feat(guard): wire Doors B and C to the real guard (Phase 2 step 4)

Adds llm_ingestion_guard>=0.2,<0.3 as this library's first and only runtime
dependency, and guard_adapter.py -- the one module that imports it. The flows
themselves are unchanged: they still take an injected gate, and importing the
package still does not import the guard, so a Door A consumer is unaffected by
the dependency's state.

Door B screens the exact bytes it persists. The guard's §6 bookends
(prepare_input -> model -> screen_output) assume a model call in between; this
library makes none, and prepare_input returns prompt-shaped text (sanitized
AND spotlight-fenced with a per-call nonce) that must never reach disk. So the
adapter calls screen_output alone, on the extracted text as it stands, and
hands that same text back -- the verdict is then a statement about the bytes
actually written. This supersedes the plan's "bookends" wording, recorded
there under "Settled during implementation (step 4)".

It follows that the gate refuses rather than repairs: a file carrying an
invisible carrier is rejected, not stripped and persisted. Sanitizing first
would write a document differing invisibly from the operator's file while
source_sha256 still points at the original bytes. Operator decision; the
policy is PRESET_USER_UPLOAD, so any finding at all is held back.

Door C hands the bundle over whole to okf.import_bundle, which resolves the
cross-link graph across concepts. Per-concept reasons are derived from the
scan findings (severity:label) because stamp_concept keeps the disposition and
drops the reason strings behind it.

Assumption B1 closes as a signature smoke test over what the adapters actually
call -- screen_output and okf.import_bundle signatures, the Disposition values
both doors compare by value, the Origin/Channel vocabularies Door C validates,
the result fields read, and the upload preset's shape. prepare_input is not
pinned: drift there cannot reach this library. Behaviour is pinned against the
real scanner too, including the persist-gate proof that a fail-secure fixture
leaves the bundle byte-identical.

B2 closes with it: git+https tag install over anonymously readable HTTPS, no
credential. A direct reference is an install-time channel, not the pin -- the
range stays in pyproject, is satisfied by the tag install today, and resolves
normally once the package index exists. A packaging test enforces that the
guard remains the only runtime dependency (verified by hand-mutation).

CLAUDE.md

@@ -79,9 +79,12 @@ Phase 4 preconditions (coordination, not unilateral moves):
 ## Stack
 
 Python 3.10+. Package `llm_ingestion_okf` (src layout, hatchling).
-**Zero runtime dependencies in the core** (stdlib only, like the guard).
-The only permitted future runtime dependency is `llm-ingestion-guard`
-(itself zero-dep), added when the first persist gate is implemented.
+**Exactly one runtime dependency, ever:** `llm-ingestion-guard>=0.2,<0.3`
+(itself zero-dep), landed with the Door B/C persist gates. Everything else is
+stdlib, and a packaging test enforces it. Only `guard_adapter.py` imports the
+guard; importing the package does not. Install channel until the package
+index exists (a direct reference is a channel, not the pin):
+`pip install "llm-ingestion-guard @ git+https://git.fromaitochitta.com/open/llm-ingestion-pipeline-security.git@v0.2.0"`.
 Binary extraction parsers live behind the `[extract]` extra only.
 
 Phase 4 adds a `node/` half: Node/ESM with zero npm dependencies