feat: MiniMax provider for image/video/podcast skills + new music-generation skill (#3437)

* docs(spec): MiniMax integration for generation skills + new music skill

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(plan): MiniMax generation providers implementation plan

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(skills): add importlib loader + FakeResp for skill tests

* test(skills): register loaded module in sys.modules; raise requests.HTTPError in FakeResp

* feat(image-generation): add MiniMax provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(image-generation): guard unknown provider, derive ref MIME, strengthen tests

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(video-generation): add MiniMax provider with async poll/download

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(video-generation): surface base_resp errors while polling; add timeout test

* feat(podcast-generation): add MiniMax t2a_v2 provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(podcast-generation): restore TTS credential guard; add volcengine + voice tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(music-generation): new MiniMax music skill via skill-creator

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(music-generation): treat empty lyrics as absent; test no-audio-data path

* refactor(skills): add request timeouts to MiniMax network calls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Potential fix for pull request finding 'Explicit returns mixed with implicit (fall through) returns'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* fix(models): strip inconsistent user-message names for MiniMax chat

DeerFlow middlewares tag user messages with provenance names (user-input, summary, loop_warning); langchain serializes them into the OpenAI-compatible payload and MiniMax rejects mismatched user-message names with "user name must be consistent (2013)". PatchedChatMiniMax now drops the per-message name from user-role messages. Point the config.example MiniMax models at PatchedChatMiniMax so they also get reasoning_content mapping.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(image-generation): MiniMax sends JSON prompt field, guard 1500-char limit

MiniMax image-01 takes one text string capped at 1500 chars, but the skill was sending the whole structured JSON. The MiniMax provider now extracts the JSON `prompt` field (relying on prompt_optimizer to expand it) and fails fast with a clear error before calling the API when that field exceeds 1500 chars. Authoring stays provider-agnostic; Gemini still receives the full JSON.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(podcast-generation): per-provider TTS concurrency and retry/backoff

Each TTS provider owns its concurrency internally — MiniMax runs single-threaded to reduce rate-limit failures, Volcengine keeps 4 workers — with automatic retry and backoff on transient HTTP and base_resp errors. No caller-facing concurrency knob.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(skills): address Copilot review comments on generation skills

- video: add raise_for_status + timeout to the Gemini download/POST/poll calls so non-2xx responses surface as clear HTTP errors instead of JSON/KeyError or hangs
- video: check the task Fail status before the generic base_resp check so the failure keeps its task_id context
- video/image: create the output file parent directory before writing (matching music-generation) so nested output paths do not raise FileNotFoundError
- music: require a non-empty prompt and fail fast with ValueError instead of sending an empty prompt to the API

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(scripts): reclaim dev ports across worktrees in make stop/dev

All deer-flow worktrees (main checkout + linked worktrees) hardcode the same dev ports (8001/3000/2026), so a service started from any worktree must be reclaimable from another. stop_all now resolves the set of worktree roots (DEERFLOW_ROOTS) and treats a process as deer-flow-owned when its open files live under any of them. It also force-kills survivors on 2026 alongside 8001/3000, fixing `make dev` aborting on the nginx port preflight when a prior nginx lingered on 2026.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(view-image): hide the injected image-context message from the UI

ViewImageMiddleware injects a HumanMessage (text + base64 images) so the vision model can see viewed images, but it was the only internal injector that set neither hide_from_ui nor a hidden name, so it leaked into the chat UI (and IM channels) as a user bubble reading "Here are the images you've viewed:". Mark it with additional_kwargs={"hide_from_ui": True}, matching todo/dynamic_context injections, which the frontend isHiddenFromUIMessage and the channel sender already honor. The model still receives the full content.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(minimax): mark M2.7 models as text-only (no vision)

MiniMax M2.7 / M2.7-highspeed do not support vision; only M3 does. The
provider config asserted vision support for M2.7 in four places.

- config.example.yaml: 4 M2.7 entries -> supports_vision: false
- backend/docs/CONFIGURATION.md: M2.7 + highspeed -> supports_vision: false
- wizard: add LLMProvider.model_vision_overrides + extra_config_for() so
  selecting an M2.7 model writes supports_vision: false while M3 (default)
  keeps vision; wire it through setup_wizard.py
- tests: M2.7-highspeed fixture -> supports_vision=False; add
  test_minimax_vision_is_per_model

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

backend/docs/CONFIGURATION.md

@@ -113,7 +113,7 @@ models:
     base_url: https://api.minimax.io/v1
     max_tokens: 4096
     temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
-    supports_vision: true
+    supports_vision: false  # M2.7 is text-only; M3 supports vision
 
   - name: minimax-m2.7-highspeed
     display_name: MiniMax M2.7 Highspeed
@@ -123,7 +123,7 @@ models:
     base_url: https://api.minimax.io/v1
     max_tokens: 4096
     temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
-    supports_vision: true
+    supports_vision: false  # M2.7 is text-only; M3 supports vision
   - name: openrouter-gemini-2.5-flash
     display_name: Gemini 2.5 Flash (OpenRouter)
     use: langchain_openai:ChatOpenAI

backend/packages/harness/deerflow/agents/middlewares/view_image_middleware.py

@@ -179,8 +179,10 @@ class ViewImageMiddleware(AgentMiddleware[ViewImageMiddlewareState]):
         # Create the image details message with text and image content
         image_content = self._create_image_details_message(state)
 
-        # Create a new human message with mixed content (text + images)
-        human_msg = HumanMessage(content=image_content)
+        # Create a new human message with mixed content (text + images). This is
+        # internal context for the model only, so hide it from the chat UI and IM
+        # channels (matches the other middleware-injected context messages).
+        human_msg = HumanMessage(content=image_content, additional_kwargs={"hide_from_ui": True})
 
         logger.debug("Injecting image details message with images before LLM call")
 

backend/packages/harness/deerflow/models/patched_minimax.py

@@ -114,8 +114,27 @@ class PatchedChatMiniMax(ChatOpenAI):
             }
         else:
             payload["extra_body"] = {"reasoning_split": True}
+        self._strip_user_message_names(payload)
         return payload
 
+    @staticmethod
+    def _strip_user_message_names(payload: dict) -> None:
+        """Drop the per-message ``name`` field from user-role messages.
+
+        DeerFlow middlewares tag user messages with internal provenance names
+        (``user-input``, ``summary``, ``loop_warning``, ...). ``langchain_openai``
+        serializes those into the OpenAI-compatible request, but MiniMax requires
+        every user-role ``name`` to be identical and otherwise rejects the request
+        with ``invalid params, user name must be consistent (2013)``. MiniMax does
+        not use the per-message author name, so strip it.
+        """
+        messages = payload.get("messages")
+        if not isinstance(messages, list):
+            return
+        for message in messages:
+            if isinstance(message, dict) and message.get("role") == "user":
+                message.pop("name", None)
+
     def _convert_chunk_to_generation_chunk(
         self,
         chunk: dict,

backend/tests/test_model_factory.py

@@ -715,7 +715,7 @@ def test_openai_compatible_provider_multiple_models(monkeypatch):
         base_url="https://api.minimax.io/v1",
         api_key="test-key",
         temperature=1.0,
-        supports_vision=True,
+        supports_vision=False,  # M2.7 is text-only; M3 supports vision
         supports_thinking=False,
     )
     cfg = _make_app_config([m1, m2])

backend/tests/test_patched_minimax.py

@@ -1,4 +1,4 @@
-from langchain_core.messages import AIMessageChunk, HumanMessage
+from langchain_core.messages import AIMessage, AIMessageChunk, HumanMessage, SystemMessage
 
 from deerflow.models.patched_minimax import PatchedChatMiniMax
 
@@ -21,6 +21,30 @@ def test_get_request_payload_preserves_thinking_and_forces_reasoning_split():
     assert payload["extra_body"]["reasoning_split"] is True
 
 
+def test_get_request_payload_strips_inconsistent_user_message_names():
+    """MiniMax rejects user messages whose `name` fields differ (error 2013).
+
+    DeerFlow middlewares tag user messages with internal provenance names
+    (e.g. "summary", "user-input", "loop_warning"). langchain serializes those
+    into the OpenAI-compatible payload, and MiniMax requires every user-role
+    name to be consistent. Strip them so the request is accepted.
+    """
+    model = _make_model()
+
+    payload = model._get_request_payload(
+        [
+            SystemMessage(content="system"),
+            HumanMessage(content="older summary", name="summary"),
+            AIMessage(content="ok"),
+            HumanMessage(content="latest question", name="user-input"),
+        ]
+    )
+
+    user_messages = [m for m in payload["messages"] if m["role"] == "user"]
+    assert len(user_messages) == 2
+    assert all(m.get("name") is None for m in user_messages)
+
+
 def test_create_chat_result_maps_reasoning_details_to_reasoning_content():
     model = _make_model()
     response = {

backend/tests/test_setup_wizard.py

@@ -54,6 +54,29 @@ class TestProviders:
         assert providers["deepseek"].use == "deerflow.models.patched_deepseek:PatchedChatDeepSeek"
         assert providers["volcengine"].extra_config["api_base"] == "https://ark.cn-beijing.volces.com/api/v3"
 
+    def test_minimax_vision_is_per_model(self):
+        """M3 supports vision; M2.7 variants are text-only.
+
+        The provider-level extra_config carries the default (M3) capability, but
+        extra_config_for() must drop vision when an M2.7 model is selected.
+        """
+        providers = {provider.name: provider for provider in LLM_PROVIDERS}
+
+        for name in ("minimax", "minimax_cn"):
+            provider = providers[name]
+            assert provider.extra_config["supports_vision"] is True
+            assert provider.extra_config_for("MiniMax-M3")["supports_vision"] is True
+            assert provider.extra_config_for("MiniMax-M2.7")["supports_vision"] is False
+            assert provider.extra_config_for("MiniMax-M2.7-highspeed")["supports_vision"] is False
+            # Override must not mutate the shared provider-level config.
+            assert provider.extra_config["supports_vision"] is True
+
+    def test_extra_config_for_returns_provider_config_without_override(self):
+        """Providers without per-model overrides return their config unchanged."""
+        providers = {provider.name: provider for provider in LLM_PROVIDERS}
+        openai = providers["openai"]
+        assert openai.extra_config_for("gpt-5") == openai.extra_config
+
     def test_llm_providers_have_required_fields(self):
         for p in LLM_PROVIDERS:
             assert p.name

backend/tests/test_view_image_middleware.py

@@ -356,6 +356,9 @@ class TestInjectImageMessage:
         # Mixed-content payload: list of text + image_url blocks
         assert isinstance(injected.content, list)
         assert any(isinstance(b, dict) and b.get("type") == "image_url" for b in injected.content)
+        # Internal injection: must be hidden from the chat UI (and IM channels),
+        # like the other middleware-injected context messages.
+        assert injected.additional_kwargs.get("hide_from_ui") is True
 
 
 class TestBeforeModel: