teleo-codex/ops/pipeline-v2/lib/domains.py
m3taversal 05d74d5e32 sync: import all VPS pipeline + diagnostics code as baseline
Imports 67 files from VPS (/opt/teleo-eval/) into repo as the single source
of truth. Previously only 8 of 67 files existed in repo — the rest were
deployed directly to VPS via SCP, causing massive drift.

Includes:
- pipeline/lib/: 33 Python modules (daemon core, extraction, evaluation, merge, cascade, cross-domain, costs, attribution, etc.)
- pipeline/: main daemon (teleo-pipeline.py), reweave.py, batch-extract-50.sh
- diagnostics/: 19 files (4-page dashboard, alerting, daily digest, review queue, tier1 metrics)
- agent-state/: bootstrap, lib-state, cascade inbox processor, schema
- systemd/: service unit files for reference
- deploy.sh: rsync-based deploy with --dry-run, syntax checks, dirty-tree gate
- research-session.sh: updated with Step 8.5 digest + cascade inbox processing

No new code written — all files are exact copies from VPS as of 2026-04-06.
From this point forward: edit in repo, commit, then deploy.sh.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 00:00:00 +01:00

87 lines
3 KiB
Python

"""Domain→agent mapping and domain detection — single source of truth.
Extracted from evaluate.py and merge.py (Phase 3 refactor).
All domain classification logic goes through this module.
"""
import re
# Canonical domain→agent mapping. Every domain must have exactly one primary agent.
DOMAIN_AGENT_MAP: dict[str, str] = {
"internet-finance": "Rio",
"entertainment": "Clay",
"health": "Vida",
"ai-alignment": "Theseus",
"space-development": "Astra",
"mechanisms": "Rio",
"living-capital": "Rio",
"living-agents": "Theseus",
"teleohumanity": "Leo",
"grand-strategy": "Leo",
"critical-systems": "Theseus",
"collective-intelligence": "Theseus",
"teleological-economics": "Rio",
"cultural-dynamics": "Clay",
}
# Valid domain names — derived from the map, not maintained separately.
VALID_DOMAINS: frozenset[str] = frozenset(DOMAIN_AGENT_MAP.keys())
# Inverse mapping: agent name (lowercase) → primary domain (for branch detection).
_AGENT_PRIMARY_DOMAIN: dict[str, str] = {
"rio": "internet-finance",
"clay": "entertainment",
"theseus": "ai-alignment",
"vida": "health",
"astra": "space-development",
"leo": "grand-strategy",
}
def agent_for_domain(domain: str | None) -> str:
"""Get the reviewing agent for a domain. Falls back to Leo."""
if domain is None:
return "Leo"
return DOMAIN_AGENT_MAP.get(domain, "Leo")
def detect_domain_from_diff(diff: str) -> str | None:
"""Detect primary domain from changed file paths in a unified diff.
Checks domains/, entities/, core/, foundations/ for domain classification.
Returns the most-referenced domain, or None if no domain files found.
"""
domain_counts: dict[str, int] = {}
for line in diff.split("\n"):
if line.startswith("diff --git"):
# Check domains/ and entities/ (both carry domain info)
match = re.search(r"(?:domains|entities)/([^/]+)/", line)
if match:
d = match.group(1)
domain_counts[d] = domain_counts.get(d, 0) + 1
continue
# Check core/ subdirectories
match = re.search(r"core/([^/]+)/", line)
if match:
d = match.group(1)
if d in DOMAIN_AGENT_MAP:
domain_counts[d] = domain_counts.get(d, 0) + 1
continue
# Check foundations/ subdirectories
match = re.search(r"foundations/([^/]+)/", line)
if match:
d = match.group(1)
if d in DOMAIN_AGENT_MAP:
domain_counts[d] = domain_counts.get(d, 0) + 1
if domain_counts:
return max(domain_counts, key=domain_counts.get)
return None
def detect_domain_from_branch(branch: str) -> str | None:
"""Extract domain from branch name like 'rio/claims-futarchy''internet-finance'.
Uses agent prefix → primary domain mapping for pipeline branches.
"""
prefix = branch.split("/")[0].lower() if "/" in branch else ""
return _AGENT_PRIMARY_DOMAIN.get(prefix)