Digital Garden

refactor | Audit round 3: dedup site styles, single-read lint, doc consolidation

Thu, 30 Jul 2026 00:00:00 GMT

Single-sourced the category key: new --category-{concept,entity,source,note} tokens in color.css plus a shared category-dot.css rule now feed the backlink chips, the graph legend, and the graph canvas (which resolves the same variable names through its probe node) — three hand-synced copies of the same four colors collapsed to one, with TYPE_BY_CATEGORY exported from contract.ts so the legend derives from the contract instead of hardcoding it.
Extracted entry-list.css from the category listings and the per-tag pages, which carried ~45 lines of byte-identical CSS; each page now keeps only its own deltas (tag pages’ ellipsis clipping, the entity source-count and letter-group rules).
Unified the two listing branches in [category]/index.astro behind a single group shape (an ungrouped listing is one unlabelled group). Fixes a latent bug: the letter-grouped branch omitted entry-count, so entity (sources: N) badges would have silently vanished had Entities ever passed 24 pages.
wiki_lint.py now reads each page once — frontmatter and [[links]] are parsed at collection time and carried on Page — instead of re-opening every file in four separate checks. Measured on this repo: 330 file reads → 82, 4–5 reads per page → 1. No behavior change; 59 Python tests still pass.
Removed dead code: skeleton.css (18 lines, unreferenced, describing Music/Movies/Mastodon feeds this repo doesn’t have), an unused Node type re-export in remark-wiki-links.ts, and the unused --primary / --primary-foreground / --destructive / --red-9 / --red-11 / --aspect-video tokens. The gray/space/radius/blur scales were left whole on purpose — a scale is a system, not a per-use token.
Docs: the lint check catalog lived in five places (script docstring, scripts/README.md table, CLAUDE.md Lint Layer 1, CLAUDE.md Ingest step 9, root README). The scripts/README.md table is now canonical and the other four point at it; CLAUDE.md shed ~1.1K chars with no loss of workflow instruction.
Verified: wiki_lint clean, 59 Python tests, 45 Bun tests, astro check 0 errors, 214 pages built (unchanged), Biome clean. Listing/legend/backlink rendering checked against computed styles in a real browser — pixel-identical.
pages touched: none (site + scripts + docs only).

refactor | Audit round 2: literal-code guard, strict MIME, dev-fresh snapshot

Sat, 25 Jul 2026 00:00:00 GMT

rehost_images.py now treats image syntax inside fenced code blocks, inline code, and HTML comments as literal text: a shared protected-span pass (line-based fence tracking, then inline/comment scan over fence-masked text) gates both the URL scanner and the rewriter, so protected occurrences are neither downloaded nor rewritten.
Content-Type is authoritative in rehost_images.py: a declared non-image type (e.g. text/html on a .png URL) is rejected outright; the URL-suffix fallback applies only when the server declares nothing useful (missing or octet-stream).
Garden snapshot memo is now production-only; astro dev rebuilds per request. Verified against the audit repro: edit index.md → the next /search.json response reflects it without a restart; site/README.md dev caveat rewritten (content edits reload live; only brand-new pages still need a restart).
Tests: Python 43 → 59 (protected-region matrix, _ext_for matrix, masquerading-HTML and missing-content-type fetch cases); Bun 45, astro check 0 errors, build 214 pages — all green.
pages touched: none (scripts + site infrastructure only).

refactor | Contract-driven lint + hardened rehoster + index cleanup (audit follow-up)

Sat, 25 Jul 2026 00:00:00 GMT

Added garden.config.json — root-level contract for categories (slug + type), search order, wiki-link grammar (incl. table-escaped [[slug\|alias]]), raw filename grammar, and the 100-char index summary budget; consumed by scripts/wiki_lint.py at runtime and site/src/lib/contract.ts at build time (six previously drifting definition sites collapsed to one).
Rewrote wiki_lint.py as a contract validator: exits 1 on findings (--report-only keeps exit 0), sees escaped-pipe links, flags cross-category duplicate slugs, and newly checks index format / section membership / alphabetical order / summary length / entity (sources: N) counts, frontmatter type-vs-category, and raw-file naming; 28 stdlib unit tests plus a Python↔TS link-grammar consistency corpus (tests/link-grammar.json).
Hardened rehost_images.py: URL rewrites now happen inside image nodes only (a plain link to the same URL stays untouched); downloads follow redirects manually with per-hop public-IP validation, reject non-image content-types before reading the body, and stream under a 25 MiB cap with timeouts; 15 mock-transport unit tests.
index.md cleanup driven by the new lint: 3 Concepts sort inversions fixed; all 52 over-budget summaries rewritten to ≤ 100 chars; claude-code count corrected 4 → 5; openai count 7 made verifiable by linking the entity at first mention in the two source pages that only named it in prose.
Site: garden data layer now builds one memoized snapshot per build (pages + link graph + canvas/search datasets) instead of re-deriving per route; pure modules link-graph.ts / index-summaries.ts extracted; buildSlugMap throws on duplicate slugs; 32 new bun tests (45 total).
raw/ narrowed to markdown-only in CLAUDE.md (was: PDFs/images allowed that the site couldn’t render); enforced by the lint’s raw-naming check.
CI: wiki_lint gates via exit code (grep hack removed), Python tests run under uv, actions pinned by SHA, Bun pinned via .bun-version.
pages touched: 2026-04-27-agent-principles-architecture-engineering, 2026-06-04-llm-powered-autonomous-agents

refactor | Canonicalize source→raw pointers; site derives the link from the slug

Sun, 19 Jul 2026 00:00:00 GMT

Problem surfaced by the human: 2026-07-07-harness-engineering-self-improvement wrote its raw pointer as bare inline code (Raw file: ...) instead of the linked form the other 10 source pages use, so the site’s relative-raw-link rewrite never fired and the page rendered with no route to /raw/.
Fixed the page to the canonical form: Source file: [`raw/<slug>.md`](../../raw/<slug>.md).; updated: bumped.
Site hardening so the affordance no longer depends on prose format: /sources/<slug> pages now always render an “Ingested copy” link in the header callout, derived from the source page and raw file sharing a slug (mirror of the existing reverse pointer on /raw/<slug>). All 11 source pages verified carrying it in the built output.
Documented the canonical Source file: line in CLAUDE.md (Ingest step 5) and the slug-derived callout in site/README.md.
Verification: wiki_lint.py clean; site bun test 13 pass, astro check 0 errors, build 214 pages.
pages touched: 2026-07-07-harness-engineering-self-improvement

query | "New understanding of Harness after the RSI survey + recent ingests?"

Sat, 18 Jul 2026 00:00:00 GMT

Synthesized the harness thread across the Jul 2026 ingests: Weng RSI survey (Jul 7) + first-party vendor batch (Jul 12: Codex Windows sandbox, loop engineering, model & effort level).
Added Postscript 2 (2026-07-18): from thesis to product surface to harness-why-it-matters-now; intro reframed (6-of-11 sources, two postscripts); Postscript 1 retitled with its date.
New claims filed: four-part frame now has a shipped primitive per row; cost/token budget as a harness dimension the Q1–Q2 sources lacked; effort dial as early internalization evidence (marked inference); Weng’s evaluator-outside-the-loop prescription already shipped as sandbox write carve-outs.
Tracker updates recorded: cross-domain portability moved partially; 10×/6× decompositions and the counter-example still missing; new watch item — /goal’s unspecified evaluator model as a reward-hacking surface.
index.md note summary refreshed; wiki_lint.py clean.
pages touched: harness-why-it-matters-now

refactor | Source-title cleanup + mobile nav tweak

Sat, 18 Jul 2026 00:00:00 GMT

2026-07-12-codex-windows-sandbox-engineering: dropped the redundant English half of the bilingual title: — the raw file (OpenAI’s official zh-Hans page) is Chinese-titled, matching the other Chinese-language sources. updated: bumped.
Site: Sources nav item is now wide-viewport-only (the mobile top bar overflowed with four items plus the toggles).
pages touched: 2026-07-12-codex-windows-sandbox-engineering.

refactor | Site refinements

Sat, 18 Jul 2026 00:00:00 GMT

Site round-2 polish per human review: production URL set to wiki.lkwplus.com; title/subtitle/footer reworded as “a naive frontend for the LLM Wiki”; source pages surface the original-article link as a callout above the prose (header separator-underline glitch fixed); backlinks redesigned as type-keyed chips; homepage stats restyled after lkwplus.com/tokens “All-time patterns”; astro-erudite credited in the footer and site/README.md.

refactor | Static site frontend (site/) + repo hardening

Sat, 18 Jul 2026 00:00:00 GMT

Added site/ — an Astro + Bun static frontend rendering the garden read-only. Wiki links ([[slug]], [[slug|alias]], table-escaped [[slug\|alias]]) resolved by a custom remark plugin matching wiki_lint.py’s grammar; backlinks computed and shown on every page; index.md one-liners reused verbatim for listings, the ⌘K search palette and hover previews; log.md parsed into an activity timeline (also the RSS feed); math rendered to MathML via Temml; force-directed canvas graph of all pages and links. Design tokens mirror lkwplus.com (Radix gray light-dark() scale, Geist fonts, Utopia scales, 1px-border surfaces).
Site is a display layer only: it owns no content and normal Ingest/Query/Lint never touches it. Documented in site/README.md; coupling points recorded in CLAUDE.md (Layout section).
Rehosted the one remaining third-party image URL in raw/ (2026-04-27-harness-engineering-codex-agent-first.md, Contentful → R2, 4ba6c70266181619.webp); the original ingest had reported “1 image rehosted” while this second one slipped through. All 115 image references in raw/ now point at R2.
Added .github/workflows/ci.yml: wiki lint (non-clean report fails) + site format/test/check/build under Bun.
Updated README.md (Site + CI sections) and CLAUDE.md (site/ layer in Layout).
pages touched: none (wiki content untouched; raw/ byte-change limited to the sanctioned image-URL rewrite).

ingest | Anthropic — Loop engineering + Model & effort level (2 sources)

Sun, 12 Jul 2026 00:00:00 GMT

Ingested raw/2026-07-12-loop-engineering-getting-started.md (Delba de Oliveira & Michael Segner, claude.com blog, Jun 30 2026) and raw/2026-07-12-claude-model-effort-level.md (Lydia Hallie, claude.com blog, Jul 7 2026). The two posts cross-reference each other; ingested together.
Renamed both from dropped filenames; frontmatter curated (authors filled from bylines, tags replaced, descriptions rewritten).
Markdown fixes at intake (human-requested format repair): loop post — 8 escaped-backtick spans (\ + backtick artifacts) unescaped to real inline code; effort post — “andresults” typo split, missing ## restored on the “Fable vs. Opus vs. Sonnet” heading.
13 images rehosted to R2 (3 + 10), 0 failed; all read. Diagram-only evidence captured: turn-based loop exits “or the effort budget runs out”; /goal evaluator-model cycle; proactive-loop cloud composition (schedule → goal+check → PR → second-agent review → human merges); ~400 vs ~2,800 token low/high-effort comparison; raise-effort-vs-switch-model decision tree; converging/diverging quality-vs-tokens curves.
Created 2 source pages: 2026-07-12-loop-engineering-getting-started, 2026-07-12-claude-model-effort-level.
Created 2 concept pages: loop-engineering (four-type taxonomy, hand-off ladder, mapping onto existing loop pages), model-and-effort-selection (two dials, failure-triage heuristic, token economics).
Updated 8 existing pages: claude-code (loop primitives section + two-dials bullet; sources 2→4), anthropic (first-party operating guidance + model lineup; sources 3→5), agent-loop (loop-engineering added to named variants), verifier-loop (verification skills + /goal as productized verifiers), ralph-wiggum-loop (Anthropic’s fresh-context-reviewer corroboration), reasoning-models (effort as the user-facing dial over trained budget allocation), claude-skills (verification-skill archetype + scripts-for-deterministic-work), context-engineering (steering-not-teaching mechanism paragraph).
Back-scan: no existing open questions resolved by these posts (the mid-session model-switch cost example on 2026-04-27-claude-code-architecture-governance-engineering remains open — the effort post covers switching guidance but no numbers).
New open questions flagged: /goal’s evaluator model unspecified (graded channel → reward-hacking surface); “effort budget runs out” in the loop diagram vs “effort shapes but doesn’t cap” in the effort post — same mechanism or not; effort-level enumeration (low/medium/high/max) and per-model defaults not in the body.
index.md: 4 new entries; refreshed 8 summaries. wiki_lint.py clean on first run.
No contradictions surfaced between the two posts and the existing wiki; the diagram-vs-prose “effort budget” tension is noted as an open question, not a contradiction.
pages touched: 2026-07-12-loop-engineering-getting-started, 2026-07-12-claude-model-effort-level, loop-engineering, model-and-effort-selection, claude-code, anthropic, agent-loop, verifier-loop, ralph-wiggum-loop, reasoning-models, claude-skills, context-engineering, index.md.

ingest | OpenAI — Building the Codex Windows sandbox

Sun, 12 Jul 2026 00:00:00 GMT

Ingested raw/2026-07-12-codex-windows-sandbox-engineering.md (David Wiesen, OpenAI engineering blog, May 2026; Chinese translation of the English original). Renamed from the dropped filename; frontmatter curated (author/published filled, tags replaced, description kept).
Markdown fixes at intake (allowed mutations only + human-requested format repair): 3 broken nested-list indentations, 1 broken inline-code span ([Everyone, Logon, Synthetic]), removed trailing “Keep reading” navigation fragments left by the clipper.
7 diagrams rehosted to R2 via uv run --with boto3 --with httpx --with python-dotenv; all 7 read (rendered SVG→PNG locally via ImageMagick). Diagram-only evidence captured: named-pipe JSON IPC protocol and sandbox control plane paths (~/.codex/.sandbox, .sandbox-secrets, cap_sid).
Verified key claims against the English original (fetched from openai.com) — translation is faithful.
Created source page: 2026-07-12-codex-windows-sandbox-engineering.
Created concept page: agent-sandboxing — sandbox as OS-enforced execution boundary; per-OS primitives table; design axes from the Windows case.
Updated 4 pages: codex (new The sandbox (shipped product surface) section; sources 2→3), openai (third OpenAI-authored source listed; sources 6→7), harness (execution-boundary row + relation entry now link agent-sandboxing), prompt-injection (sandbox as OS-enforced sink-cutting; env-var suppression as cautionary case).
Back-scan: marked the internal-vs-external Codex open question on codex partially resolved (this is the first shipped-surface source).
index.md: 2 new entries; refreshed codex, openai, prompt-injection summaries.
No contradictions surfaced.
pages touched: 2026-07-12-codex-windows-sandbox-engineering, agent-sandboxing, codex, openai, harness, prompt-injection, index.md.

refactor | Lint-fix pass + schema upgrades (per lint entry above)

Sun, 12 Jul 2026 00:00:00 GMT

Human approved all findings from the [2026-07-12] lint; this entry records the fixes.
Updated harness-why-it-matters-now: 6→8 sources framing (Weng 2023/2026 bracket the window), Codex-verification wording now reads as resolved, added Postscript (2026-07) section — the convergence held and escalated to RSI.
Synced 4 concept pages to the Jul 2026 Weng source: llm-agent (new Weng’s own 2026 revision — agent anatomy → harness anatomy section), agent-evaluation (new Evaluation as the RSI bottleneck section: weak evaluators, evaluator-outside-the-loop, RE-Bench 2h/8h), eval-grader-reward (new A third loop: grading self-improvement section), llm-training-pipeline (stage 7 now links the RSI hierarchy).
Marked 3 resolved open questions in place (strikethrough + dated resolution note): Codex primary-citation on 2026-04-27-agent-principles-architecture-engineering; Yao↔meta-harness on 2026-04-27-the-second-half-of-ai (partial); agent-safety-thread note on 2026-06-04-llm-powered-autonomous-agents.
Created 3 pages: shunyu-yao (entity, sources: 2), agentic-context-engineering (ACE), meta-context-engineering (MCE). Back-linked from react, agent-evaluation, context-engineering, recursive-self-improvement, meta-harness, and both Weng source pages.
Added missing entity [[links]] on source pages: peter-steinberger, codebase-as-system-of-record, cursor on the agent-principles source; deepseek, anthropic, openai on the llm-training source. Added the Weng-2026 companion pointer on 2026-06-04-llm-powered-autonomous-agents.
index.md: 3 new entries; refreshed 6 drifted summaries (context-engineering, agent-loop, reward-hacking, agent-evaluation, llm-agent, harness-why-it-matters-now).
Schema (CLAUDE.md) upgrades, motivated by community critiques of the LLM Wiki pattern (lint validates wiki-to-wiki consistency, not wiki-to-source fidelity; resolved open questions never get revisited): Ingest gains step 7 Back-scan open questions and an entity-linking rule in step 6; index step gains a re-read-the-line rule; Lint gains Layer 3 — Fidelity spot-check (wiki → raw); Co-evolution documents the ~120-page / ~10K-token synthesis-horizon trigger for adding a qmd-style search layer. scripts/README.md step references updated.
wiki_lint.py clean on first run after all edits.
pages touched: harness-why-it-matters-now, llm-agent, agent-evaluation, eval-grader-reward, llm-training-pipeline, 2026-04-27-agent-principles-architecture-engineering, 2026-04-27-the-second-half-of-ai, 2026-06-04-llm-powered-autonomous-agents, 2026-07-07-harness-engineering-self-improvement, shunyu-yao, agentic-context-engineering, meta-context-engineering, react, context-engineering, recursive-self-improvement, meta-harness, 2026-04-27-llm-training-principles-paths-practices, index.md, CLAUDE.md, scripts/README.md.

lint | Full health-check (Layer 1 + Layer 2)

Sun, 12 Jul 2026 00:00:00 GMT

Layer 1 (wiki_lint.py): clean — 0 mechanical issues across 70 wiki pages.
Layer 2 (editorial): no unflagged factual contradictions found. Main findings, proposed to the human (not auto-fixed):
Stale after the Jul 2026 Weng ingest: harness-why-it-matters-now (still says “six ingested sources”; convergence table missing both Weng sources), llm-agent, agent-evaluation, eval-grader-reward, llm-training-pipeline (none absorbed RSI / self-improving-harness / RE-Bench material already present on harness and reward-hacking).
Resolved-but-unmarked open questions: Codex 1500-PR primary-citation follow-up on 2026-04-27-agent-principles-architecture-engineering (resolved by 2026-04-27-harness-engineering-codex-agent-first); Yao↔meta-harness connection on 2026-04-27-the-second-half-of-ai (partially resolved by the Jul 2026 ingest); “no agent-safety thread” note on 2026-06-04-llm-powered-autonomous-agents (superseded by recursive-self-improvement + reward-hacking RSI sections).
Missing-page candidates (2+ mentions, no page): Shunyu Yao (entity; named on 11+ pages), ACE / MCE (concepts), Aardvark (entity), Kangwook Lee (entity — disambiguation from Meta-Harness “Lee et al.”).
Missing cross-references: source pages often name entities in prose without [[entity]] links (deepseek, anthropic, cursor, peter-steinberger); several concept pages missing links into the Jul 2026 source.
Index summary drift: context-engineering, agent-loop, reward-hacking summaries predate their Jul 2026 sections. (sources: N) entity counts verified — no errors.
pages touched: none (findings only; fixes await human decision).

ingest | Lilian Weng — Harness Engineering for Self-Improvement

Tue, 07 Jul 2026 00:00:00 GMT

Ingested raw/2026-07-07-harness-engineering-self-improvement.md (Lil’Log, Jul 2026). Comprehensive survey on harness engineering as the near-term path to recursive self-improvement.
Created source page: 2026-07-07-harness-engineering-self-improvement.
Created 3 new concept pages: recursive-self-improvement, evolutionary-search-llm, self-improving-harness.
Updated 6 existing pages: harness (RSI substrate + coding-agent harness convergence), meta-harness (algorithm pseudocode + RSI placement), context-engineering (ACE + MCE sections), reward-hacking (self-improvement loop concerns), lilian-weng (second source), agent-loop (loop as optimization target).
Updated index.md with new pages + updated entity summary.
Image rehosting: 17 images rehosted to R2 via uv run --project scripts; 0 failed.
wiki_lint.py passed clean.
No contradictions surfaced; the new source extends and formalizes concepts already present in the wiki (harness, meta-harness, context-engineering) rather than contradicting them.

refactor | Drop (sources: N) from Concepts in index.md (align with schema)

Thu, 04 Jun 2026 00:00:00 GMT

Resolves the schema-vs-file drift flagged in the ingest entry above. CLAUDE.md specifies the (sources: N) suffix is entity-only; index.md had drifted to carry it on every concept line. Stripped it from all 44 Concepts lines; the 14 Entities lines keep it.
Decision made in the PR #7 review thread: align the file to the schema (drop from concepts) rather than loosen CLAUDE.md. CLAUDE.md unchanged — it already says entity-only.
Pages touched: index.md.

refactor | R2 rehost succeeded — supersedes the "rehosting FAILED" note in the ingest entry above

Thu, 04 Jun 2026 00:00:00 GMT

Correction to the ingest entry above. The R2 403 Forbidden was a token-permission/bucket issue on the configured .env. After the human fixed it, uv run rehost_images.py ../raw/2026-06-04-llm-powered-autonomous-agents.md --env ../.env rehosted all 13 images successfully (13 rehosted, 0 skipped, 0 failed).
The raw file’s image embeds now resolve to obsidian-r2.lkwplus.com/digital-garden/<digest>.png; 0 ![](...) embeds remain on lilianweng.github.io. The residual lilianweng.github.io strings in the file are prose cross-links + the citation block — not images, not rehosted by design.
This supersedes the prior entry’s “R2 rehosting FAILED” paragraph and its closing “images NOT rehosted — R2 403” note. Per the never-rewrite-history rule the prior entry is left intact. (Surfaced by the PR #7 review.)
Also in this PR: the human reformatted the GPT-Engineer code-writing system-prompt block in the raw body into a single fenced text block (a markdown-rendering fix for a broken nested lang fence). This means the ingest entry’s “body byte-identical” claim held at ingest time but no longer describes the current file — noted here so the discrepancy isn’t mistaken for an error.
Pages touched: raw/2026-06-04-llm-powered-autonomous-agents.md (13 images rehosted; system-prompt code-fence fix).

ingest | Lilian Weng's "LLM Powered Autonomous Agents"

Thu, 04 Jun 2026 00:00:00 GMT

Source: Lilian Weng, LLM Powered Autonomous Agents (https://lilianweng.github.io/posts/2023-06-23-agent/, published 2023-06-23). The canonical 2023 survey defining the agent anatomy LLM brain + Planning + Memory + Tool use. Treated as the wiki’s conceptual ancestor — most agent vocabulary in the 2026 sources traces back here. Oldest source ingested so far (2023 vs. the 2025–2026 cluster).
Pre-ingest prep: dropped at repo root LLM Powered Autonomous Agents.md, untracked. Plain mv (not git mv) into raw/2026-06-04-llm-powered-autonomous-agents.md (date = ingest date, today). Curated frontmatter: replaced tags: ["clippings"] with 6 topical tags (llm-agent, planning, memory, tool-use, react, self-reflection); replaced the clipper’s ~1500-char description: (first-paragraph dump, with stray tabs + curly quotes) with a 150-char English one-sentence summary of what the source is about. Body left byte-identical (verified by a frontmatter-only rewrite that asserted the post-fence bytes were unchanged).
R2 rehosting FAILED — flagged to human. scripts/rehost_images.py --keep-local .tmp-imgs/ downloaded all 13 images from lilianweng.github.io fine, but every R2 upload hit 403 Forbidden on HeadObject — a credential/permission/bucket problem on the configured R2 token, not a network issue. Consequence: the raw/ file’s image URLs still point at lilianweng.github.io (not rewritten to R2). Local copies were written before the failing S3 call, so image-reading was unaffected. Needs: fix .env R2 token perms (Object Read/Write on the bucket) + R2_BUCKET name, then re-run the (idempotent) rehoster. Also: the project’s scripts run under uv, which wasn’t installed; PEP 668 blocked system pip, so a scripts/.venv was created with the three deps (httpx, boto3, python-dotenv) to run the rehoster.
Image-reading: all 13 figures viewed and identified by content digest. Two are load-bearing for new pages — agent-overview.png (the four-spoke anatomy: Agent → Tools/Action/Memory/Planning, with Planning = Reflection/Self-critics/Chain-of-thoughts/Subgoal-decomposition) and memory.png (the human-memory taxonomy tree). Others confirmed details: reflexion.png (ReAct band + Reflect band w/ heuristic h), algorithm-distillation.png (cross-episode histories → causal transformer), generative-agents.png (Perceive→Memory Stream→Retrieve→Plan/Reflect→Act), hugging-gpt.png (4-stage controller loop), mips.png (ScaNN leads the recall@10/speed Pareto front), api-bank-process.png (search→call→refine pseudocode). sea-otter.png decorative (skipped for content).
Editorial decisions, surfaced to the human first via a structured question (CLAUDE.md step 3): rich new-page scope chosen (6 concept pages) over lean/minimal; POC systems mentioned only (no entity pages for AutoGPT / BabyAGI / GPT-Engineer / Generative Agents / HuggingGPT / ChemCrow — discussed on the source + tool-use / llm-agent instead). Framing emphasis agreed: present the 2023 → 2026 lineage, not an isolated summary.
Created 1 source page; 1 entity (lilian-weng); 6 concepts (llm-agent the anatomy hub, chain-of-thought, task-decomposition, self-reflection, tool-use, maximum-inner-product-search).
Updated 8 existing pages with ancestor cross-links / new sections: agent-memory (new Lineage — the 2023 human-memory taxonomy table: the 2026 four-types frame = Weng’s human taxonomy minus sensory, re-applied to file-backed storage; vector-store default is the assumption 2026 pushed back on); react (Weng’s survey noted as earliest catalog of ReAct, filed under self-reflection; “Not chain-of-thought” now links chain-of-thought); agent-loop (Thought/Action/Observation provenance; llm-agent backlink); reasoning-models (CoT-as-prompting-trick now links chain-of-thought; cross-link added); agent-evaluation (new Early precedent — LLM-as-judge fails in expert domains (2023) section: ChemCrow + API-Bank’s three levels); agent-computer-interface (named as engineered descendant of tool-use / MRKL’s “knowing when & how”); chroma (MIPS substrate cross-link; prune_chunks framed as answering what to retrieve vs. 2023’s how fast); openai (sources 5 → 6; ChatGPT Plugins / function calling as the productized tool-use form).
Cross-linking density check: all 7 new pages have inbound links from ≥1 non-index wiki page (most from 4–6); no orphan risk. llm-agent is the hub, inbound from the source + all 5 sibling concepts + agent-loop + agent-memory.
wiki_lint.py: run after edits — see final report; fixed any findings, re-ran to clean.
Editorial note (not auto-fixed): the index carries (sources: N) suffixes on concept lines, which CLAUDE.md says are entity-only. Pre-existing drift across all ~38 concepts. Matched the file convention for the 6 new concepts (each sources: 1) to keep the index internally uniform; flagged the schema-vs-file mismatch for a human decision rather than silently mass-editing.
Pages touched: 2026-06-04-llm-powered-autonomous-agents, lilian-weng, llm-agent, chain-of-thought, task-decomposition, self-reflection, tool-use, maximum-inner-product-search, agent-memory, react, agent-loop, reasoning-models, agent-evaluation, agent-computer-interface, chroma, openai, index.md. Plus raw/2026-06-04-llm-powered-autonomous-agents.md (rename, frontmatter; images NOT rehosted — R2 403, see above).
New open follow-ups flagged: which of the article’s three “challenges” (finite context, long-term planning, NL-interface reliability) were solved vs. deferred by 2026? (2026-06-04-llm-powered-autonomous-agents); is the self-reflection → ralph-wiggum-loop/verifier-loop lineage direct or convergent? (self-reflection); Boiko et al.’s bioweapon red-team is an early agent-misuse eval with no dedicated wiki thread yet — candidate page if more sources land; lilian-weng OpenAI/Thinking-Machines affiliation is background, not established by this source — wants a primary ingest before stated as fact.

query | "What is Harness and why is it suddenly hot?"

Mon, 27 Apr 2026 00:00:00 GMT

Conversational explanation of harness in Chinese, grounded in the existing concept page. Human asked the synthesis-flavored “why now” follow-up, agreed to file the answer as a note.
Created harness-why-it-matters-now — wiki’s first note. Structure: convergence window table (six sources within ~10 weeks), five enabling conditions that matured at once (model floor, long-running agents, eval bottleneck, first-party data, Meta-Harness number), three displaced mental models, four caveats, signals to track.
One backlink added on harness (one-line “time-slice view” pointer at the bottom) so the note isn’t an orphan; otherwise no concept / entity / source pages modified — the note synthesizes existing material rather than introducing new claims. All citations link to pages already present.
wiki_lint.py: 1 orphan on first run (the new note); fixed by the harness backlink; second run clean.
Pages touched: harness-why-it-matters-now, harness, index.md.

ingest | Shunyu Yao's "The Second Half"

Mon, 27 Apr 2026 00:00:00 GMT

Source: Shunyu Yao (openai; ReAct 2022, CALM 2019), The Second Half (https://ysymyth.github.io/The-Second-Half/, published 2025-04-10). Based on talks at Stanford 224N and Columbia. The wiki’s first thesis-level source — not a technical post but a field-level argument: a working “recipe” (language pretraining + scale + reasoning-as-action) now generalizes broadly enough that benchmark-hillclimbing has been industrialized, so the field’s bottleneck shifts from training methods to evaluation design — what Yao names the utility problem. Second OpenAI-authored source after the Lopopolo / Codex post.
Pre-ingest prep: dropped file at repo root The Second Half.md, untracked. Plain mv (not git mv) into raw/2026-04-27-the-second-half-of-ai.md. Ran scripts/rehost_images.py (4 images ysymyth.github.io → R2). Curated frontmatter: replaced tags: ["clippings"] with 6 topical tags (agent-evaluation, reasoning, reinforcement-learning, react, benchmarks, utility-problem); replaced clipper-style description: "tldr: We're at AI's halftime." with a one-sentence English summary of what the source is about.
Image-reading: all 4 figures viewed. Three are load-bearing: image 1 (the citation-asymmetry scale — Transformer 168K vs WMT’14 1.3K, AlexNet 172K vs ImageNet 49K, GPT-3 49K vs SuperGLUE 2.5K — direct evidence for the “first-half methods >> benchmarks” claim); image 3 (Jason Wei’s saturation curves — MATH 5%→95% in 3 yrs, SWE-bench-verified 5%→80% in 1 yr, AIME 10%→95% in ~1 yr — direct evidence for “any benchmark gets solved in months”); image 4 (tau-bench setup with the agent mid-trajectory negotiating with a simulated user — direct evidence for the autonomous-eval critique). Image 2 (the canonical ReAct figure) is the right anchor for the new react page.
Editorial decisions before writing, surfaced to the human first per CLAUDE.md step 2: no shunyu-yao entity page (attributed inline as plain text); yes react concept page; no utility-problem concept page (folded into agent-evaluation + the source page); 8 existing pages updated; tags react and utility-problem kept on the source frontmatter even though only react has its own page (frontmatter tags don’t have to map 1:1 to wiki pages).
Created 1 source page; 1 concept (react).
Updated 8 existing pages with primary-source citations / new sections: agent-evaluation (sources 1 → 2; new section The utility problem — eval setups vs. real-world setups with the autonomous + i.i.d. assumption critique, the Chatbot Arena / tau-bench / sequential-familiarity counter-examples, and the field-level “fix the eval frame first” generalization); reasoning-models (1 → 2; new section Reasoning as a strange RL action with the algorithm + environment + priors decomposition); pretraining (1 → 2; new section Pretraining as RL priors — the most important RL ingredient came from outside RL); post-training (1 → 2; new section Post-training as RL with reasoning in the action space reframing the o-series / R1 wave); agent-loop (2 → 3; “the ~20-line ReAct loop” line now links to react; Named loop variants bullet added); long-running-agents (2 → 3; new section on Yao’s i.i.d.-vs-sequential point — Google SWE vs SWE-agent gap and the missing-benchmarks problem); agent-memory (1 → 2; parallel section on why long-term memory benchmarks barely exist under i.i.d.); openai (4 → 5; opening reframed as “first thesis-level OpenAI-authored source”, new public-posts entry, environment-first → priors-first → recipe-era arc).
Cross-linking density check: react connects to ≥3 existing pages (agent-loop, reasoning-models, pretraining, post-training, ralph-wiggum-loop, harness, multi-agent-orchestration, claude-subagents) and inbound from 5 wiki pages plus the source — no orphan risk.
wiki_lint.py clean on first run after edits — 0 mechanical issues.
Pages touched: 2026-04-27-the-second-half-of-ai, react, agent-evaluation, reasoning-models, pretraining, post-training, agent-loop, long-running-agents, agent-memory, openai, index.md. Plus raw/2026-04-27-the-second-half-of-ai.md (rename, frontmatter, 4 images rehosted).
New open follow-ups flagged on pages: utility problem is named but not operationalized — wiki should track whether later sources propose a metric beyond “judged by economics and GDP” (2026-04-27-the-second-half-of-ai); the autonomous + i.i.d. assumptions are illustrative, not exhaustive — what other eval assumptions are similarly load-bearing? (2026-04-27-the-second-half-of-ai, agent-evaluation); the reasoning-as-action argument is intuitive rather than mechanistic — Yao flags this himself, watch for a follow-up post (react); cross-link with meta-harness is structurally similar to Yao’s “augment the recipe with novel components” prescription but he doesn’t name it — worth a note when a future ingest connects them.

refactor | rehost_images.py --keep-local + workflow update

Mon, 27 Apr 2026 00:00:00 GMT

Triggered by friction at the start of the Yao ingest below: chained curl commands without --max-time got stuck in the sandbox during the image-reading step, then I burned more time killing them than the downloads would have taken. Operational mistake, not network — the same downloads worked in 8s with bounded timeouts.
Real fix: the script already has the bytes in memory (it downloads each image to upload). Saving a local copy at the same time removes the second curl pass entirely.
Added --keep-local <DIR> to scripts/rehost_images.py. Writes each downloaded image to <DIR>/<digest>.<ext> (same name as the R2 key, sans prefix) on both OK (newly uploaded) and SKIP (already in bucket) paths. Smoke-tested end to end against a real external URL.
CLAUDE.md Workflow — Ingest step 1 rewritten: now invokes scripts/rehost_images.py <file> --keep-local .tmp-imgs/, with an explicit “Do not chain bare curl calls for this” line so the next agent doesn’t re-discover the failure mode.
scripts/README.md updated with the new flag, including a property line noting --keep-local reuses in-memory bytes.
For the Yao ingest itself the markdown was already rewritten before the flag landed, so this ingest fell back to disciplined curl --max-time 15. From the next ingest onward the flag is the path.
Pages touched: scripts/rehost_images.py, CLAUDE.md, scripts/README.md.

ingest | Kangwook Lee's "Investigating how Codex context compaction works"

Mon, 27 Apr 2026 00:00:00 GMT

Source: Kangwook Lee, Investigating how Codex context compaction works (https://x.com/Kangwook_Lee/article/2028955292025962534, published 2026-03-04). Independent investigation, third-party reverse-engineering of openai‘s closed compact() API path used by codex models. Image-heavy: 7 images carry the leaked-prompt screenshots, pipeline diagrams, and script source — all the load-bearing evidence is visual.
Pre-ingest prep: dropped file at repo root Investigating how Codex context compaction works.md, untracked. mv into raw/2026-04-27-codex-context-compaction-investigation.md. Ran scripts/rehost_images.py (7 images pbs.twimg.com → R2). Curated frontmatter: replaced clipper tags: ["clippings"] with 6 topical tags (codex, context-engineering, prompt-injection, prompt-extraction, openai, compaction); replaced truncated description: ending in ... with one-sentence English summary of what the source is about (the reverse-engineering, not its first paragraph).
Image-reading discipline followed (and formalized in the refactor entry above): rehosted, curl-ed all 7 images into .tmp-imgs/, viewed each via the read tool, cleaned up. Three of the seven were the entire payoff — the leaked-prompt-output screenshot, the pipeline diagram, and the script source — and would have been lost reading prose alone.
Per-question editorial decisions before writing: (1) merge compaction details into existing context-engineering rather than spawn a separate context-compaction page; (2) defer a prompt-extraction page; (3) emphasize pipeline + verbatim prompts + open questions, gloss the injection method; (4) no entity page for Kangwook Lee (single-source author); (5) # Juice: 192 system-prompt trivia kept out of the notable-quotes section.
Created 1 source page (2026-04-27-codex-context-compaction-investigation). No new entity / concept pages — all content absorbed into existing pages per (1)–(4) above.
Updated 3 existing pages: context-engineering (sources 3 → 4; new section Codex’s two compaction paths (and the actual prompts) with the verbatim compaction prompt and handoff prompt, the encryption-scheme pipeline, and the cross-link back to claude-md‘s ## Compact Instructions and claude-code‘s HANDOFF.md pattern); codex (sources 1 → 2; new section Compaction internals (third-party reverse-engineering) with the two-paths-same-prompts framing and Fernet AES-128-CBC + HMAC-SHA256 detail, plus an open-question bullet); openai (sources 3 → 4; new Third-party investigations of OpenAI APIs sub-section to keep this source distinguishable from the OpenAI-authored ones above it).
wiki_lint.py clean on first run after edits — no broken links, index in sync.
Pages touched: 2026-04-27-codex-context-compaction-investigation, context-engineering, codex, openai, index.md. Plus raw/2026-04-27-codex-context-compaction-investigation.md (rename, frontmatter, 7 images rehosted).
New open follow-ups flagged: why two compaction paths if prompts are near-identical? what else (tool results? file refs?) is in the encrypted blob? extraction stability across model versions / account types isn’t audited; this source is one snapshot, not a spec (2026-04-27-codex-context-compaction-investigation, codex).

refactor | Image-reading rule + .gitignore .tmp-imgs/

Mon, 27 Apr 2026 00:00:00 GMT

Surfaced during the Codex compaction ingest below: the article’s payload (leaked compaction prompt, handoff prompt, Fernet pipeline, full-script source) lives entirely in screenshots, not prose. Reading text alone would have produced a faithful-looking summary that was quietly missing the point.
CLAUDE.md Workflow — Ingest step 1 rewritten: dropped the soft “selectively” framing for image viewing in favor of default-read after rehosting; decorative images (banners, avatars, logos) are the only exception. Added the practical mechanic since the image-reading tool only accepts local paths: curl rehosted URLs into .tmp-imgs/, view, delete the dir.
.gitignore adds .tmp-imgs/ so the scratch dir can’t be accidentally committed.
Pages touched: CLAUDE.md, .gitignore.

ingest | OpenAI Codex's "Harness engineering" post

Mon, 27 Apr 2026 00:00:00 GMT

Source: Ryan Lopopolo / openai / codex team, Harness engineering: leveraging Codex in an agent-first world (https://openai.com/index/harness-engineering/, published 2026-02-11). The wiki’s first directly-OpenAI-authored primary source. Ingested zh-CN version (the variant dropped into the repo root by the human).
Pre-ingest prep: dropped file was at repo root 工程技术：在智能体优先的世界中利用 Codex.md and not under git. mv (not git mv since untracked) into raw/2026-04-27-harness-engineering-codex-agent-first.md. Ran scripts/rehost_images.py (1 image, Contentful CDN → R2). Curated frontmatter (replaced tags: [clippings] with 6 topical tags; replaced clipper-generated description: "作者：Ryan Lopopolo，技术人员" with one-sentence Chinese summary).
This source resolves a previously-flagged follow-up: the “OpenAI Codex 1500 PRs / 3 engineers” claim was flagged on harness and 2026-04-27-agent-principles-architecture-engineering as wanting primary verification. This post is that primary source — the previously-second-hand numbers are now first-hand. Updated harness to reflect the resolution.
Created 1 source page; 2 entities (ryan-lopopolo, codex); 5 concepts (agent-legibility, codebase-as-system-of-record, architectural-invariants, ralph-wiggum-loop, entropy-and-garbage-collection).
Updated 8 existing pages with second/third-source citations / new sections: openai (sources 2 → 3, page-level reframe — the wiki’s view of OpenAI shifted from “cited at one remove via Tw93” to “directly-authored primary source on agentic coding”); claude-md (sources 2 → 3, added “Primary-source corroboration: OpenAI Codex’s AGENTS.md” section with the table-of-contents framing and four named failure modes of “one big AGENTS.md”); harness (sources 2 → 3, rewrote the Codex case section to reference the primary source and the 5 new concept pages); context-engineering (sources 2 → 3, added “Context is a scarce resource — primary citation” section with the four-reason failure-mode list); verifier-loop (sources 2 → 3, added Chrome DevTools Protocol bridge + linter-error-as-fix-instruction); long-running-agents (sources 1 → 2, 6+ hr Codex runs + worktree-per-change + ephemeral observability); agent-loop (sources 1 → 2, added Named loop variants section pointing to ralph-wiggum-loop); multi-agent-orchestration (sources 1 → 2, added “Agent-to-agent reviews as the default” section).
Cross-linking density check: each new concept page connects to ≥3 existing pages and ≥2 existing pages connect back to each — no orphans. The 5 new concepts form a cluster with harness / verifier-loop / claude-md as the connective tissue to the prior wiki.
wiki_lint.py first run: 1 broken link ([[agents-md|claude-md]] had slug/display reversed; should be [[claude-md|AGENTS.md]]). Fixed; second run clean.
Pages touched: 2026-04-27-harness-engineering-codex-agent-first, ryan-lopopolo, codex, agent-legibility, codebase-as-system-of-record, architectural-invariants, ralph-wiggum-loop, entropy-and-garbage-collection, openai, claude-md, harness, context-engineering, verifier-loop, long-running-agents, agent-loop, multi-agent-orchestration, index.md. Plus raw/2026-04-27-harness-engineering-codex-agent-first.md (rename, frontmatter, 1 image rehosted).
New open follow-ups flagged: “~10× throughput” multiplier isn’t decomposed (model speed vs. tooling investment vs. discipline-of-no-manual-code vs. baseline selection effects) (codex); architectural coherence over time in fully-agent-generated codebases is named open by the post itself (2026-04-27-harness-engineering-codex-agent-first); end-to-end autonomy claim is hedged “depends on this codebase’s specific structure and tooling” — portability to claude-code / other repos is open; the AGENTS.md ~100-line figure isn’t given as a token-count, would be useful to compare against anthropic‘s CLAUDE.md ~2.5K-token sizing; “Aardvark” is named in the post as another agent participating in the same codebase — worth ingesting OpenAI’s Aardvark intro post when it lands in raw/; cleanup-loop fleet sizing (entropy-and-garbage-collection) and cleanup-vs-feature PR ratio aren’t quantified — flagged for any future Codex publication.

refactor | scripts/wiki_lint.py + workflow integration

Mon, 27 Apr 2026 00:00:00 GMT

Triggered by the broken-link / index-drift checks I had to do by hand at the end of the LLM-training ingest. Catching [[reward-design]] (typo for [[eval-grader-reward]]) by ad-hoc Python one-liner is exactly the kind of thing that should be a script.
Added scripts/wiki_lint.py — pure stdlib (no uv / no deps), runs in <1s on the current wiki, always exits 0. Five checks: broken [[links]], missing-from-index, phantom-in-index, orphans, frontmatter completeness.
Orphan rule per editorial direction: entity / concept / note pages count as orphans only with zero inbound from other wiki pages. Source-page inbound counts (a page cited by a source is connected). index.md inbound is excluded — every page is in the index by design, so it’s not an informative signal.
Wired into both workflows in CLAUDE.md: Ingest step 6 now runs the script and requires clean before logging; Lint workflow split into Layer 1 (mechanical, scripted) and Layer 2 (editorial, LLM judgment — contradictions, stale claims, missing cross-refs).
Documentation updated: scripts/README.md gets a wiki_lint.py section with usage, check matrix, and trigger points.
First clean run: 0 mechanical issues — the LLM-training ingest is structurally tight.
Pages touched: scripts/wiki_lint.py (new), scripts/README.md, CLAUDE.md.

ingest | Tw93's "你不知道的大模型训练" essay

Mon, 27 Apr 2026 00:00:00 GMT

Source: Tw93, “你不知道的大模型训练：原理、路径与新实践” (https://tw93.fun/2026-04-03/llm.html, published 2026-04-04). Third in the series; jumps a layer up from runtime Agent engineering to the training stack itself. Frame: by 2026 the perceived capability gap between models is decided by the back half of the nine-stage pipeline (post-training, eval / reward, harness, distillation), not pretraining scale.
Pre-ingest prep: raw file already at canonical name 2026-04-27-llm-training-principles-paths-practices.md and committed in c976912; images already self-hosted on obsidian-r2.lkwplus.com; frontmatter already curated (6 tags, one-sentence Chinese description). No mutations needed.
Wider footprint than prior ingests because this article opens an entire new domain (LLM training) that the wiki had no scaffolding for. Decided up front to seed the spine rather than minimal-touch ingest, on the bet that future training-stack sources will reference back to these pages.
Created 1 source page; 5 entities (deepseek, openai, moonshot-ai, cursor, chroma); 13 concepts (llm-training-pipeline, pretraining, chinchilla-scaling, data-engineering, mixture-of-experts, post-training, grpo, eval-grader-reward, reward-hacking, constitutional-ai, deliberative-alignment, reasoning-models, distillation, meta-harness).
Updated 4 existing pages with third-source citations / scope clarifications: anthropic (sources 2 → 3; added Constitutional AI, reasoning-model observability, Sycophancy to Subterfuge, Natural Emergent Misalignment from Reward Hacking as the alignment-research surface); tw93 (sources 2 → 3; trajectory note “Claude Code user → Agent engineer reader → training-stack synthesizer”); harness (added “Harness at a different scale: meta-harness” section distinguishing runtime engineering from outer-loop search; flags Meta-Harness 6× spread as strongest empirical support yet for “Harness > model”); agent-evaluation (scope note pointing to eval-grader-reward for the training-time cousin).
Resolved naming overlap: harness (runtime, Tw93) vs. meta-harness (outer-loop search, Lee et al. 2026) — same word, different scale, cross-linked both ways. Same disambiguation done for agent-evaluation (runtime) vs. eval-grader-reward (training-time).
Pages touched: 2026-04-27-llm-training-principles-paths-practices, deepseek, openai, moonshot-ai, cursor, chroma, llm-training-pipeline, pretraining, chinchilla-scaling, data-engineering, mixture-of-experts, post-training, grpo, eval-grader-reward, reward-hacking, constitutional-ai, deliberative-alignment, reasoning-models, distillation, meta-harness, anthropic, tw93, harness, agent-evaluation, index.md.
New open follow-ups flagged: the Meta-Harness 6× spread / +4.7-on-5-held-out-models numbers want decomposition against the primary paper (meta-harness); the held-out model identities aren’t named in the article. DeepSeek-V3’s “no rollbacks across 14.8T tokens” is unusual enough to merit cross-checking against contemporaneous Llama 3 / Qwen 3 reports (pretraining). Junyang Lin’s thinking/instruct mode tradeoff is presented as a problem statement — what did Qwen3 actually ship? (reasoning-models). Verified rewards are clean for math/code/logic; how the field handles open-ended tasks (writing, advice) without collapsing to RLHF preference noise is left open (eval-grader-reward). The relationship between Meta-Harness-style outer-loop optimization and ordinary runtime harness engineering may want a dedicated note when the next training source lands (meta-harness vs. harness).

ingest | Tw93's "你不知道的 Agent" companion essay

Mon, 27 Apr 2026 00:00:00 GMT

Source: Tw93, “你不知道的 Agent：原理、架构与工程实践” (https://tw93.fun/2026-03-21/agent.html, published 2026-03-22). Companion to the prior Claude Code essay; broadens to general Agent engineering; uses openclaw as the case-study implementation.
Pre-ingest prep: renamed raw file to 2026-04-27-agent-principles-architecture-engineering.md; ran patched scripts/rehost_images.py (24 images Alibaba/Alipay CDNs → R2; one image needed the regex fix above to be picked up); curated frontmatter (6 topical tags; one-sentence Chinese description).
Author-attribution correction surfaced before writing: openclaw is Peter Steinberger’s project (PSPDFKit founder; github.com/openclaw/openclaw), not Tw93’s. The article uses it as a worked example. Source-page description, openclaw entity, peter-steinberger entity, and tw93 entity all reflect this — tang in OpenClaw code samples is a placeholder userId, not the project owner.
Created 1 source page; 2 entities (openclaw, peter-steinberger); 8 concepts (harness, agent-computer-interface, agent-loop, agent-memory, agent-evaluation, multi-agent-orchestration, long-running-agents, prompt-injection).
Updated 8 existing pages with second-source citations / new sections / contradictions: tw93 (sources 1 → 2), six-layer-agent-architecture (added scope clarifier and contrast with OpenClaw’s 5-layer), context-engineering (added Context Rot, layered tiers by stability, filesystem-as-interface, 3 compression strategies), claude-skills (counter-example accuracy data, MCP-vs-Skills cost shape), prompt-caching (cache-aware design generalization), claude-md (cross-system contract-file pattern, OpenClaw SOUL.md parallel), verifier-loop (placement inside harness, transcript-vs-outcome), claude-subagents (depth limit, minimal sub-Agent prompt), model-context-protocol (open question on diverging tool-definition size figures).
Pages touched: 2026-04-27-agent-principles-architecture-engineering, openclaw, peter-steinberger, tw93, harness, agent-computer-interface, agent-loop, agent-memory, agent-evaluation, multi-agent-orchestration, long-running-agents, prompt-injection, six-layer-agent-architecture, context-engineering, claude-skills, prompt-caching, claude-md, verifier-loop, claude-subagents, model-context-protocol, index.md.
New open follow-ups flagged: Tool Search / Programmatic Tool Calling / Tool Use Examples accuracy figures (49→74%, 150K→2K, 72→90%) all unsourced — chase primary Anthropic publications (agent-computer-interface); 70/30 vector/keyword retrieval split presented without ablation (agent-memory, openclaw); OpenAI Codex 1500-PR/3-engineer claim wants primary citation (harness); MCP definition-size figures diverge between sources — needs a real /mcp reading (model-context-protocol, openclaw).

refactor | Rehoster regex handles nested brackets

Mon, 27 Apr 2026 00:00:00 GMT

scripts/rehost_images.py: IMAGE_RE widened to allow one level of nested […] inside markdown alt text, e.g. ![... messages[] ...](url). Old pattern \[[^\]]*\] silently skipped these and reported success; surfaced when the Tw93 Agent essay rehoster claimed 23/24 done while one Alipay-CDN URL remained.
Committed separately ahead of the ingest below.

ingest | Tw93's "你不知道的 Claude Code" essay

Mon, 27 Apr 2026 00:00:00 GMT

First real ingest. Source: Tw93, “你不知道的 Claude Code：架构、治理与工程实践” (https://tw93.fun/2026-03-12/claude.html, published 2026-03-13).
Pre-ingest prep: renamed raw file to canonical 2026-04-27-claude-code-architecture-governance-engineering.md; ran scripts/rehost_images.py (16 images Fliggy CDN → R2); curated frontmatter (replaced tags: [clippings] with 6 topical tags; replaced clipper-truncated description with one-sentence summary in source language).
Pre-ingest format pass: removed 25 clipper-artifact ``` escapes inside fenced code blocks. Body otherwise byte-identical.
Created 1 source page, 4 entities (tw93, anthropic, claude-code, kaku), 10 concepts (six-layer-agent-architecture, context-engineering, prompt-caching, model-context-protocol, claude-md, claude-skills, claude-hooks, claude-subagents, plan-mode, verifier-loop).
Pages touched: 2026-04-27-claude-code-architecture-governance-engineering, tw93, anthropic, claude-code, kaku, six-layer-agent-architecture, context-engineering, prompt-caching, model-context-protocol, claude-md, claude-skills, claude-hooks, claude-subagents, plan-mode, verifier-loop, index.md.
Open follow-ups flagged on pages: corroborate defer_loading mechanism against primary Anthropic docs (prompt-caching); validate the “5 servers ≈ 25K tokens” number from a real /mcp reading (model-context-protocol).

bootstrap | Initial scaffolding

Mon, 27 Apr 2026 00:00:00 GMT

Set up the LLM Wiki layout: raw/, wiki/{sources,entities,concepts,notes}/, index.md, log.md, CLAUDE.md.
Pattern adapted from Andrej Karpathy’s LLM Wiki.
No sources ingested yet — drop the first one into raw/ and ask the agent to ingest it.