# Task 06 — Image tests: unit + integration + isolated E2E

**Phase:** `122_image_documents` · **Source:** `TODO.md:6` — "Need to support images …"

## Objective
Pin the whole image-document contract: the off-by-default byte-identity, the ingest/description/serve pipeline, the RAG display, and the end-to-end user path (upload → Sources → viewer → chat) as an isolated Playwright suite.

## Work
1. `tests/unit/test_image_documents.py` (new) — consolidates the per-task unit cases (the tasks ship code; this task ships the full pin):
   - settings: defaults (`images` False, six-extension frozenset, dir default), env overrides, case-insensitive parse (task 01);
   - the walk: image accepted iff `images=True`; off → the file is ignored (the default byte-identity);
   - `_index_file` image branch: digest over BYTES, copy to `image_dir`, `is_image`/`image_path` set, changed-image stale-copy delete, prune guard (off → survives; on + gone → pruned + copy deleted), `images_failed` in the log line (task 02);
   - `describe_image`: mock-client prompt shape (multimodal parts, chat model), cap, `None` on error/empty, the importer skip path (no row, no orphan, counter, warning) and the success path (content == summary == description; embedding called with the description only) (task 03);
   - the ext→mime map (task 04);
   - the source-frame `image_url` helper (present/absent) + the agent `read` marker + house-style frontend assertions (viewer `img` + alt + fallback; sources thumbnail fallback; chat sources inline image + alt) (task 05).
2. `tests/integration/test_docs_api.py` (extend, task 04's cases) — the image route (200 + Content-Type per ext; 404 text doc / missing id / missing file), the content endpoint's `is_image`/`image_url` omission rules; `tests/integration/test_chat_api.py` (extend, task 05's case) — the SSE `image_url` frame; `tests/integration/` (new file `test_image_import.py` or the existing import test file — follow whichever exists) — `import_sources` end-to-end: `images=True` + mock vision → the fixture PNG becomes a doc (description content, `is_summary` chunk, one content chunk); `images=False` → ignored + a pre-seeded image doc survives prune; a failing mock → `images_failed == 1`, no row, other docs indexed.
   - Fixtures: a tiny valid PNG (a few bytes, generated in-test or a committed fixture under `tests/` — check the existing fixture conventions), a mock vision client (the existing mock-LLM test patterns in `tests/`).
3. `tests/e2e/test_image_documents.py` (new — isolated run per AGENTS.md §4: `uv run pytest tests/e2e/test_image_documents.py -v --no-cov`). The suite's app instance runs with `BOR_IMAGES=true` (env override in the E2E fixture — the `conftest.py` pattern for per-suite app env):
   - upload a fixture PNG (the Sources-page upload flow or `page.request` against the upload endpoint, then trigger the sync through the UI as the Sources page does);
   - the Sources page lists the image doc (thumbnail or icon fallback);
   - open the document viewer → the image renders + the description text below it;
   - ask a question the mock LLM grounds on the image doc (the existing mock-LLM grounding pattern) → the chat's sources block shows the inline image with its caption;
   - negative: with the DEFAULT env (`BOR_IMAGES` unset/false), the same upload produces NO image doc (the default-off contract).
4. Run the full gate: `uv run pytest`, `uv run pytest --cov=app --cov-report=term-missing` (TOTAL >90%), the isolated E2E file, `uv run ruff check . && uv run pyright`.

## Testing & Quality
- This task IS the phase's test suite (see Work).
- Coverage: **>90%** on `app/` — the phase's `app/` surface (config, importer, summarizer, docs API, chat frames, agent marker) is fully exercised.

## Completion Criteria
- [ ] All test artifacts exist and pass; the isolated E2E file passes standalone.
- [ ] The default-off byte-identity is asserted (unit + integration + the E2E negative case).
- [ ] `uv run pytest --cov=app` TOTAL >90%; lint + types clean.