moritz/infrapuzzle
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(openclaw): allocate Gemini 3.8 Flash to koch agent, harden vision and tool protocols

Browse Source
This commit is contained in:
Moritz Graf
2026-10-12 19:52:11 +02:00
parent 393d928b19
commit a12b596053
4 changed files with 36 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/adr/0002-openclaw-model-selection-tiering-and-economics.md
+1 -1
View File
@@ -110,7 +110,7 @@ How do we architect the full-spectrum model selection across **all modalities**
### 4. Vision Input vs. Text-to-Image Generation (Tier 4)
* **Crucial Distinction**:
- **Vision Input (`imageModel`)**: Reading photos sent to Telegram (e.g. food ingredients, plants, receipts). Handled by `google/gemini-3.8-flash`, with `z-ai/glm-5.3-flash` as fallback.
- **Vision Input (`imageModel` vs. Dedicated Primary)**: Reading photos sent to Telegram (e.g. food ingredients, nutrition tables, plants, receipts). Note: OpenClaw only invokes `imageModel` if the primary model *lacks* image input modality. Since `z-ai/glm-5.3-flash` advertises image modality on OpenRouter, OpenClaw does not auto-divert to `imageModel`. Therefore, vision-intensive agents (specifically `koch`) must explicitly configure `primary: "openrouter/google/gemini-3.8-flash"` to leverage Google's SOTA OCR and dense-table recognition.
- **Text-to-Image Synthesis (`mediaModels.image`)**: Creating new pictures upon user request (e.g. *"Zeichne mir ein Profilbild von Octobot"*). Chat LLMs return 404 here.
* **Image Synthesis Engine**:
- **Primary**: `openrouter/google/gemini-3.1-flash-image` (Nano Banana 2).