ORCH-044 closes two blind spots that let a single de-authenticated agent
stall the shared queue for all projects:
P1 — preflight auth gate. `claude --version` answers even when logged out,
so version-only preflight was blind to auth. Adds a token-free, network-free
check of <AGENT_HOME>/.claude/.credentials.json: missing/unreadable/no-oauth
or an expired `claudeAiOauth.expiresAt` (epoch ms, vs now + skew) => preflight
FAIL; absent expiry => OK (no false positives). Result is cached on the same
preflight_cache_ttl. Post-factum safety net: launcher detects auth markers
("not logged in" / "/login" / "unauthorized" / 401) in the run log and resets
the preflight cache so the next tick re-evaluates auth. Auth failure is a gate,
not a transient — it does not spin the circuit breaker. Emergency toggle
ORCH_PREFLIGHT_CHECK_AUTH=false restores version-only behaviour.
P3 — empty log / no result-JSON => job failed. exit_code==0 with an empty or
JSON-less run log no longer counts as success: a separate result_ok flag gates
stage advance + usage comments, fires a Telegram alert, and routes the job
through the normal transient/permanent failure path (exit_code integrity in
agent_runs preserved).
Scope: P2 (--effort) is intentionally excluded and tracked in ORCH-50.
New settings: ORCH_PREFLIGHT_CHECK_AUTH, ORCH_CLAUDE_CREDENTIALS_PATH,
ORCH_AUTH_EXPIRY_SKEW_SECONDS. Docs updated (INFRA.md, internals.md, CHANGELOG).
Refs: ORCH-044
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
162 lines
7.7 KiB
Python
162 lines
7.7 KiB
Python
from pydantic_settings import BaseSettings
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
# Plane
|
|
plane_api_url: str = "http://localhost:8091"
|
|
# ORCH-017: external (browser) web URL of Plane for clickable issue links in
|
|
# notifications, e.g. https://plane.example.org. Falls back to plane_api_url,
|
|
# but a loopback fallback (localhost/127.0.0.1) is treated as "no web URL" and
|
|
# the Plane link is omitted (see notifications._build_plane_issue_link).
|
|
plane_web_url: str = ""
|
|
plane_api_token: str = ""
|
|
plane_workspace_slug: str = ""
|
|
plane_webhook_secret: str = ""
|
|
plane_project_id: str = ""
|
|
|
|
# Per-agent Plane bot tokens (feat: per-agent comment authorship).
|
|
# When set, add_comment posts under the matching bot so Plane shows the
|
|
# real author (Analyst/Architect/...). Empty -> fallback to plane_api_token.
|
|
plane_bot_analyst: str = ""
|
|
plane_bot_architect: str = ""
|
|
plane_bot_developer: str = ""
|
|
plane_bot_reviewer: str = ""
|
|
plane_bot_tester: str = ""
|
|
plane_bot_deployer: str = ""
|
|
plane_bot_stream: str = ""
|
|
|
|
# Gitea
|
|
gitea_url: str = "http://localhost:3000"
|
|
gitea_public_url: str = "" # external URL for clickable links in comments; falls back to gitea_url
|
|
gitea_token: str = ""
|
|
gitea_webhook_secret: str = ""
|
|
gitea_owner: str = "admin"
|
|
default_repo: str = "enduro-trails"
|
|
|
|
# ORCH-6: multi-repo project registry. JSON array of
|
|
# {plane_project_id, repo, work_item_prefix, name}.
|
|
# Empty -> built-in default registry in src/projects.py.
|
|
projects_json: str = ""
|
|
|
|
# Claude CLI
|
|
claude_bin: str = "/opt/claude-code/bin/claude.exe"
|
|
repos_dir: str = "/repos"
|
|
host_repos_dir: str = "/home/slin/repos"
|
|
worktrees_dir: str = "/repos/_wt" # ORCH-2 / S-4: isolated worktree per task/branch
|
|
|
|
# DB
|
|
db_path: str = "/app/data/orchestrator.db"
|
|
|
|
# ORCH-1 (F-2b): persistent job queue / background worker.
|
|
# max_concurrency -> max agent jobs running in parallel (env ORCH_MAX_CONCURRENCY)
|
|
# queue_poll_interval -> worker loop poll seconds (env ORCH_QUEUE_POLL_INTERVAL)
|
|
max_concurrency: int = 1
|
|
queue_poll_interval: float = 2.0
|
|
|
|
# ORCH-1b (resilience): preflight + 429/rate-limit + backoff + circuit breaker.
|
|
# preflight_cache_ttl -> cache the cheap CLI/network preflight result (seconds);
|
|
# the worker does NOT re-run `claude --version` more often
|
|
# than this (env ORCH_PREFLIGHT_CACHE_TTL).
|
|
# backoff_base_seconds -> base for exponential transient backoff.
|
|
# backoff_max_seconds -> ceiling for the transient backoff.
|
|
# transient_max_attempts -> retry budget for transient (429/overload/network)
|
|
# failures, separate from code-fault `attempts`.
|
|
# breaker_threshold -> consecutive transient failures that OPEN the breaker.
|
|
# breaker_pause_seconds -> how long the breaker stays open before half-open.
|
|
preflight_cache_ttl: int = 45
|
|
# ORCH-044 (P1): token-free preflight auth gate. After `claude --version`
|
|
# succeeds, preflight also checks that claude is logged in by reading the
|
|
# local OAuth credentials file (no network / no prompt-ping — BR-1).
|
|
# preflight_check_auth -> master toggle (env ORCH_PREFLIGHT_CHECK_AUTH).
|
|
# Emergency off-switch if the check ever
|
|
# false-positives and wedges the shared queue.
|
|
# claude_credentials_path -> explicit path to .credentials.json
|
|
# (env ORCH_CLAUDE_CREDENTIALS_PATH). Empty ->
|
|
# <AGENT_HOME>/.claude/.credentials.json, where
|
|
# AGENT_HOME is the HOME the launcher really
|
|
# spawns claude under (/home/slin), NOT the
|
|
# orchestrator process env.
|
|
# auth_expiry_skew_seconds -> clock-drift slack when comparing
|
|
# claudeAiOauth.expiresAt (env
|
|
# ORCH_AUTH_EXPIRY_SKEW_SECONDS); a token within
|
|
# this many seconds of now is treated as expired.
|
|
preflight_check_auth: bool = True
|
|
claude_credentials_path: str = ""
|
|
auth_expiry_skew_seconds: int = 0
|
|
backoff_base_seconds: int = 10
|
|
backoff_max_seconds: int = 600
|
|
transient_max_attempts: int = 5
|
|
breaker_threshold: int = 3
|
|
breaker_pause_seconds: int = 300
|
|
|
|
# ORCH-7 (M-2): agent timeout + graceful kill.
|
|
# agent_timeout_seconds -> default per-agent wall-clock budget; the watchdog
|
|
# kills the run after this (env ORCH_AGENT_TIMEOUT_SECONDS).
|
|
# agent_kill_grace_seconds-> pause between SIGTERM and SIGKILL so claude can
|
|
# flush artifacts before the hard kill
|
|
# (env ORCH_AGENT_KILL_GRACE_SECONDS).
|
|
# agent_timeout_overrides_json -> optional per-agent override JSON object,
|
|
# e.g. {"reviewer": 3600, "architect": 2700}
|
|
# (env ORCH_AGENT_TIMEOUT_OVERRIDES_JSON).
|
|
agent_timeout_seconds: int = 1800
|
|
agent_kill_grace_seconds: int = 20
|
|
agent_timeout_overrides_json: str = ""
|
|
|
|
# ORCH-41: per-agent LLM model. Empty -> agent_model_default. Resolution order:
|
|
# project-override (projects_json agent_models) > ORCH_AGENT_MODEL_<AGENT> >
|
|
# agent_model_default > CLI default (no --model flag). Default is 4-8 because
|
|
# 4-7 == 4-8 in price (Slava 05.06); do NOT hardcode the version anywhere else.
|
|
agent_model_default: str = "claude-opus-4-8"
|
|
agent_model_analyst: str = ""
|
|
agent_model_architect: str = ""
|
|
agent_model_developer: str = ""
|
|
agent_model_reviewer: str = ""
|
|
agent_model_tester: str = ""
|
|
agent_model_deployer: str = ""
|
|
|
|
# ORCH-41: per-agent effort / reasoning level: low|medium|high|xhigh|max.
|
|
# Empty -> agent_effort_default. Same resolution order as model. Default split:
|
|
# thinking agents (analyst/architect/developer/reviewer) -> high; mechanical
|
|
# agents (tester/deployer) -> medium.
|
|
agent_effort_default: str = "high"
|
|
agent_effort_analyst: str = "high"
|
|
agent_effort_architect: str = "high"
|
|
agent_effort_developer: str = "high"
|
|
agent_effort_reviewer: str = "high"
|
|
agent_effort_tester: str = "medium"
|
|
agent_effort_deployer: str = "medium"
|
|
|
|
# ORCH-41: optional per-agent fallback model used when the primary is
|
|
# overloaded (--fallback-model, works with --print). Empty -> no flag.
|
|
agent_fallback_model: str = ""
|
|
|
|
# L-2: run-log rotation. Old per-run logs in <data>/runs/*.log are pruned at
|
|
# app startup (best-effort). A *.log is removed if it is older than
|
|
# log_keep_days OR not within the log_keep_max most-recent logs (whichever
|
|
# hits first). Only *.log files are touched; the active run log is skipped.
|
|
# log_keep_days -> max age in days (env ORCH_LOG_KEEP_DAYS).
|
|
# log_keep_max -> max number of newest logs to retain (env ORCH_LOG_KEEP_MAX).
|
|
log_keep_days: int = 30
|
|
log_keep_max: int = 500
|
|
|
|
|
|
# ORCH-045: quality-gate CI poll/retry. check_ci_green polls the Gitea
|
|
# combined commit status up to ci_poll_max_attempts times, sleeping
|
|
# ci_poll_interval_s between attempts, to ride out a transient pending
|
|
# state right after the developer push (race fix, see ORCH-017).
|
|
# ci_poll_max_attempts -> max status polls (env ORCH_CI_POLL_MAX_ATTEMPTS)
|
|
# ci_poll_interval_s -> seconds between polls (env ORCH_CI_POLL_INTERVAL_S)
|
|
ci_poll_max_attempts: int = 12
|
|
ci_poll_interval_s: int = 10
|
|
|
|
# Telegram notifications
|
|
telegram_bot_token: str = ""
|
|
telegram_chat_id: str = ""
|
|
|
|
class Config:
|
|
env_prefix = "ORCH_"
|
|
env_file = ".env"
|
|
|
|
|
|
settings = Settings()
|