Remove unused blocks field and add_blocks parameter. The LLM never
used add_blocks in practice, making it dead code that taught a
misleading bidirectional pattern. Replace with remove_blocked_by
for dependency rewiring. Single-source-of-truth with blockedBy only.
s08/s09/s10/s11/s_full inject background-results and inbox as user
messages before LLM calls. The paired hardcoded assistant "Noted..."
responses were unnecessary — consecutive user messages work fine and
the fake acks added noise with no functional value.
Affected: agents/s08, s09, s10, s11, s_full + docs (zh/en/ja s08, s09)
Comprehensive rewrite establishing the harness engineering narrative
across the entire repository.
README (EN/ZH/JA): added "The Model IS the Agent" manifesto with
historical proof (DQN, OpenAI Five, AlphaStar, Tencent Jueyu),
"What an Agent Is NOT" critique, harness engineer role definition,
"Why Claude Code" as masterclass in harness design, and universe
vision. Consistent framing: model = driver, harness = vehicle.
docs (36 files, 3 languages): injected one-line "Harness layer"
callout after the motto in every session document (s01-s12).
agents (13 Python files): added harness framing comment before
each module docstring.
skills/agent-philosophy.md: full rewrite aligned with harness
narrative.
- 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
