Create llm_enhance repo: extract LLM enhancement from phpMan with Source/Transform/Sink abstraction

[chedong]

Context

Following 2026-07-14 architectural simplification (docs/01-PRODUCT.md §2.12 + docs/05-PLAN.md §"Migration Plan"), LLM enhancement moves out of phpMan into a standalone repo. Must serve multiple content sources, not just phpMan:

• phpMan: SQLite cache → MD files → enhanced MD
• myblog: MySQL (Movable Type) → MD files → enhanced MD
• future: filesystem, HTTP API, etc.

Goal

llm_enhance repo with source-agnostic abstraction. Same LLM transforms + task manager serves all projects.

Key design (full spec docs/05-PLAN.md §1.2-1.5)

Three ABCs:

• Source: yields Entry objects. Impls: MysqlExportSource (myblog), PhpmanCacheSource (phpMan), FilesystemSource, HttpApiSource.
• Transform: Entry → enhanced Entry. Versioned (e.g. emoji@v2). Impls: EmojiTransform, OkfTransform, TranslationTransform.
• Sink: persists results. Impls: FilesystemSink, SqliteSink (phpMan compat), HttpApiSink.

Plus:

• TaskManager: SQLite-backed queue, resume, rate limiting, cost tracking
• LLMClient: multi-provider (OpenAI-compat, Anthropic), retry, truncation detection
• Prompt loader: versioned prompts in src/llm_enhance/prompts/

Migration source map (Phase B)

From phpMan.php → llm_enhance:

From	To
enhanceManPage()	transform/emoji.py:EmojiTransform.apply()
callLLM()	llm/client.py:LLMClient.call()
cleanEmojiHtml()	transform/emoji.py:post_process()
cli/batch-enhance.php	cli.py:run_command()
LLM config (5 keys)	per-project YAML configs

Deleted (only existed for LLM path):

• formatMarkdownToHTML(), formatInlineMarkdown()
• renderTocSidebar()

Steps (Phase A+B+C+D, ~3-4 weeks)

1. W1: Create repo, pyproject.toml, src layout, ABCs + tests
2. W2: Port cli/batch-enhance.php → Python CLI (queue/resume/rate-limit)
3. W2-3: Implement MysqlExportSource for myblog MT 4.x/5.x schema
4. W3: Implement PhpmanCacheSource reading ~/.phpman/cache/db.sqlite
5. Test: llm_enhance run --config=myblog.yaml --limit=10 --dry-run and same for phpMan

Related

• Full design: docs/05-PLAN.md §1
• Related: PID paths hardcoded in /status endpoint (coupled to external doc-enhance project) #219 (PID paths in /status coupled to doc-enhance project)
• See companion issue for site_stats repo.