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

fix(openclaw): remove gemini-2.5-flash from ocr and vision fallbacks

Browse Source
This commit is contained in:
Moritz Graf
2026-10-06 21:41:19 +02:00
parent 4e2a7120d6
commit a0e461a0b7
3 changed files with 2 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) ### 4. Vision Input vs. Text-to-Image Generation (Tier 4)
* **Crucial Distinction**: * **Crucial Distinction**:
- **Vision Input (`imageModel`)**: Reading photos sent to Telegram (e.g. food ingredients, plants, receipts). Handled by `google/gemini-3.8-flash` or `z-ai/glm-5.3-flash`, with `google/gemini-2.5-flash` as fallback. - **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.
- **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. - **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**: * **Image Synthesis Engine**:
- **Primary**: `openrouter/google/gemini-3.1-flash-image` (Nano Banana 2). - **Primary**: `openrouter/google/gemini-3.1-flash-image` (Nano Banana 2).
k8s/openclaw/TROUBLESHOOTING.md
+1 -1
View File
@@ -532,7 +532,7 @@ This document captures fixed issues, operational quirks, and incident root-cause
3. **Telegram Confirmation**: Dispatched the exact confirmation message with meal macros and updated daily totals directly to Telegram Topic 21 using `openclaw message send --channel telegram --target "-1004326921510" --thread-id 21`. 3. **Telegram Confirmation**: Dispatched the exact confirmation message with meal macros and updated daily totals directly to Telegram Topic 21 using `openclaw message send --channel telegram --target "-1004326921510" --thread-id 21`.
4. **Configured Dedicated Multimodal Vision Models**: Corrected `agents.defaults.imageModel` in `k8s/openclaw/openclaw-instance.secret.yaml` and ADR 0002: 4. **Configured Dedicated Multimodal Vision Models**: Corrected `agents.defaults.imageModel` in `k8s/openclaw/openclaw-instance.secret.yaml` and ADR 0002:
- Primary: `openrouter/google/gemini-3.8-flash` - Primary: `openrouter/google/gemini-3.8-flash`
- Fallbacks: `openrouter/google/gemini-2.5-flash`, `openrouter/z-ai/glm-5.3-flash`. - Fallbacks: `openrouter/z-ai/glm-5.3-flash`.
- **How to Avoid Recurrence**: - **How to Avoid Recurrence**:
- Never configure diffusion or raster generation models (`*-image` without chat/text output) as `imageModel` for visual input understanding. - Never configure diffusion or raster generation models (`*-image` without chat/text output) as `imageModel` for visual input understanding.
- Employ dedicated multimodal frontier models (Gemini Flash) with proven OCR and label comprehension for vision tasks. - Employ dedicated multimodal frontier models (Gemini Flash) with proven OCR and label comprehension for vision tasks.
k8s/openclaw/openclaw-instance.secret.yaml
BIN
View File
Binary file not shown.