Files
deepseek-v4-quant/memory/2026-04-30-model-normalizer-docs.md
biondizzle f63eed5cfd Purge INT4 references — expert weights are FP4 (E2M1), not INT4
All docs and scripts updated. Historical memory entries annotated.
2026-05-08 02:33:46 +00:00

55 lines
3.3 KiB
Markdown

# Session: 2026-04-30 21:47:11 UTC
- **Session Key**: agent:main:main
- **Session ID**: 92ae6ac9-9697-477d-9574-44daaf400e8b
- **Source**: webchat
## Conversation Summary
user: A new session was started via /new or /reset. Run your Session Startup sequence - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
Current time: Thursday, April 30th, 2026 - 8:11 PM (UTC) / 2026-04-30 20:11 UTC
assistant: Hey Mike. Vinny 🔧 — back online. What are we working on tonight?
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-control-ui",
"id": "openclaw-control-ui"
}
```
[Thu 2026-04-30 20:14 UTC] Take a gander at `/home/openclaw/dev/api.vultrinference.com` I added functionality when people pass `-normalize` at the end of a model name it runs the model through a normalizer which basically changes `reasoning_content` to regular `reasoning` and `content` blocks. Take a look at `/home/openclaw/dev/api.vultrinference.com/normalizer_proxy.py` to get the full picture of what it actually does.
Can you update the docs in `/home/openclaw/dev/api.vultrinference.com/templates/openapi` to state that?
assistant: Got it. I'll update the `model` field descriptions and add the `reasoning` field to the message schemas, plus note the normalizer in the endpoint description.
assistant: Done. Here's what I updated in the OpenAPI spec:
1. **`/chat/completions` endpoint description** — added a "Normalizer Mode" section listing all 6 normalizations the proxy applies
2. **`model` field in both request payloads** (standard + RAG) — added note about appending `-normalize` to the model name
3. **`chat-completion-message` schema** — added `reasoning` field (replaces the non-standard `reasoning_content`)
4. **`chat-completion-stream-message` schema** — added `reasoning` field for streaming deltas
Want me to regenerate the HTML docs from the YAML, or does `generate_docs.sh` handle that separately?
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-control-ui",
"id": "openclaw-control-ui"
}
```
[Thu 2026-04-30 20:20 UTC] ohh. that file is automatically generated., You need to edit each individual yaml and then when i run generate it merges those into the openapi.yaml
assistant: Got it — let me revert the openapi.yaml and edit the source files instead.
assistant: Now I'll edit the source files — `paths.yaml` for the endpoint description, and `schemas.yaml` for the model field and reasoning fields.
assistant: Done. Here's what I changed in the source files:
**`paths.yaml`:**
- `/chat/completions` description — added the full normalizer mode section listing all 6 transformations
**`schemas.yaml`:**
- `chat-completion-request-payload.model` — added `-normalize` suffix note
- `chat-rag-request-payload.model` — same
- `chat-completion-message` — added `reasoning` field (non-streaming response)
- `chat-completion-stream-message` — added `reasoning` field (streaming delta)
Run `generate_docs.sh` whenever you're ready and it'll merge everything into the final `openapi.yaml`.