ANTHROPIC_API_KEY is now the ONLY accepted credential. Through v0.1.0 the
preflight cleared on CLAUDE_CODE_OAUTH_TOKEN, and run_s10 went further: an
unset key printed "note: relying on the CLI's own credentials" and carried
on. That note was not a warning, it was a decision - made silently, on the
operator's behalf, about who pays. Both paths are gone; a run with no key
refuses with exit 2 before anything is opened.
Red first, both halves: _check_credentials refuses an OAuth-only env, and
the run entrance is driven as a real subprocess with a deliberately missing
bundle, so the credential refusal must win the race against the bundle
error. Detach it and the process reaches navigate_bundle instead - a
different exit code, no refusal line, the fallback back in the output. The
positive control (key set) gets past the gate and fails on the bundle, so
the gate is a gate and not a wall. 997 -> 1002, offline, no key in env.
The SDK exception is now stated where a reader meets it, not implied: this
framework runs on the Claude Agent SDK, which starts the Claude Code CLI it
bundles as a subprocess. That is the SDK's intended use WITH an API key,
and it is a deliberate, stated exception to the owner's rule that his own
code never starts Claude Code. Rewriting to direct HTTP calls was weighed
and declined - measuring what the Agent SDK offers is the point of D7. The
repo is closed as a worked example.
Two prose claims were corrected rather than left standing: run_s10.py is no
longer byte-frozen (it carries exactly one change, and runs/s10/ is still
the v0.1.0 run), and its two round() call sites moved 110->118, 130->138.
The credential paragraph is prose under an existing heading, not a new
section: test_readme_anchors_loadbearing.py pins 14 heading ids MEASURED on
the published page and forbids re-deriving them. This order forbids push, so
a new heading could not have been honestly re-measured.
Version 0.1.1: pyproject.toml, uv.lock self-entry, CHANGELOG - 3 of 3. No
version badge in README, no constant in src. v0.1.0 stands as released.
Order 20260920T131502Z-7496226791-from-.claude. The older D7 mirroring order
20260913T053840Z-9473220509 is retired unexecuted: po closes at v1.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Door A pin bump to the tag released 2026-07-23 (f14c075), verified present on
the public open/ remote before bumping. v0.3.2 fixes frontmatter/index values
to be emitted verbatim (only source_query is whitespace-collapsed, per
ingest-spec §5) and types the NUL-byte path failure as SourceError.
Verified after the bump: 562 tests green, golden fixture byte-for-byte
identical (test_materializes_golden_byte_for_byte), mutation controls still
diverge so the golden test stays load-bearing, ruff + mypy --strict clean.
No error code changed, so the exc.value.code asserts stand unmigrated.
This confirms the library CHANGELOG claim that shipped golden fixtures and
both consumers are unaffected — for this consumer, as measured.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MQu2xxwedckjU56byu1aUG
Pin dae0bd1a -> v0.3.1 (=692f2df) on the public Forgejo mirror; uv.lock pins
the exact commit behind the tag.
- Drop the mypy override: the library ships py.typed from v0.2.0, so strict
mode now follows its real types instead of follow_untyped_imports.
- Migrate 8 library-error assertions from pytest.raises(match=...) to
exc.value.code — message text is explicitly unstable from v0.3.0, the
codes are the stability contract.
- Fix a real breakage the bump surfaced: IngestResult gained a required
`stamp` field (d3a3bcc), which the delegation fake did not construct.
- The read-only SQL test loses resolution under the code contract
(`sql_failed` is generic), so it now proves read-onlyness by effect —
the write never lands — instead of by message wording.
- Correct the guard plan: G1's persist-gate anchor (ingest.py:372-387) died
with the 2026-07-16 adoption. Door A is ungated by the library's own
README, so gating stays our responsibility at the call site.
Verified: 426 tests green, golden output byte-exact unchanged, full gate
clean (ruff + format + mypy strict).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RmNAgbRXUgvoSKxVK4Bevv
Replace the local 391-line ingest implementation with a thin adapter over
the shared llm-ingestion-okf library (git-pinned dae0bd1a via Forgejo,
tool.uv.sources). The materialize() signature is preserved; error types are
now the library's typed hierarchy rooted in IngestError, re-exported from
the consumer seam.
- tests/test_ingest_adoption.py: new load-bearing seam tests (delegation,
offline invariant — allow_network is never passed, error contract),
detach-proven red twice.
- Golden suites (file + sql) pass UNCHANGED — byte-exact behaviour proven
against the repo-local fixtures.
- 6 test files migrated to the library error hierarchy; escaping/typed-cell
unit tests dropped (byte-bound by the ingest-edge.md golden, unit-owned by
the library's own 189-test suite). Provenance stamp now asserted
independently from the §5 rule.
- mypy override follow_untyped_imports for llm_ingestion_okf (no py.typed
upstream yet — reported as a finding).
Suite: 386 passed; ruff + format + mypy --strict clean; shared/, examples/,
runs/s10/ and run_s10.py byte-untouched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- File-layer decision vocabulary (§4.2 set) with SKIP semantics — an unknown
decision never reaches the store (C-F7, the review's run proof is the fixture)
- Fail-fast caps (max_files / max_rationale_chars) via InboxLimitError raised
OUTSIDE the tolerant try — a cap breach is never swallowed as a skip
- R-6 id grammar (mirrors ingest _ID_RE) as a pydantic pattern on
VerdictDocument.id AND re-checked in write_verdict, since model_copy(update=)
bypasses model validation — traversal ids can no longer write outside the inbox
- promotion._filename_token: any sanitised id maps to a content hash — 'e/vil'
can no longer clobber the distinct id 'evil' (restarbeid-funn 2)
- SDK pinned >=0.2.111,<0.3 + version guard test naming the sdk_client.py
attribute premises; resolved 0.2.120, all premises re-verified against it
- sdk_client read loop bound offline with REAL SDK message types (R-4/R-5):
text aggregation, error fail-paths, usage/cost extraction, _total_tokens
fail-closed, non-positive budget guard
- test_sdk_isolation comment no longer claims the --system-prompt ""
serialization the test body does not bind (honesty rule §1)
Guard-G2 assessment (guard-plan §4): the allowlist + caps + id grammar landed
here are G2's necessary part; an optional scan_output depth pass over
rationale (still a verbatim prose channel into the fold prompt, R-9) remains
relevant as a later additive session — the trigger picture is unchanged.
4 detach proofs red → restored green. Full gate: 389 passed (365→389),
ruff+format+mypy clean; golden + shared/ + runs/s10/ byte-untouched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude Agent SDK verified against official docs + PyPI 2026-07-03 (0.2.110, CLI
bundled, offline import without API key). Contracts mirror method-spec §10/§4.1/§8:
data-source, model-map (per-profile default required), termination (positive caps),
binary feedback decision. TDD: tests written red-first; suite 14/14 green without
any API key; ruff + mypy --strict clean.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AaQCFnfsh3tfq1VfzdJpoi
