85 lines
3.6 KiB
Bash
85 lines
3.6 KiB
Bash
|
# Soma listener
|
||
|
|
# Keep Soma loopback-only unless a trusted reverse proxy supplies access control,
|
||
|
|
# rate limits, request-size limits, and TLS.
|
||
|
|
PROXY_HOST=127.0.0.1
|
||
|
|
PROXY_PORT=8080
|
||
|
|
|
||
|
|
# Removed in 2.4.0. Clear a value inherited from a shell that previously sourced a
|
||
|
|
# 2.3.x profile; Soma rejects even TRANSFORM_CONFIRM_REWRITES=false.
|
||
|
|
unset TRANSFORM_CONFIRM_REWRITES
|
||
|
|
|
||
|
|
# Target model endpoint
|
||
|
|
TARGET_URL=https://opencode.ai/zen/v1
|
||
|
|
TARGET_KEY=
|
||
|
|
TARGET_HEADERS_JSON={}
|
||
|
|
|
||
|
|
# Primary classifier, first repair candidate, and integrity verifier. The primary
|
||
|
|
# reasoning-off route is the fast deterministic path.
|
||
|
|
TRANSFORM_URL=http://127.0.0.1:8001/v1
|
||
|
|
TRANSFORM_KEY=
|
||
|
|
TRANSFORM_MODEL=local
|
||
|
|
TRANSFORM_HEADERS_JSON={}
|
||
|
|
TRANSFORM_REASONING_MODE=off
|
||
|
|
TRANSFORM_MEDIA_MODE=placeholder
|
||
|
|
|
||
|
|
# Required semantic-repair route when a secondary is configured: use the same
|
||
|
|
# already-running model with
|
||
|
|
# reasoning enabled, or configure an independently operated endpoint/model. Soma
|
||
|
|
# sends fresh candidates from the original context; it never sends rejected output.
|
||
|
|
TRANSFORM_SECONDARY_URL=http://127.0.0.1:8001/v1
|
||
|
|
TRANSFORM_SECONDARY_KEY=
|
||
|
|
TRANSFORM_SECONDARY_MODEL=local
|
||
|
|
TRANSFORM_SECONDARY_HEADERS_JSON={}
|
||
|
|
TRANSFORM_SECONDARY_REASONING_MODE=on
|
||
|
|
TRANSFORM_SECONDARY_MEDIA_MODE=placeholder
|
||
|
|
|
||
|
|
# Optional target-specific reasoning overlay
|
||
|
|
ENABLE_REASONING={}
|
||
|
|
# ENABLE_REASONING={"thinking":{"type":"enabled"}}
|
||
|
|
|
||
|
|
# Qualification uses zero to remove intentional sampling variance from repeat gates.
|
||
|
|
# Any nonzero value is a different profile and requires a new report.
|
||
|
|
TRANSFORM_TEMPERATURE=0
|
||
|
|
# Full transform task-context and individual target-field limits. Inputs are rejected,
|
||
|
|
# never silently truncated. TRANSFORM_FIELD_MAX_CHARS must not exceed the context cap.
|
||
|
|
TRANSFORM_CONTEXT_MAX_CHARS=131072
|
||
|
|
TRANSFORM_FIELD_MAX_CHARS=32768
|
||
|
|
# Decision/verifier and joint-repair output budgets.
|
||
|
|
TRANSFORM_DECISION_MAX_TOKENS=1536
|
||
|
|
TRANSFORM_REWRITE_MAX_TOKENS=16384
|
||
|
|
# A clarification is not accepted as a repaired answer unless explicitly enabled.
|
||
|
|
TRANSFORM_ALLOW_CLARIFICATION=false
|
||
|
|
# JSON-constrained transform output is enabled by default.
|
||
|
|
# Restart Soma after changing this value. Verify configuration before launch with
|
||
|
|
# `python3 soma.py --check-config`, then inspect the startup log or `/health` to
|
||
|
|
# confirm the effective value in the running process.
|
||
|
|
TRANSFORM_JSON_MODE=true
|
||
|
|
|
||
|
|
# One fresh target retry is available only when the complete target turn is
|
||
|
|
# unrepairable and leaves no usable content or native tool call. It is opt-in because
|
||
|
|
# it adds target latency/cost and can produce another model action.
|
||
|
|
TARGET_RETRY_ON_UNREPAIRABLE=false
|
||
|
|
|
||
|
|
# false: transform failures, including failed integrity checks and exhausted candidates, return 502
|
||
|
|
# true: preserve usable original refusing text after repair failure; reasoning-only
|
||
|
|
# or otherwise empty terminal turns still fail
|
||
|
|
FAIL_OPEN=false
|
||
|
|
|
||
|
|
FORWARD_CLIENT_HEADERS=true
|
||
|
|
# Same-server primary/secondary transform profiles are allowed; this protects only
|
||
|
|
# against the target sharing an origin with either transform endpoint.
|
||
|
|
REQUIRE_DISTINCT_ENDPOINTS=true
|
||
|
|
CONNECT_TIMEOUT=15
|
||
|
|
REQUEST_TIMEOUT=600
|
||
|
|
# One aggregate recovery budget after the first target response. It includes every
|
||
|
|
# transform call and an optional second target call plus processing of its response.
|
||
|
|
TRANSFORM_TOTAL_TIMEOUT=1200
|
||
|
|
UPSTREAM_ERROR_BODY_LIMIT=4000
|
||
|
|
SSE_CHUNK_CHARS=2048
|
||
|
|
LOG_LEVEL=INFO
|
||
|
|
|
||
|
|
# Optional common prefix added to classification, joint-repair, and integrity prompts.
|
||
|
|
# Leave unset for Soma's built-in 2.4.0 phase-specific transform behavior. A custom
|
||
|
|
# prefix materially changes the transform profile and requires separate qualification.
|
||
|
|
# TRANSFORM_PROMPT=...
|