TODO: drop snapshot blob from md-tracking; use git for diff source

Per follow-up: SF generates many of these .md files itself (.sf/wiki/*,
.sf/milestones/**/*.md, docs/plans/**), so storing gzipped snapshots in
the DB would duplicate disk + git for no benefit.

Simpler design: store only the sha + meta in sf.db; compute diffs
on demand against `git show HEAD:<path>`. Naturally handles both
"working-tree edit not yet committed" and "another agent committed
while SF wasn't running".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

TODO.md

@@ -118,31 +118,45 @@ Explicit out of scope:
   is expected, no signal in tracking.
 - `node_modules`, `dist`, vendored copies — irrelevant.
 
-Storage in `sf.db`:
+Storage in `sf.db` — **shas only, no content snapshots**. SF generates
+many of these files itself; caching their contents in the DB would
+duplicate disk + git for no benefit:
 
 ```sql
 CREATE TABLE tracked_md_files (
   relpath        TEXT PRIMARY KEY,        -- repo-relative path
-  sha256         TEXT NOT NULL,
+  sha256         TEXT NOT NULL,           -- hash of last-seen content
   size_bytes     INTEGER NOT NULL,
   last_seen_at   TEXT NOT NULL,
-  snapshot       BLOB,                    -- gzipped content, optional
   category       TEXT                     -- 'meta'|'wiki'|'milestone'|'adr'|'plan'
 );
 ```
 
+For diff source, use **git** (these are all tracked files; if they're
+not, the agent should add them or skip tracking that path):
+
+```
+git show HEAD:<relpath>     ← what was committed
+<relpath>                   ← what's on disk now
+diff the two                ← what changed since the last commit
+```
+
+This naturally handles "the operator edited but hasn't committed yet"
+(diff shows the working-tree change) and "another agent committed and
+SF wasn't running" (diff shows the new commit).
+
 On session start + each autonomous-cycle entry, walk the configured
 glob set, hash each file, diff against `tracked_md_files.sha256`.
 For each changed file:
 
-1. Compute diff against `snapshot` (or `git show HEAD:<path>` if the
-   file is tracked).
-2. Surface to operator: "**N** files changed since last seen — review
-   or accept?" with per-file inline diffs.
-3. On accept → update sha + snapshot. On reject → restore from
-   snapshot.
-4. New files (sha not in DB) → import + classify by glob category.
-5. Deleted files → archive (don't purge until operator confirms).
+1. Surface to operator: "**N** files changed since SF last saw — review
+   or accept?" with per-file diff (computed from git, not from a DB
+   blob).
+2. On accept → update sha + last_seen_at. No content stored.
+3. New files (sha not in DB) → classify by glob category, store sha,
+   continue.
+4. Deleted files → archive the DB row (mark inactive); don't purge
+   until operator confirms.
 
 Useful for:
 - hand-edits / cross-agent edits / git pulls (the original