ingest: add team-ai-Engineering as fourth test-case category A repo instantiated from the template before the shared bash-lib refactor landed surfaces drift in derived projects: ADD for the lib that didn't exist yet, REFUSE for files the template rewired since instantiation. Documents adopt.sh --dry-run as a drift detector complementary to update-from-template.sh.

psaboia committed Jun 25, 2026

lint: correct test-case framing on Adopt-Existing-Repo-Design markov_embeddings_and_rag is the prototype where the pattern was originally explored, not a 'manually adopted' repo. The template was extracted from it and the two evolved in parallel from a common idea ancestor. Found while running scripts/adopt.sh stub against it; the REFUSE on wiki/init-wiki.sh wasn't custom-vs-template, it was parallel evolution.

psaboia committed Jun 25, 2026

ingest: Adopt-Existing-Repo-Design New synthesis page consolidating issue #6 discussion (Priscila's original body + @hegu-1's two follow-up comments) into a concrete design for scripts/adopt.sh. Key reframe from hegu-1 captured: never-touch is computed, not enumerated. Three lists model — ADD allowlist (template-owned), TOUCH grants (host-owned via .llm-wiki-adopt-grants.yml), NEVER-TOUCH (derived). Test approach proposes a controlled fixture + a real-repo dry-run against crcresearch/FUNSD as a no-wiki public candidate. Index updated under Mechanisms (adjacent to other in-design pages).

psaboia committed Jun 24, 2026

log: 2026-06-18 ingest | Lesson-Gitignore-Anchor-Propagation

chrissweet committed Jun 18, 2026

Lesson-Gitignore-Anchor-Propagation — sync-time footgun from PR #39 `.gitignore` leading-slash entries anchor to the repo root of whichever clone the file lives in. Shipping a template-local block through `ALWAYS_FILES` moved the anchor into derived repos, where it silently shadowed their real paths. Mostly latent (tracked files unaffected) but bites: projects that legitimately track `.claude/hooks/`, paths that are untracked at sync time, and contributors confused by `git check-ignore` reporting their own `CLAUDE.md` as ignored. Root cause classified as "scope-sensitive content shipped through a scope-preserving channel" — sister to Lesson-Parallel-File-Drift (same content in two files) but distinct (same file in two scopes). Pages touched: - Lesson-Gitignore-Anchor-Propagation.md (new) - Home_llm-wiki-memory-template.md (Lessons learned entry) - index_llm-wiki-memory-template.md (Lessons learned entry) - Sync-Flow.md (See also back-ref) - Lesson-Parallel-File-Drift.md (See also back-ref) - Lesson-Template-Contribution-Discipline.md (See also back-ref)

chrissweet committed Jun 18, 2026

log: lint fix dead wikilinks + Home sync Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

lint: fix dead wikilinks + sync Home with Lesson-Template-Contribution-Discipline Two findings from routine lint after today's ingest: - Yesterday's log entry for the Analysis-of-Wiki-Push-Race-Pattern ingest used [[wikilink]] syntax for personal Claude memory file names (project-web-forager-wiki-multi-writer, feedback-wiki-write-default-multi-writer). They are not wiki pages; the wikilink syntax tripped the lint pass as dead links. Replaced with backticked plain text plus an explanatory note that these are per-user personal memory, not wiki pages. - Home was missing the new Lesson-Template-Contribution-Discipline page. Per PR #32's category-level rule a new Lesson joining an existing category warrants a Home representative-link slot. Added under Lessons learned, fourth entry. Health otherwise clean: no orphans, no other dead links, no missing frontmatter, no index gaps, no untyped pages. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

log: ingest Lesson-Template-Contribution-Discipline Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

ingest: Lesson-Template-Contribution-Discipline New synthesis page filed in response to user observation that lessons learned during template development should live in wiki memory rather than per-user Claude local memory, so they survive a clean pull (via --dev-self per PR #25). Captures four rationalizations and their empirical incidents: 1. Defaulting to single-writer when web_forager proved multi-writer (incident: 2026-06-12 Omegaice/csweet1 log_*.md collision, ~3 min manual reconcile). 2. Introducing speculative "Option C" integrations the user did not propose (MCP overreach in PR7's first draft, pushed back on 2026-06-13). 3. Hardcoding speculative PR numbers in code (PR #28 stale #26 references; Priscila cleaned up four in commit e48f7d4). 4. Adding structural assertions that lock historical state rather than catch behaviour regressions (PR6's three rename-locking assertions, flagged 2026-06-13). Each pattern has the same shape as Discipline-Gates' Universal Rationalizations, just one layer up: instead of rationalizing a bad wiki entry, the agent rationalizes a bad PR draft, a noisy test, or a stale reference. Discipline-Gates See-also gains a back-reference. Sister page to Lesson-Hook-Type-Matters, Lesson-Parallel-File-Drift, Lesson-Validation-Methodology — matches their synthesis-type + empirical-motivation style. After this lands the four corresponding personal Claude memory entries can be deleted; the lessons now live where they survive a clean pull. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

log: lint reconcile classifications after cluster + PR6 land Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

lint: reconcile classifications after cluster + PR6 land Five model_fusion-cluster PRs (#28-#32) merged on 2026-06-12 and PR6 (#33, wiki-write-protocol rename) opened with CI green on 2026-06-13. Implementation-Status, Multi-Agent-Write-Protocol, and Limitation- Inverse-Edges-Missing still classified all of this work in its pre-merge form. Bringing them to current state. Implementation-Status: - Five new Implemented rows for PRs #28-#32 (Memory boundary, analysis + decision page types, SessionStart auto-load, inverse-edge vocabulary, Home category-nav). Each row names the specific files that landed and the Analysis-of-model_fusion-Recommendations rec it closes. - The previously single Aspirational Multi-Agent-Write-Protocol row split into three: production wiring (PR7, planned), inverse-edge upstream SHACL spec (deferred), inverse-edge PostToolUse write-time check (deferred). - New In-review row for PR #33 (PR6 rename, CI green, mergeStateStatus CLEAN). Multi-Agent-Write-Protocol banner: appended a 2026-06-13 update referencing PR #33 and the PR6/PR7 housekeeping-then-wiring split. Limitation-Inverse-Edges-Missing: substantively rewritten. Title now "(Partially Closed)". The proposed-fix snake-case inverse names (extended-by:, supported-by:, criticized-by:) replaced with the camelCase names that PR #31 actually shipped (extendedBy, supportedBy, criticizedBy) and that match Edge-Types.md.template. The "KG materialises inverses, agents do not author them" stance made explicit. New "What remains" section names the upstream SHACL gap and the optional PostToolUse check. Status: in-repo half closed, upstream half + write-time check still pending. Wiki-Corrections-Log entry appended with the receipt. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 13, 2026

log: ingest Analysis-of-Wiki-Push-Race-Pattern + Multi-Agent-Write-Protocol reclassification Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

ingest: Analysis-of-Wiki-Push-Race-Pattern + reclassify Multi-Agent-Write-Protocol New type: analysis page filed in response to a 2026-06-12 production collision in wiki/web_forager.wiki/ (3-4 human+agent teams; Csweet1 push rejected after Omegaice advanced remote by 20 commits in the interim; conflict on log_web_forager.md from same-date entries from both authors; ~3 minute manual rebase recovery). The Multi-Agent-Write-Protocol prototype at scripts/multi-agent-write-protocol-proto/ (shipped in PR #11; 9/9 CI scenarios green on ubuntu-latest + macos-latest) handles exactly this collision shape automatically via wiki_push's mechanical union-merge for log_* files. The prototype is implemented but not wired into any agent overlay; the only callers are the 9 CI scenarios. Reclassification: the Multi-Agent-Write-Protocol banner is rewritten from "design + prototype only, not yet wired" to "design + prototype shipped, production wiring is the gap." Implementation-Status's row is updated to name the wiring (not the design) as the specific gap and to outline what a wiring PR should contain. Second type: analysis page filed (after Analysis-of-model_fusion- Recommendations earlier today). Both acknowledge the SCHEMA violation that PR #29 closes. Cross-references: Multi-Agent-Write-Protocol gains See-also entry to the new page; Analysis-of-model_fusion-Recommendations and Lesson-Validation-Methodology gain back-refs as sister/related pages. Index updated under Applied examples (after the sister analysis page). Home updated per PR #32's category-level rule: the page is significant enough to warrant a Home entry, not just an Index entry. Wiki-Corrections-Log entry appended for the receipt. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

log: lint Home sync — model_fusion entries + KG status refresh Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

lint: Home sync — add model_fusion pages, refresh KG status Two drifts found on Home that earlier-today ingests/lint didn't update: - Line 29: KG-Pipeline still said "designed, not yet implemented". The morning's KG aspirational -> implemented correction (commit 6cd8197) updated 9 pages but missed Home. Refreshed to the Index form: "PR #14: scripts/kg/, rdflib + pyshacl in-process; SPARQL over wiki frontmatter, optional Fuseki". - Applied examples: Lessons-Learned-From-model_fusion and Analysis-of-model_fusion-Recommendations were both filed earlier today and added to Index but not to Home. Both qualify as representative-link material per PR #32's category-level rule. Added under Applied examples on Home with one-line descriptions matching Index. This is effectively the first lint pass under PR #32's just-shipped Home category-nav convention, even though #32 hasn't merged yet — the fix-pattern matches what its new Verification Gate criterion will enforce mechanically. Wiki-Corrections-Log entry appended. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

log: ingest Analysis-of-model_fusion-Recommendations Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

ingest: Analysis-of-model_fusion-Recommendations (first type: analysis page) Assessment of the 12 recommendations in Lessons-Learned-From-model_fusion, filed in response to user's question about which would bring the greatest value. Endorses #1 SessionStart auto-load, #4 analysis/decision page types, #8 Claude-memory boundary, #9(b) reciprocal-edge enforcement. Pushes back on #10 (variant proliferation risk), #6 (belongs in lint over the KG, not a hook), #11 (overlaps with auto-compact), #2 (false- positive risk). Dogfood: filed under type: analysis, which is not declared in SCHEMA -- the point being that this is the exact gap recommendation #4 names. The page is empirical evidence for the recommendation it endorses. SCHEMA violation acknowledged in the page body. Index updated under Applied examples. Lessons-Learned-From-model_fusion See-also gains the reciprocal back-reference. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

log: lint refresh Lessons-Learned-From-model_fusion to HEAD 88f4624 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

lint: refresh Lessons-Learned-From-model_fusion to HEAD 88f4624 Page declared verification against fc2472a (2026-06-04), an unresolvable fork-local SHA. Refreshed against actual current HEAD 88f4624 (2026-06-12). Three commits between the original snapshot and HEAD touch the field report's 12 recommendations: - PR #14 / 2018186: scripts/kg/ (KG pipeline shipped, rdflib + pyshacl) - PR #16 / b86c9e4: wiki/Edge-Types.md.template (inverse-edge vocabulary) - PR #25 / 88f4624: scripts/instantiate.sh --dev-self (recursive bootstrap fix shipped) Page updates: - Headline tally refreshed: 0 fully addressed / 3 partial / 9 missing, plus recursive-bootstrap RESOLVED. - Table row 9 refined: inverse vocabulary shipped but not yet wired into init-wiki.sh page-type list; PostToolUse does not enforce. - Body #9(a) rewritten to reference the shipped vocabulary and KG pipeline rather than designed-but-pending. - "The recursive bootstrap problem" section flipped to "RESOLVED in PR #25" with --dev-self behavior enumerated. - Provenance path corrected (/TCF/ -> /CRS_research/, the only real checkout) and the unresolvable fc2472a flagged as fork-local. 5 bidirectional back-references added on the high-value related: entries (sister page + three lessons + one limitation). The other 5 (Verification -Gate, Discipline-Gates, Three-Operations, PostToolUse-Hook, Implementation -Status) left one-way per the morning's heavily-linked roll-up rule. Wiki-Corrections-Log appended with the second-pass entry. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

log: lint KG aspirational -> implemented + bidirectional back-references Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

lint: KG aspirational -> implemented; bidirectional back-references; example cleanup Stale-claim correction: PR #14 shipped scripts/kg/ (rdflib + pyshacl in-process KG pipeline) to template main, but nine wiki pages still described the pipeline as aspirational. Reclassified Knowledge-Graph- Pipeline to implemented; corrected architecture from Fuseki to rdflib + pyshacl; flagged the distribution gap (scripts/kg/ not yet in ALWAYS_FILES, likely to ship as features/kg/ under RFC #13). Updated Implementation-Status, Wiki-LLM-Pattern, Three-Operations, Typed-Edges- and-Frontmatter, SCHEMA, Limitation-Inverse-Edges-Missing, Sync-Flow, and the index to match. Example cleanup: Wiki-LLM-Pattern line 23 used the placeholder example [Markov-Chain-v5c2](Markov-Chain-v5c2). Replaced with a real wiki page name so lint and the KG see a valid edge. Bidirectional back-references added for the high-value concept <-> lesson / limitation pairs (Verification-Gate, Discipline-Gates, Lesson- Validation-Methodology, Lesson-Parallel-File-Drift, Template-vs-Derived- Projects, PostToolUse-Hook, Agent-Overlays). Index/log roll-ups (Implementation-Status, Wiki-Corrections-Log) intentionally left one-way. Wiki-Corrections-Log entry appended with the receipt. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

ingest: Lessons-Learned-From-model_fusion (field report + 12-gap verification table) New synthesis page filed as a sister to Applied-Example-Microelectronics-Tutor-Demo: a second empirical test of the template from a different domain (NIR + PAD pharma analytics, 43 wiki pages, ~5 months of active curation in PaperAnalyticalDeviceND/model_fusion). Headline content: - Verification table of 12 implementation-gap recommendations against current template HEAD fc2472a: 0 fully addressed, 2 partial, 10 still missing. - Each recommendation labelled with empirical motivation (what fell through the cracks in the source session) and a refined fix. - Cross-references existing template lessons (hook-type-matters, parallel-file-drift) and the inverse-edges-missing limitation that recommendation #9 builds on. - Includes the "recursive bootstrap problem": cloning the template lands contributors without llm-wiki context. Proposed fix: dev-mode bootstrap that clones the template's own GitHub Wiki locally, gitignored and excluded from the instantiate allowlist. Updates the index Applied-examples section and appends a log entry. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 12, 2026

log: lint entry for Multi-Agent-Write-Protocol redesign Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 1, 2026

Rewrite Multi-Agent-Write-Protocol as push-time-only + SessionStart Replaces the per-agent-branch design with a transparent push-time-only wrapper. Agents work directly on local main (standard git workflow); the wiki-push wrapper handles conflict resolution only when an optimistic push is rejected. The complementary session_start hook keeps the agent's read view fresh and defers cleanly (no auto-rebase) on divergence. Key spec changes: - "Design at a glance" table separates read freshness, write collision prevention, and mechanical merges as three concerns with one mechanism each. - "The protocol" split into two subsections (session start; write). Session start has four outcomes (up-to-date / fast-forward / ahead / diverged); only fast-forward modifies local main. - "Default behaviour: don't push" section makes explicit that the protocol replaces the *mechanics* of push, not the *policy* (agents don't push by default; user asks or agent asks first; push then means invoke wiki-push). - "Wiki only" scope made explicit (project main repos keep existing conventions). - Six worked examples (added two for session_start outcomes). - Failure modes section gains halt-at-cap recovery: local main has the un-pushed work + any partial merge commits; agent or user decides to keep retrying / abandon / cherry-pick. Implementation-Status updated to reflect the prototype's CI-green status on the template fork at chrissweet/llm-wiki-memory-template branch multi-agent-write-protocol-proto. Log entry follows in a separate commit per Log-Entry-Attribution. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed Jun 1, 2026

log: ingest entry for Multi-Agent-Write-Protocol page Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026

Ingest Multi-Agent-Write-Protocol spec page A new aspirational page documenting an OCC-with-semantic-retry write protocol for wikis with multiple LLM-agent writers. The protocol prevents push-level collisions by construction: each agent writes via its own contribution branch, attempts a merge against current main, and either pushes cleanly or re-plans its writes semantically before retrying. No separate reconciler is needed; the writing agent reconciles its own attempts. The page covers: the protocol's six steps; conflict classification (union-merge for index/log files via .gitattributes, three-way merge for non-overlapping content, semantic resolution for overlapping content); required agent capabilities; failure modes (livelock cap K=3, network faults, stale branches, name collisions); four worked examples spanning the mechanical-merge and semantic-resolution cases; open questions; and cross-references to existing wiki pages (Verification-Gate, Sync-Flow, PostToolUse-Hook, etc). Implementation-Status gains the page under Aspirational, pointing at the deterministic prototype in progress at the Omniscient_2 sister repo. Home and index updated in the Mechanisms section. Log entry follows in a separate commit per Log-Entry-Attribution. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026

log: ingest entry for Test-Harness page (PR #10 documentation) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026

log: lint entry for 2026-05-31 wiki-vs-code reconciliation (retroactive) Appends the log entry for commit 8601db0 (the corrections work) that was missed in the original commit cycle. The Verification Gate criterion "log entry appended" was not run; this commit is the receipt. Per Log-Entry-Attribution: one commit per log entry, separated from the content commits. This entry refers backwards to 8601db0 as the content commit it documents. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026

Ingest Test-Harness page; add In review bucket to Implementation-Status Documents scripts/test-mvp/ and the GitHub Actions workflow that ship in PR #10 (chrissweet/llm-wiki-memory-template add-test-harness), addressing template issue #5. The harness implements the structural half of Lesson-Validation-Methodology: smoke against real template, e2e against a simulated derivative with MVP patches applied. 91 assertions across 1 smoke + 6 e2e stages on bash 3.2-compatible code, matrix on ubuntu and macOS. The page makes the gap-analysis explicit: the harness covers stage 2, stage 5, and Agent-Instance assertions in stage 1 that the trimmed MVP slates for deferral; the harness does NOT yet cover ALWAYS_FILES updates to the sync scripts (the footgun Sync-Flow documents and PR #1 hit). Filed as follow-up work, not yet implemented in the harness. Implementation-Status gains a fourth bucket ("In review") for features that exist as code in an open PR but are not yet merged into template main. Home and index updated in the Mechanisms section. Log entry to follow in a separate commit per Log-Entry-Attribution convention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026

Flag KG pipeline aspirational; correct none-overlay framing; fix Sync-Flow ALWAYS_FILES; add Implementation-Status + Wiki-Corrections-Log Reconciles the wiki with the template code on main, where notes-driven documentation had drifted from what shipped: - Knowledge-Graph-Pipeline is described across 8 pages as if implemented, but scripts/kg/build-graph.sh does not exist in the template repo. The source page now carries a NOT YET IMPLEMENTED banner and a status: aspirational frontmatter field. Citations on the seven dependent pages are softened to "designed, not yet implemented" so the aspirational status is visible at every mention. - The none "overlay" is not an overlay: --agent=none in instantiate.sh is a no-install flag, and there is no wiki/agents/none/ directory. Limitation-Untested-Overlays and Agent-Overlays are reframed accordingly, separating minimal mode from the two true overlays (claude-code, cursor). Limitation-Untested-Overlays also corrects a phrasing claim: the README uses "Shipped but not yet validated" / "Likewise unvalidated", not "untested-live". - Sync-Flow's ALWAYS_FILES section was inaccurate: it mixed contents from four separate arrays and listed the nonexistent scripts/kg/*.sh. Section rewritten to describe all five arrays (ALWAYS_FILES, CLAUDE_FILES, CURSOR_FILES, ONE_SHOT_FILES, SUBSTITUTE_FILES) with the file lists actually present in the sync scripts on main. New pages: - Implementation-Status.md: single normative source for what is real today vs aspirational, with a Partially Implemented bucket for Cursor's structural-but-not-behavioral validation. - Wiki-Corrections-Log.md: append-only log of each correction; this commit is the first entry. Home and index updated with a "Governance and meta" section linking the two new pages. Verification debts noted in the Corrections Log but not corrected this round: Applied-Example-Microelectronics-Tutor-Demo staleness, the permission-model claims in Limitation-Prompt-Injection-Residual, and the existence of chrissweet/llm-wiki-tutor-template cited by Governance. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chrissweet committed May 31, 2026