Converts the three open TODO items into executable phases (Protocol B
append, numbered after the existing 149):
- 150_drop_sync_result — retire span.sync-result; #sync-progress becomes
the single sync surface and the sole aria-live region (TODO L5)
- 151_pdf_image_extraction — dedupe PDF image occurrences (46 placements
-> 15 unique in podman-systemd.pdf), composite /SMask so masked images
are not blank, and skip near-white decorative underlays (TODO L4)
- 152_sync_progress_image_pass — report the PDF vision-image position so
the sync label stops freezing at the last chunk (TODO L3)
Both reported bugs were reproduced against test_sources/podman-systemd.pdf
before authoring; root causes are recorded in the phase overviews. The
TODO file is cleared now that its items live in .agents/phases/.
LLM-Generated: true
All verification complete. The `ink-soft`/`--surface` pair the box uses is already pinned AA by the existing theme E2E suites (8.2:1 dark, ~6.9:1 light). Everything is green — no fixes were needed.
**Phase 149 final verification report**
- Verified (no re-work needed): `#sync-progress` box wiring (single `setSyncLabel` writer with `running` flag; `is-running` class travels with the spin; aria-label owned by the writer), the panel/icon-only-button CSS, and the 5-test dedicated E2E; all 6 pre-existing sync E2Es' running pins migrated to the box, settled pins untouched.
- Dedicated E2E: `uv run pytest tests/e2e/test_sync_progress_box.py -v --no-cov` → **5 passed in 198.6 s** (isolation, slow-proxy mock; under the 600 s budget).
- Full suite: `uv run pytest --cov=app --cov-report=term-missing` → **3463 passed, app/ coverage 99%** (>90% gate).
- Migrated sync E2Es, each in isolation: `test_sync_button` 3 passed, `test_sync_cancel` 3, `test_sync_chunk_progress` 2, `test_sync_label_mobile` 4, `test_sync_summary_visibility` 3, `test_sync_upload_progress` 4 — all green.
- Lint/types: `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors.
- Criteria: in-flight spinner-only button + full untruncated wrapped box (desktop & mobile 390×844, `scrollWidth ≤ clientWidth`) ✓; settle byte-identical ("Synced HH:MM" + `3 added`, box hidden, aria restored) ✓; `#sync-result` sole live region (box `aria-hidden`), mid-run reload re-attaches ✓; WCAG (AA contrast both themes via the pinned ink-soft/surface pair, focus-visible, reduced-motion kill intact at styles.css L2201) ✓; cancel/409/error/upload/status API unchanged (green suites above) ✓.
- Documentation: README.md reviewed in full (sync-states paragraph now matches the shipped UI; env-var table matches `app/config.py` and covers all `.env.example` vars; pages/commands verified) and AGENTS.md reviewed in full — **verified consistent, no changes needed**.
- Notable: no defects found in this or prior work; no live infrastructure touched.
- Next pending phase: none — `todo/` will be empty once the harness moves 149 (only 149 was pending).
Protocol B append (phases 141-145) for the five TODO items: the
read-range dedupe false "Already in context" bug (141), the stale
KB overview recency ordering + honest intro (142), the mobile
keyboard pop after answer completion (143), the document modal
back-button history entry (144), and the git original-source links
in answers + the doc modal (145). TODO.md cleared (items now live
in .agents/phases/todo/).
LLM-Generated: true
Converts the TODO list into the phased-execution roadmap (Protocol B
append): incremental folder summaries on sync (127), the mobile sync
label with the pinned (n/m) count (128), per-chunk embed progress in
the sync label (129), chat answer clusters with the bottom-right
actions row (130), read(offset/limit) line ranges for huge documents
(131), visible chat image-upload feedback (132), and the garbage-PDF
text gate with the page-screenshot vision fallback (133 — includes
the diagnosed root cause of the hnb guide's pre-phase-126 binary
import). Each phase carries its dedicated in-isolation Playwright
suite; TODO.md is cleared (items now live in .agents/phases/todo/).
LLM-Generated: true
All verification complete — every gate green. Final report:
**Phase 117 final verification pass — all criteria verified** (tasks 01–04 were already in `complete/`; I re-verified the full gate myself, no code changes needed)
- **Verified:** `appendToolLine` wraps lines in `details.tool-calls-disclosure` (open live, `closeToolCalls` at delta/done/stop + restore-closed, count via textContent); `addToolLines` parity (closed); `.tool-call` deboxed / `code` dechipped; new disclosure/summary CSS; only the one pinned CSS assert updated
- `uv run pytest` → **2466 passed**
- `uv run pytest --cov=app --cov-report=term-missing` → **99%** on `app/` (>90% floor)
- E2E in isolation: `test_tool_call_compact.py` **4 passed** (fold/expand/deboxed-flow/restored-folded); `test_agent_document_tools.py` **4 passed**; `test_big_read_progress.py` **4 passed** (live disclosure open + `.tool-elapsed` visible); `test_thinking_display.py` **5 passed**; `test_smoke.py` **3 passed**
- `uv run ruff check . && uv run pyright` → clean (pyright 0 errors, 0 warnings)
- Completion criteria: pins 1–4 ✅ (E2E above); live "calling tool" state byte-identical ✅ (`test_frontend_tool_states.py` 10 passed incl. `test_calling_tool_label_strings`); scope ✅ — `git diff` limited to the 3 frontend assets + 2 unit tests + E2E story + phase files, **0 changes in `app/`**
- Notable: `TODO.md` carries a **pre-existing uncommitted owner edit** (new retrieval-context idea) already in the tree before this pass — left untouched, will ride along in the harness commit; pre-existing committed quirk: the brain-wave commit's styles.css comment mislabels itself "Phase 117" (cosmetic, out of this diff)
- No commit made (harness commits + moves the phase); **next pending phase: none** — `todo/` holds only phase 117