Commit History
10 days ago
-
docs(plans): Phase 3 s3 done — the smoke Job exists and its first run came back 6/6
avoigt1121 +1: Claude Opus 5.5Slice: phase3-review-hardening/s3 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>7f95498 -
feat(smoke): the scheduled smoke Job, and the plan's decisions
avoigt1121 +1: Claude Opus 5.5scripts/smoke_job.py creates, lists, fetches and deletes the Phase 3 smoke Job as decided 2026-10-29 (D1-D4): an HF Scheduled Job on cpu-basic in the project lead's organisation namespace (her user namespace holds lit-agent's Monday job, whose recreate script aborts on a second scheduled Job), every 3 hours, ending itself after 7 days (SMOKE_END_EPOCH), with no secret: each run clones the dev Space at a pinned sha, runs smoke_live.py in-process and prints its counts-only record behind RECORD_MARKER (new --print-record), and fetch reads the records back from the Job logs into .smoke/hf-job.jsonl. tests/test_smoke_job.py pins the spec (no secret, cpu-basic, org namespace, one Job at a time, the end guard, the pinned sha) and the log parsing. The addendum gets one sentence on the scheduled runs (plan C8); the plan records D1-D4. Slice: phase3-review-hardening/s3 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>814e741 -
docs(plans): Phase 3 review and hardening — plan, D1-D4 open
avoigt1121 +1: Claude Opus 5.5Smoke week, cost and latency report. D1 where scheduled runs execute, D2 cadence, D3 cost cap and D4 where results go are the project lead's; s1 (harness) done, s2 (report) drafted outside this repo, s3/s4 blocked on the decisions. Slice: phase3-review-hardening/s1 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>cbcabf5
13 days ago
-
docs(plan): s5 is on orchestrator prod (46f8006, 2026-10-23)
avoigt1121 +1: Claude Opus 5.5Status cell brought in line with git on 2026-10-26. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>1eefa35
17 days ago
-
docs: the security-review addendum is to be filed now (decided 2026-10-22, the project lead)
avoigt1121 +1: Claude Opus 5.5Recorded at the source: the plan's s4 row, its D2 note and s4 bullet, and ADR-0001's consequence line. The project lead files it; nothing is sent from a session. Slice: phase1-knowledge-specialist-s4 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>aa10ca2 -
docs(plans): s5 on orchestrator dev 62e1e23 (C10-C12 met; C1 is the project lead's); the name scrub
avoigt1121 +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>a145232 -
docs: name no institution in the public repo (the client's Tech Transfer rule)
avoigt1121 +1: Claude Opus 5.5Both Spaces are public. The client's sponsoring lab ruled 2026-10-21 that its technology-transfer office looks before anything public carries the institution's or the centre's name, and the contract needs written consent for either. Ten mentions in docs, docstrings and comments now say "the client" or "this agent's endpoints"; the title, card, README and UI never named either. tests/test_no_institution_name.py fails if a tracked file names them again. The paste-ready addendum in the business folder is unchanged. Comments and docs only: no behaviour change. 246 passed; host table current. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>081f1c7
18 days ago
-
docs(plans): s3 on prod f1bf43d, s6 done, s5 merged on orchestrator dev (dev push blocked by KNO-006)
avoigt1121 +1: Claude Opus 5.5Slice: phase1-knowledge-specialist-s3 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>92fb816 -
docs(plans): s4 on dev; C13 drafted
avoigt1121 +1: Claude Opus 5.5Slice: phase1-knowledge-specialist/s4 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>b67e00e -
docs(plans): s2 on dev at af3e3ac; s3 open; what s2 changed
avoigt1121 +1: Claude Opus 5.5Slice: phase1-knowledge-specialist/s2 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>e84baa9 -
security: D5-A — accept the 8 pillow 12.3.0 CVEs here until 2026-11-20
avoigt1121 +1: Claude Opus 5.5The project lead decided D5-A (2026-10-20): a justified acceptance in this repo only. This Space takes identifiers only and opens no caller-supplied image; the fix needs a fleet-wide gradio move (gradio 6.28.0 requires pillow<13). security/accepted-vulns.txt feeds pip-audit --ignore-vuln; the scan fails on an expired entry, and tests/test_accepted_vulns.py fails once the lock moves pillow off 12.3.0, so the acceptance cannot outlive its reason. Scan green. Slice: phase1-knowledge-specialist/s2 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>17acd0c -
security: accept one gitleaks false positive by fingerprint; record the open pillow CVEs as D5
avoigt1121 +1: Claude Opus 5.5The s1 security record quoted the docstring phrase it called a false positive, so it tripped the same rule; reworded, and the never-pushed commit is ignored by its exact fingerprint. pillow 12.3.0 (via gradio 6.28.0, pillow<13) has 8 new CVEs fixed only in 13.0.0, fleet-wide: not accepted, raised as plan D5. Slice: phase1-knowledge-specialist/s2 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>e119adb
19 days ago
-
docs(plans): s1 on dev at 5b9f592; s2 and s4 open
avoigt1121 +1: Claude Opus 5.5Slice: phase1-knowledge-specialist/s1 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>8444397 -
feat: governed ToolUniverse core for the knowledge specialist (s1)
avoigt1121 +1: Claude Opus 5.5The repo from the pdac-spatial-agent template, plus the core every endpoint will sit on (ADR-0001, accepted 2026-10-20): - config/tools_allowlist.yaml: the memo's 28 tools by exact 1.5.6 name; the 12 the five endpoints use are the only ones loaded. - config/sources.yaml: 8 sources with hosts, licences checked 2026-10-20 (Reactome is CC0, not CC BY 4.0; DGIdb unconfirmed, so no DGIdb endpoint), TTLs, rate limits, timeouts, coverage notes. - src/tu_client.py, the only importer of tooluniverse: loads with keep_default_tools=False and load_workspace=False, refuses startup on any model-provider key, a version other than 1.5.6, an extra or forbidden tool, or ToolUniverse's own cache being on. load_workspace=False matters: with any workspace present, 1.5.6 seeds a profile that loads all 2,691 tools and reads workspace and ~/.tooluniverse .env files (found by these tests). - provenance (10 fields per row), pinned output schemas (drift = no rows), SQLite cache that keeps retr…377417d