sync: 鍚屾灞€鍩熺綉鏈€鏂颁唬鐮?(source master @ b69568e4)

This commit is contained in:
gozeros committed 2026-10-21 14:51:31 +08:00
1 parent 4f7f07504a
commit 8bc8b0e082
1651 files changed
+278599 -11416

No files matched your search

@@ -49,7 +49,6 @@ models:
use: deerflow.models.openai_codex_provider:CodexChatModel
model: gpt-5.4
supports_thinking: true
supports_reasoning_effort: true
- name: claude-sonnet-4.6
display_name: Claude Sonnet 4.6 (Claude Code OAuth)
@@ -59,6 +58,15 @@ models:
supports_thinking: true
```
Whether a model exposes the per-chat reasoning-effort selector is managed by
an administrator in **Model Management** and persisted in the
`model_capabilities` database table. For upgrade compatibility, a legacy
`supports_reasoning_effort: true` value is imported once at startup only when
that model has no database row. Existing database values (including `false`)
are never overwritten; after that first import the database is authoritative.
Remove the legacy YAML field when convenient. Model Management also removes it
the next time the model list is saved, and new configurations should not add it.
**Auth behavior for CLI-backed providers**:
- `CodexChatModel` loads Codex CLI auth from `~/.codex/auth.json`
- The Codex Responses endpoint currently rejects `max_tokens` and `max_output_tokens`, so `CodexChatModel` does not expose a request-level token cap
@@ -123,6 +131,27 @@ models:
If your OpenRouter key lives in a different environment variable name, point `api_key` at that variable explicitly (for example `api_key: $OPENROUTER_API_KEY`).
**vLLM (per-model, do not change other entries)**:
`use` is per model. SiliconFlow / DeepSeek entries should stay on `langchain_openai:ChatOpenAI`. For a self-hosted vLLM reasoning model (thinking may arrive as `reasoning` on newer vLLM, or `reasoning_content` on older builds), set only that one entry to `VllmChatModel`:
```yaml
models:
- name: qwen3.6
display_name: qwen3.6
use: deerflow.models.vllm_provider:VllmChatModel
model: qwen3.6
api_key: $VLLM_API_KEY
base_url: http://127.0.0.1:8001/v1
supports_thinking: true
when_thinking_enabled:
extra_body:
chat_template_kwargs:
enable_thinking: true
```
The default `langchain_openai:ChatOpenAI` path also maps both thinking field names onto the UI's `reasoning_content`. Use `VllmChatModel` when follow-up turns must echo vLLM's original `reasoning` field.
**Thinking Models**:
Some models support "thinking" mode for complex reasoning:
@@ -270,21 +299,21 @@ skills:
# Host path (optional, default: ../skills)
path: /custom/path/to/skills
# Container mount path (default: /mnt/skills)
container_path: /mnt/skills
# Optional system-prompt routing rule for the es_query skill
es_query_routing:
enabled: true
prompt: |
当用户的问题需要基于 Elasticsearch Query DSL 灵活构造、调整或执行查询时,优先使用 `es_query` 技能。
执行前先读取该技能的 SKILL.md,并严格遵循其中的流程和参数。
```
`skills.es_query_routing.enabled` controls whether the routing rule is injected
into the overall agent system prompt. Edit `prompt` to tune the matching boundary
or invocation requirements. When disabled (the schema default), the block is not
injected. Custom agents receive it only when their explicit skill allowlist
contains `es_query`.
# Container mount path (default: /mnt/skills)
container_path: /mnt/skills
# Optional system-prompt routing rule for the es_query skill
es_query_routing:
enabled: true
prompt: |
当用户的问题需要基于 Elasticsearch Query DSL 灵活构造、调整或执行查询时,优先使用 `es_query` 技能。
执行前先读取该技能的 SKILL.md,并严格遵循其中的流程和参数。
```
`skills.es_query_routing.enabled` controls whether the routing rule is injected
into the overall agent system prompt. Edit `prompt` to tune the matching boundary
or invocation requirements. When disabled (the schema default), the block is not
injected. Custom agents receive it only when their explicit skill allowlist
contains `es_query`.
**How Skills Work**:
- Skills are stored in `deer-flow/skills/{public,custom}/`