Artur Mukhamadiev
1d7b867986
The bridge counted tool and model calls against fixed 100 and 50 caps, so CONFLUENCE_WEB_MAX_CONFLUENCE_CALLS / CONFLUENCE_WEB_MAX_MODEL_CALLS above the defaults were cut short inside the container, and the model cap failed the run outright. The backend now passes both values into the container at start, the supervisor forwards them to the bridge, and LIMITS reads them with the same 1-1000 validation as the backend, falling back to 100/50 when absent or invalid. Add a test that loads LIMITS in fresh processes with good and bad values for both budgets and the deadline.
70 lines
3.9 KiB
Plaintext
70 lines
3.9 KiB
Plaintext
# Confluence Research Web UI: backend deployment configuration.
|
|
# Copy to deploy/confluence-web.env (git-ignored) and adjust. Values are read by
|
|
# scripts/run-backend.sh and exported only into the backend process. Nothing in
|
|
# this file is ever passed to the agent container.
|
|
|
|
# --- Confluence (read-only, user PAT is supplied in the browser at query time) ---
|
|
# Approved base origins (comma separated, include context path if any).
|
|
# Include the Confluence context path (collab.lge.com serves REST under /main).
|
|
CONFLUENCE_WEB_APPROVED_ORIGINS=https://collab.lge.com/main
|
|
# Optional outbound proxy for Confluence only (socks5://, socks5h://, http://, https://).
|
|
CONFLUENCE_WEB_CONFLUENCE_PROXY=socks5://127.0.0.1:1560
|
|
# Optional corporate CA bundle (PEM). Leave unset to use the system trust store.
|
|
#CONFLUENCE_WEB_CORPORATE_CA_PATH=/etc/ssl/certs/corporate-ca.pem
|
|
|
|
# --- Model provider (OpenAI-compatible Chat Completions; backend-held key) ---
|
|
CONFLUENCE_WEB_MODEL_PROVIDER=openai
|
|
# llama.cpp server tunnel; the endpoint is the full chat completions URL.
|
|
CONFLUENCE_WEB_MODEL_ENDPOINT=http://127.0.0.1:4901/v1/chat/completions
|
|
# llama-server accepts any bearer token; a real provider needs its real key here.
|
|
CONFLUENCE_WEB_MODEL_API_KEY=llama-cpp
|
|
CONFLUENCE_WEB_MODEL_NAME=Qwen3.6-35B-A3B
|
|
# Provider token limits (separate from the application byte limits in CONTRACTS.md).
|
|
CONFLUENCE_WEB_MODEL_CONTEXT_WINDOW_TOKENS=131072
|
|
CONFLUENCE_WEB_MODEL_MAX_OUTPUT_TOKENS=8192
|
|
# Per-call HTTP timeout; keep below the query deadline (CONFLUENCE_WEB_QUERY_TIMEOUT_SECONDS).
|
|
CONFLUENCE_WEB_MODEL_TIMEOUT_SECONDS=540
|
|
|
|
# --- Agent runtime container (rootless Docker) ---
|
|
# Use the exact built tag or, better, the image ID printed by `make build-image`.
|
|
CONFLUENCE_WEB_RUNTIME_IMAGE=confluence-pi-agent:rev1
|
|
# Unique per deployment; startup/periodic reconciliation removes containers with this label value.
|
|
CONFLUENCE_WEB_CONTAINER_LABEL_VALUE=confluence-web-local
|
|
#CONFLUENCE_WEB_DOCKER_HOST=unix:///run/user/1000/docker.sock
|
|
|
|
# --- HTTP / storage ---
|
|
# Loopback only by default. To serve colleagues on an internal network, bind the
|
|
# host's LAN address AND enable TLS below (PATs must not cross the network in clear).
|
|
CONFLUENCE_WEB_BIND_HOST=127.0.0.1
|
|
CONFLUENCE_WEB_BIND_PORT=8000
|
|
# Optional TLS termination by Uvicorn. Generate with: scripts/make-tls.sh <lan-ip>
|
|
# (name-constrained private CA; distribute deploy/tls/ca.crt to colleagues).
|
|
#CONFLUENCE_WEB_TLS_CERT=./deploy/tls/server.crt
|
|
#CONFLUENCE_WEB_TLS_KEY=./deploy/tls/server.key
|
|
# Absolute path to the frontend tree (index.html, css/, js/, vendor/, assets/).
|
|
CONFLUENCE_WEB_FRONTEND_DIST_DIR=./frontend
|
|
# Private artifact storage (created 0700; purged on startup).
|
|
CONFLUENCE_WEB_ARTIFACT_DIR=/tmp/confluence_web_artifacts
|
|
CONFLUENCE_WEB_QUERY_TIMEOUT_SECONDS=600
|
|
# Protocol maximum for one query (60-3600 s); the query timeout must not exceed it.
|
|
# Passed into the agent container at start so its supervisor enforces the same bound.
|
|
CONFLUENCE_WEB_MAX_DEADLINE_SECONDS=900
|
|
CONFLUENCE_WEB_CLEANUP_TIMEOUT_SECONDS=10
|
|
# Per-query call budgets (1-1000 each); cache hits are free. Reaching a budget returns an
|
|
# error to the agent, which then answers from what it has. Passed into the agent container
|
|
# so its bridge enforces the same counts. The request history keeps at most 100 tool
|
|
# entries, so a Confluence budget above 100 loses later history entries.
|
|
CONFLUENCE_WEB_MAX_CONFLUENCE_CALLS=100
|
|
CONFLUENCE_WEB_MAX_MODEL_CALLS=50
|
|
|
|
# --- Admission queue (docs/QUEUE_SPECIFICATION.md); defaults shown, allowed ranges in comments ---
|
|
# Reservation window after promotion, seconds (30-60).
|
|
#CONFLUENCE_WEB_QUEUE_RESERVATION_SECONDS=45
|
|
# Heartbeat timeout for queued (not yet reserved) tickets, seconds (5-60).
|
|
#CONFLUENCE_WEB_QUEUE_HEARTBEAT_SECONDS=15
|
|
# Maximum queued tickets, excluding the reserved and running sessions (1-100).
|
|
#CONFLUENCE_WEB_QUEUE_MAX_LENGTH=20
|
|
|
|
# Never set in production. Substitutes the container, model and Confluence with fakes.
|
|
CONFLUENCE_WEB_DEV_MODE=false
|