Add critical-path figures with captions, ASCII topology sketches,
labeled teaching-code vs code.py snippets, and details collapses for
optional depth. Recompress official PNGs; keep essay spine visible.
Co-authored-by: Xinlu Lai <CrazyBoyM@users.noreply.github.com>
Pull Anthropic essay PNGs (primitives, dynamic-vs-static, six patterns,
quarantine triage) into images/, wire them into EN/ZH/JA with captions,
and add a short untrusted-input beat. Drop substitute SVGs for those four.
Co-authored-by: Xinlu Lai <CrazyBoyM@users.noreply.github.com>
Full rewrite of EN/ZH/JA as a progressive essay with harness-essay spine,
six-pattern toolbox, neighbor comparisons, and SVG-first figures
(dynamic-vs-static, primitives, six patterns). Keep null-isolation and
longest-prefix resume in the teaching runtime; bump translation-sync to v15.
Co-authored-by: Xinlu Lai <CrazyBoyM@users.noreply.github.com>
Introduce Classify-And-Act through Loop Until Done after primitives,
map each onto agent/parallel/pipeline, show review-changes as a
fanout+verify composition, and add a matching six-panel SVG.
Co-authored-by: Xinlu Lai <CrazyBoyM@users.noreply.github.com>
- initialize dark mode state after mount from document to avoid mismatched first render state.
- render a placeholder before mount to reduce theme icon hydration mismatch risk.
- s03: inject reminder into tool_result instead of mutating history (#37)
- s05: SkillLoader uses rglob("SKILL.md") + frontmatter name priority,
matching Agent Skills standard (#30, PR #34)
- CI: upgrade actions/checkout and actions/setup-node to v6 (#36)
- docs: update s05 skill directory structure in all 3 languages
- 11 sessions from basic agent loop to autonomous teams
- Python MVP implementations for each session
- Mental-model-first docs in en/zh/ja
- Interactive web platform with step-through visualizations
- Incremental architecture: each session adds one mechanism
