Files
ATOCore/scripts/seed_project_state.py
Anto01 775960c8c8 feat: "Make It Actually Useful" sprint — observability + Phase 10
Pipeline observability:
- Retrieval harness runs nightly (Step E in batch-extract.sh)
- Pipeline summary persisted to project state after each run
  (pipeline_last_run, pipeline_summary, retrieval_harness_result)
- Dashboard enhanced: interaction total + by_client, pipeline health
  (last_run, hours_since, harness results, triage stats), dynamic
  project list from registry

Phase 10 — reinforcement-based auto-promotion:
- auto_promote_reinforced(): candidates with reference_count >= 3 and
  confidence >= 0.7 auto-graduate to active
- expire_stale_candidates(): candidates unreinforced for 14+ days
  auto-rejected to prevent unbounded queue growth
- Both wired into nightly cron (Step B2)
- Batch script: scripts/auto_promote_reinforced.py (--dry-run support)

Knowledge seeding:
- scripts/seed_project_state.py: 26 curated Trusted Project State
  entries across p04-gigabit, p05-interferometer, p06-polisher,
  atomizer-v2, abb-space, atocore (decisions, requirements, facts,
  contacts, milestones)

Tests: 299 → 303 (4 new Phase 10 tests)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 13:59:12 -04:00

160 lines
7.3 KiB
Python

#!/usr/bin/env python3
"""Seed Trusted Project State entries for all active projects.
Populates the project_state table with curated decisions, requirements,
facts, contacts, and milestones so context packs have real content
in the highest-trust tier.
Usage:
python3 scripts/seed_project_state.py --base-url http://dalidou:8100
python3 scripts/seed_project_state.py --base-url http://dalidou:8100 --dry-run
"""
from __future__ import annotations
import argparse
import json
import urllib.request
import sys
# Each entry: (project, category, key, value, source)
SEED_ENTRIES: list[tuple[str, str, str, str, str]] = [
# ---- p04-gigabit (GigaBIT M1 1.2m Primary Mirror) ----
("p04-gigabit", "fact", "mirror-spec",
"1.2m borosilicate primary mirror for GigaBIT telescope. F/1.5, lightweight isogrid back structure.",
"CDR docs + vault"),
("p04-gigabit", "decision", "back-structure",
"Option B selected: conical isogrid back structure with variable rib density. Chosen over flat-back for stiffness-to-weight ratio.",
"CDR 2026-01"),
("p04-gigabit", "decision", "polishing-vendor",
"ABB Space (formerly INO) selected as polishing vendor. Contract includes computer-controlled polishing (CCP) and ion beam figuring (IBF).",
"Entente de service 2026-01"),
("p04-gigabit", "requirement", "surface-quality",
"Surface figure accuracy: < 25nm RMS after final figuring. Microroughness: < 2nm RMS.",
"CDR requirements"),
("p04-gigabit", "contact", "abb-space",
"ABB Space (INO), Quebec City. Primary contact for mirror polishing, CCP, and IBF. Project lead: coordinating FDR deliverables.",
"vendor records"),
("p04-gigabit", "milestone", "fdr",
"Final Design Review (FDR) in preparation. Deliverables include interface drawings, thermal analysis, and updated error budget.",
"project timeline"),
# ---- p05-interferometer (Fullum Interferometer) ----
("p05-interferometer", "fact", "system-overview",
"Custom Fizeau interferometer for in-situ metrology of large optics. Designed for the Fullum observatory polishing facility.",
"vault docs"),
("p05-interferometer", "decision", "cgh-design",
"Computer-generated hologram (CGH) selected for null testing of the 1.2m mirror. Vendor: Diffraction International.",
"vendor correspondence"),
("p05-interferometer", "requirement", "measurement-accuracy",
"Measurement accuracy target: lambda/20 (< 30nm PV) for surface figure verification.",
"system requirements"),
("p05-interferometer", "fact", "laser-source",
"HeNe laser source at 632.8nm. Beam expansion to cover full 1.2m aperture via diverger + CGH.",
"optical design docs"),
("p05-interferometer", "contact", "diffraction-intl",
"Diffraction International: CGH vendor. Fabricates the computer-generated hologram for null testing.",
"vendor records"),
# ---- p06-polisher (Polisher Suite / P11-Polisher-Fullum) ----
("p06-polisher", "fact", "suite-overview",
"Integrated CNC polishing suite for the Fullum observatory. Includes 3-axis polishing machine, metrology integration, and real-time process control.",
"vault docs"),
("p06-polisher", "decision", "control-architecture",
"Beckhoff TwinCAT 3 selected for real-time motion control. EtherCAT fieldbus for servo drives and I/O.",
"architecture docs"),
("p06-polisher", "decision", "firmware-split",
"Firmware split into safety layer (PLC-level interlocks) and application layer (trajectory generation, adaptive dwell-time).",
"architecture docs"),
("p06-polisher", "requirement", "axis-travel",
"Z-axis: 200mm travel for tool engagement. X/Y: covers 1.2m mirror diameter plus overshoot margin.",
"mechanical requirements"),
("p06-polisher", "fact", "telemetry",
"Real-time telemetry via MQTT. Metrics: spindle RPM, force sensor, temperature probes, position feedback at 1kHz.",
"control design docs"),
("p06-polisher", "contact", "fullum-observatory",
"Fullum Observatory: site where the polishing suite will be installed. Provides infrastructure (power, vibration isolation, clean environment).",
"project records"),
# ---- atomizer-v2 ----
("atomizer-v2", "fact", "product-overview",
"Atomizer V2: internal project management and multi-agent orchestration platform. War-room based task coordination.",
"repo docs"),
("atomizer-v2", "decision", "projects-first-architecture",
"Migration to projects-first architecture: each project is a workspace with its own agents, tasks, and knowledge.",
"war-room-migration-plan-v2.md"),
# ---- abb-space (P08) ----
("abb-space", "fact", "contract-overview",
"ABB Space mirror polishing contract. Phase 1: spherical mirror polishing (200mm). Schott Zerodur substrate.",
"quotes + correspondence"),
("abb-space", "contact", "schott",
"Schott AG: substrate supplier for Zerodur mirror blanks. Quote received for 200mm blank.",
"vendor records"),
# ---- atocore ----
("atocore", "fact", "architecture",
"AtoCore: runtime memory and knowledge layer. FastAPI + SQLite + ChromaDB. Hosted on Dalidou (Docker). Nightly pipeline: backup, extract, triage, synthesis.",
"codebase"),
("atocore", "decision", "no-api-keys",
"No API keys allowed in AtoCore. LLM-assisted features use OAuth via 'claude -p' CLI or equivalent CLI-authenticated paths.",
"DEV-LEDGER 2026-04-12"),
("atocore", "decision", "storage-separation",
"Human-readable sources (vault, drive) and machine operational storage (SQLite, ChromaDB) must remain separate. Machine DB is derived state.",
"AGENTS.md"),
("atocore", "decision", "extraction-off-hot-path",
"Extraction stays off the capture hot path. Batch/manual only. Never block interaction recording with extraction.",
"DEV-LEDGER 2026-04-11"),
]
def main() -> None:
parser = argparse.ArgumentParser(description="Seed Trusted Project State")
parser.add_argument("--base-url", default="http://dalidou:8100")
parser.add_argument("--dry-run", action="store_true")
args = parser.parse_args()
base = args.base_url.rstrip("/")
created = 0
skipped = 0
errors = 0
for project, category, key, value, source in SEED_ENTRIES:
if args.dry_run:
print(f" [DRY] {project}/{category}/{key}: {value[:60]}...")
created += 1
continue
body = json.dumps({
"project": project,
"category": category,
"key": key,
"value": value,
"source": source,
"confidence": 1.0,
}).encode()
req = urllib.request.Request(
f"{base}/project/state",
data=body,
headers={"Content-Type": "application/json"},
method="POST",
)
try:
resp = urllib.request.urlopen(req, timeout=10)
result = json.loads(resp.read())
if result.get("created"):
created += 1
print(f" + {project}/{category}/{key}")
else:
skipped += 1
print(f" = {project}/{category}/{key} (already exists)")
except Exception as e:
errors += 1
print(f" ! {project}/{category}/{key}: {e}", file=sys.stderr)
print(f"\nDone: {created} created, {skipped} skipped, {errors} errors")
if __name__ == "__main__":
main()