Set flavor on open workplans from origin/prose/status. Copy existing
depends_on aliases only. Do not promote residuals.
Assistant: grok
Assistant-Session: 01a09dc1-b21e-77e1-919e-fcad2f82b267
The remote row pointed at 127.0.0.1:18000, a reverse tunnel back to the
workstation. On railiance01 the State Hub runs in the cluster on that same
machine, so the request left the box and came back to reach a local service.
Refs CUST-WP-0067-T07
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2583210@bnt-lap001
Assistant-Session: f2bff2d5-e9b2-4338-92ca-10282a927006
Maintainer decision, 2026-07-29: adopts TRSL V1C1 as this repo's
preliminary governing license, per target-revenue's
workplans/TREV-WP-0008-governance-and-pilot-rollout.md T05. Full
specialist legal review is deferred until out of beta (target-revenue
SCOPE.md §1). No Phase is yet declared for this repo.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Housekeeping triggered by the Forgejo daily-todo-md-stale-review flag
(the-custodian issue #5, 12 days stale). Reviewed: the plan was written
2025-12-17 and its dependency (issue-facade) was detached the same day
(capabilities/DETACHED-issue-facade.yaml) and never re-integrated since
-- only a repo-wide rename has touched it in 7 months. No workplan,
roadmap topic, or other repo picked this up. Archived per this repo's
own history/yymmdd-topic/ convention rather than promoted to a workplan
nobody asked for; TODO.md reset to clean.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Sync AGENTS.md, CLAUDE.md, and .claude/rules from updated project_rules
templates: workplan-first session protocol, legacy terminology footnote,
and GET /workplans/ examples.
Add related_to links to markitect-toolkit, infospace-workspace, and
context-engine so federated graph and plan-check can route new work away
from the superseded legacy platform entry.
Honest first-pass maturity vector grounded in README/docs/tests present
in this repo; no invented evidence. Flagged for human review before
publish. See reuse-surface history/2026-07-06-coverage-classification.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- Review integration files; fill SCOPE where templated
- Document dev workflow in stack-and-commands.md
- Seed WP-0002 implementation workplan; mark bootstrap finished
- Hub sync via fix-consistency
`.claude/scheduled_tasks.lock` is per-session runtime state (holds the
owning session id and pid for the ScheduleWakeup queue); it shouldn't
be committed. Widened the pattern to `.claude/*.lock` so future lock
kinds are covered too.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Three coordinated changes that let the pipeline produce a clean
chapter-by-chapter git history on long texts without archaeology after
the fact.
1. Richer commit messages. `SourcePipeline._git_commit` now diffs the
staged changes, buckets added files by output subdirectory (entities,
evaluations, classifications, mappings, analyses, metrics, logs), and
includes counts in the commit body. So `git log` reads "entities:
+23, evaluations: +23" per chapter instead of the same generic blurb
on every commit. Zero behaviour change when no output changed; falls
back to the original message if the diff query fails.
2. --eval-after-source / --classify-after-source on `infospace process`.
After a source's stages succeed, the pipeline identifies which entity
files are *new* (set diff of entity slugs before vs after), loads
their EntityMeta, and runs per-entity evaluation and/or
classification scoped to just those slugs before the per-source git
commit lands. Result: each chapter's commit is self-contained —
extraction + evaluation + classification in one atomic unit. Gated
behind explicit flags because the cost is real (LLM latency per
chapter rather than amortised across one bulk batch).
3. `markitect infospace chapters` subcommand. Lists source files in
canonical order with entity count, evaluated count, classified
count, and mean per-entity score per source. Text or JSON output.
Natural triage surface for long-text infospaces — spot chapters that
under-extracted or evaluated poorly.
Also: `docs/advanced-usage.md` gets a new "Systematic processing of
long texts" section with the recommended flag combo and the tradeoff
note on cost.
11 new unit tests cover the chapters command (text/json/no-sources),
the process flag wiring (help + provider requirement), and the
commit-body bucket logic. Full infospace+llm unit suite (315 tests)
green; 3 pre-existing infospace failures unchanged.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
All three stages of the infospace tooling roadmap are complete. The Wealth
of Nations / VSM example passes 6/6 viability thresholds on 988 entities,
and composition is demonstrated via the supply-chain-vsm example.
- Parent roadmap (roadmap/infospace-tooling/PLAN.md): header now shows the
closed status with final validation metrics.
- S3 close-out plan (roadmap/infospace-s3-closeout/PLAN.md): records the
final task dispositions. C.1–C.6 and C.8 done; C.7 (clean per-chapter
git history) is deferred indefinitely — the task was cosmetic, its
prerequisite branch no longer exists, and reconstructing 35 archival
commits would not change any output files. Rationale documented inline.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- `markitect infospace entity <name>`: single-entity lookup tolerating
hyphens/underscores/case, with substring matching, ambiguity listing,
and near-match hints. Prints slug, source path, domain, chapter, word
count, VSM system, overall score, evaluator, and evaluation file path.
- `markitect infospace evaluate --model-fallback <model>`: if any
entities fail with a rate-limit error, retry just those with a fresh
adapter on the fallback model (different free-tier models have
separate quota buckets).
- `markitect llm-check`: advisory when `OPENROUTER_API_KEY` is set but
not used by the resolved provider; targeted hint when OpenRouter
returns 401 (almost always a stale env key).
- `build_state`: raises `TypeError` with actionable message if passed a
path instead of an `InfospaceConfig` — prior failure mode was a
confusing `AttributeError` deep in the stack.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Five improvements that eliminate most of the agent-in-the-loop friction
observed while closing out the 988-entity WoN evaluation (C.1):
1. Gemini adapter now retries on 429 + 5xx with exponential backoff
(same pattern already used by OpenRouter/OpenAI). Removes the need
for shell-level retry wrappers when hitting free-tier rate limits.
2. evaluate CLI prints the underlying error ("ERROR — HTTP 503 …")
instead of a bare "ERROR", so agents don't have to drop into Python
to diagnose transient failures.
3. --entity/--chapter now respect existing evaluation files by default
(previously only the full-collection pass did). New --force flag
opts into re-evaluation. Stops silently burning free-tier quota on
re-runs of the same slug.
4. --entity accepts hyphenated slugs (matching entity filenames) and
normalizes them to the underscore form used on disk. On a miss the
CLI suggests near matches instead of a bare "not found".
5. eval-summary --update-metrics is no longer destructive:
read_metrics_file/write_metrics_file preserve structured values
(type_distribution) and don't flatten ints to floats. Fixes a
silent data loss observed on every run.
Bonus: the evaluator field in written evaluation frontmatter now
falls back from run_config.model_name to the adapter's resolved model
(or the model echoed back in the API response), so rows no longer
show `evaluator: null` when --model is omitted.
Tests: new tests/unit/llm/test_gemini.py covers retry behavior;
tests/unit/infospace/test_history.py gains a round-trip test that
pins the type_distribution / int-preservation invariants.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
