xpltdco/chrysopedia
2
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions

chore: Bump LLM max_tokens to 32768, commit M002/M003 GSD artifacts

Browse source 
- max_tokens bumped from 16384 to 32768 (extraction responses still hitting limits)
- All GSD planning/completion artifacts for M002 (deployment) and M003 (DNS + LLM routing)
- KNOWLEDGE.md updated with XPLTD domain setup flow and container healthcheck patterns
- DECISIONS.md updated with D015 (subnet) and D016 (Ollama for embeddings)
This commit is contained in:
jlightner 2026-03-30 04:22:45 +00:00
parent e09147760d
commit 9bb40f57e4
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.env.example
View file

@ -30,7 +30,7 @@ LLM_FALLBACK_MODEL=fyn-qwen35-chat
#LLM_STAGE5_MODALITY=thinking #LLM_STAGE5_MODALITY=thinking
# Max tokens for LLM responses (OpenWebUI defaults to 1000 — pipeline needs much more) # Max tokens for LLM responses (OpenWebUI defaults to 1000 — pipeline needs much more)
LLM_MAX_TOKENS=16384 LLM_MAX_TOKENS=32768
# Embedding endpoint (Ollama container in the compose stack) # Embedding endpoint (Ollama container in the compose stack)
EMBEDDING_API_URL=http://chrysopedia-ollama:11434/v1 EMBEDDING_API_URL=http://chrysopedia-ollama:11434/v1

2
backend/config.py
View file

@ -44,7 +44,7 @@ class Settings(BaseSettings):
llm_stage5_modality: str = "chat" llm_stage5_modality: str = "chat"
# Max tokens for LLM responses (OpenWebUI defaults to 1000 which truncates pipeline JSON) # Max tokens for LLM responses (OpenWebUI defaults to 1000 which truncates pipeline JSON)
llm_max_tokens: int = 16384 llm_max_tokens: int = 32768
# Embedding endpoint # Embedding endpoint
embedding_api_url: str = "http://localhost:11434/v1" embedding_api_url: str = "http://localhost:11434/v1"