Ch-04: Operating System mental model + polish ch-01~03#1
Merged
Conversation
New concept pages: agent-os, agent-scheduling, agent-resource-control, agent-sandboxing, llm-os, llm-os-analogy, llm-security, permission-modes, permission-rules-hierarchy, claude-code-permission-system, autonomy-slider, a2a-protocol, agent-card, agent-interoperability, fork-explore-commit, generation-verification-loop, scaling-laws, software-3-0, system-1-vs-system-2, virtual-context-management, llm-training-pipeline, prefix-caching, llms-txt, settings-scope-hierarchy, task-lifecycle. New entity pages: aios, claude-code, manus, memgpt, andrej-karpathy, jeremy-howard, answer-ai, asplos, google, linux-foundation. New source pages: 12 source ingestions covering AIOS, AgenticOS Workshop, Karpathy talks, A2A protocol, MemGPT, Claude Code permissions, and more. Updated existing concept/entity pages with cross-references to new pages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Six articles exploring the OS analogy for agentic systems: 01 — from Maxwell's demon to OS kernel 02 — memory hierarchy (context as virtual memory) 03 — scheduling (token budget as CPU time) 04 — trust boundary (permissions as OS security rings) 05 — cooperation protocol (tool calls as IPC/syscalls) 06 — where the analogy breaks Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
English-native version of the six OS analogy articles, independently written (not translated from Chinese). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three changes across all 18 Chinese articles in ch-01 through ch-03: 1. Humanize: remove AI writing patterns (filler phrases, inflated significance, copula avoidance, forced triplets, synonym cycling) while preserving the project's accessible-and-witty tone per writing-style.md rules. 2. Reform 延伸阅读: transform from bibliography-style reference lists to curated 1-3 recommendations. Each entry annotated with why this reader should care. No duplicates across articles in same chapter. 3. Add 概念与实体: new section at end of each article linking to relevant wiki concept/entity pages with per-article annotations. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- write-mental-model: add 延伸阅读 curation criteria (1-3 curated recommendations with three-gate evaluation), add 概念与实体 section guidelines for Chinese articles, update review pipeline to use language-specific humanizer skills (/humanizer-zh vs /humanizer) - review-pipeline: align Agent B with bilingual humanizer routing - llm-wiki-ingest/lint: minor updates Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add ch-04-operating-system to both ZH and EN .pages nav files - Add build_docs.py script for pattern docs generation - Update deploy-docs.yml workflow - Update .gitignore - Update README badges Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Test plan
uv run mkdocs build --strict -f mkdocs.zh.ymlpassesuv run mkdocs build --strict -f mkdocs.en.ymlpassesllms.txtserved correctly from site root🤖 Generated with Claude Code