused resolveTelegramAutoThreadId
to return undefined, so message tool sends without explicit threadId
would route to the main chat instead of the originating DM topic.
Fixes#52217
