glitch-university/agent0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Mirror request model for context discovery — no write_model_id needed

Browse Source 
Festinger now extracts provider/model/api-key from every intercepted
request and passes it to the context-discover queue as a fallback_model.
_process_context_discover uses it when write_model_id is not configured,
so Agent0's current model (LM Studio, Ollama, Anthropic) is automatically
reused for utility LLM calls without any extra setup.

Priority: write_model_id (explicit override) > fallback_model (request mirror)

Also updates upstream_openai default in config.yaml to LM Studio's
local address (host.docker.internal:1234).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Glitch University
2026-04-21 19:17:51 +02:00
parent ccbb5b2d45
commit 7210fe2066
3 changed files with 111 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
plugins/festinger/config.yaml
+3 -2
View File
@@ -7,9 +7,10 @@ upstream_ollama: "http://host.docker.internal:11434"
# Override via UPSTREAM_ANTHROPIC env var if needed
upstream_anthropic: "https://api.anthropic.com"
# Where the real OpenAI-compatible API is running (for /v1/chat/completions)
# Where the real OpenAI-compatible API is running (for /v1/chat/completions).
# For LM Studio set this to its local address, e.g. "http://host.docker.internal:1234"
# Override via UPSTREAM_OPENAI env var if needed
upstream_openai: "https://api.openai.com"
upstream_openai: "http://host.docker.internal:1234"
# Port this proxy listens on inside the container (exposed as 11434 on the docker network)
proxy_port: 11434