rootandClaude Opus 4.7 779158a09b scripts: chicago analyzer field-name fixes + vectorize sanitizer hardening ...

Two small fixes surfaced during smoke testing:

analyze_chicago_contracts.ts: permit field is contact_1_name not
contact_1; reported_cost is integer-string. Fixed filter (was rejecting
all 2853 permits) and contractor extraction (was empty).

vectorize_raw_corpus.ts: sanitize() expanded to strip control chars +
ALL backslashes (kills incomplete \uXXXX escapes) + UTF-16 surrogates
(unpaired surrogates from emoji split by truncate boundary). Llm_team
response cache had docs with all three pollution shapes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-25 19:34:45 -05:00

..

ab_t3_test.sh

qwen3.5 executor + continuation primitive + think:false

2026-04-20 20:19:02 -05:00

analyze_chicago_contracts.ts

scripts: chicago analyzer field-name fixes + vectorize sanitizer hardening

2026-04-25 19:34:45 -05:00

autonomous_agent.py

Fix: job tracker field name mismatch — the overnight killer

2026-04-17 10:41:32 -05:00

copilot.py

Staffing Co-Pilot — the anticipation layer that changes everything

2026-04-17 00:19:07 -05:00

dump_raw_corpus.sh

raw-corpus dump + vectorization + chicago contract inference pipeline

2026-04-25 18:44:27 -05:00

generate_demo.py

Phase 6: Ingest pipeline — CSV, JSON, PDF, text file support

2026-03-27 08:07:31 -05:00

generate_workers.py

MCP server (Bun) + 100K worker generator + lakehouse integration

2026-04-16 23:54:33 -05:00

kb_measure.py

Item 3 — geo-filtered playbook boost; diagnostic logging

2026-04-20 21:35:04 -05:00

kb_staffer_report.py

Phase 23 — contract terms + staffer identity + competence-weighted retrieval

2026-04-20 22:16:09 -05:00

lance_tune.py

IVF_PQ recall tuned from 0.80 → 0.97 via parameter sweep

2026-04-16 22:08:34 -05:00

overnight_proof.sh

Fix: job tracker field name mismatch — the overnight killer

2026-04-17 10:41:32 -05:00

quality_eval.py

Quality evaluation pipeline — tests correctness, not just structure

2026-04-16 22:14:06 -05:00

qwen3_plan.py

Qwen 3 integration + agent plan + playbook loop

2026-04-17 00:08:48 -05:00

run_kb_batch.sh

Lift k cap, drop ornamental reason field, scenario generator

2026-04-20 20:31:34 -05:00

run_staffer_demo.sh

Phase 23 — contract terms + staffer identity + competence-weighted retrieval

2026-04-20 22:16:09 -05:00

scale_10m_test.sh

10M vector scale test — cron heartbeat, runs while J sleeps

2026-04-17 01:06:38 -05:00

scale_test.py

Scale test: 2.47M rows + 10K vector index benchmarked

2026-03-27 08:31:37 -05:00

seal_agent_playbook.ts

pathway_memory: Mem0 versioning + deletion (upsert/revise/retire/history)

2026-04-25 19:31:44 -05:00

serve_imagegen.py

Ingest Ethereal 10K worker profiles — domain data in the substrate

2026-04-16 22:26:19 -05:00

serve_lab.py

Ingest Ethereal 10K worker profiles — domain data in the substrate

2026-04-16 22:26:19 -05:00

serve_ui.py

Systemd services: gateway, sidecar, UI survive reboots

2026-03-27 22:06:28 -05:00

staffing_day.py

Staffing day simulation: 94% pass, all gates clear, ready for batching

2026-04-17 00:14:34 -05:00

staffing_demo.py

PRD v2: production roadmap with ingest, vector search, hot cache phases

2026-03-27 07:54:24 -05:00

staffing_simulation.py

Fix staffing simulation verifier + clean regression: 0 hallucinations

2026-04-16 23:28:54 -05:00

stress_test.py

Stress test suite: 9/9 passed — architecture validated

2026-03-27 22:13:27 -05:00

vectorize_raw_corpus.ts

scripts: chicago analyzer field-name fixes + vectorize sanitizer hardening

2026-04-25 19:34:45 -05:00