Three owner-reported defects become executable phases; TODO.md is cleared
once the roadmap is written (Protocol B append, PLAN.md/AGENTS.md untouched).
- 165_prose_word_wrap (TODO L3): image descriptions and .txt bodies render as
a wrapping .doc-prose block instead of <pre class="doc-raw"> (page + modal via
the one renderDocument core). Code and code-ish formats keep horizontal scroll
- phase 116 locked A1 survives; extracted PDF text stays raw and the deferral
is recorded as an owner call, not an oversight.
- 166_hide_empty_answer_bubble (TODO L4): .msg .bubble:empty { display: none }.
CSS-only, so the phase-158/161 "reasoning container inserts before the bubble"
anchor and its unit pins stay untouched; the box returns at the first delta,
and the shared/restore empty-answer corners take the same path.
- 167_api_payload_diet (TODO L5): selective pure-ASGI gzip (SSE /api/chat skipped
by exact path), a depth-limited KB tree with server-side totals + truncated
nodes whose recursive updated_at comes from a new aggregate map, a
GET /api/docs/tree/node drill route, content-hash weak ETag/304 on the catalogue
reads (NOT sources_meta - bumping it would mark saved chats stale), the lazy
client drill, and a /api/* byte-budget log line plus scripts/api_payload_audit.py
whose measured numbers land in AUDIT.md.
Phase 97's "one fetch, drill client-side" contract is deliberately superseded
(locked A3); phase 116 A1, phase 158/161 anchors and A19/A20 middleware order are
explicitly preserved.
LLM-Generated: true
All green. Final report:
**Phase 160 completion pass — verified (final verification; all 5 tasks already in `complete/`)**
- **Verified, no code defects found:** budget trailers (`TOOL_BUDGET_REMAINING/LAST/SPENT`), cap-path rejection + `ROUND_CAP_FALLBACK_ANSWER` + `ROUND_CAP_WRAPUP_INSTRUCTION`, `done.budget_exhausted` (ABSENT-when-false), `rounds=/cap_hit=` log fields, `agent_max_rounds=10` default, frontend Continue button + restore + shared-page exclusion, mock markers.
- **Tests/lint:** `uv run pytest` 153/153 green (EXIT 0); `uv run pytest --cov=app --cov-report=term-missing` TOTAL **99%** (>90%); `uv run ruff check .` clean; `uv run pyright` 0 errors/0 warnings.
- **Criteria:** ① decreasing trailer pinned by unit tests (9→…→spent) ✅ ② cap path ends readable, no tool lines after cap (E2E) ✅ ③ `budget_exhausted` true-only-on-cap, absent otherwise (integration) ✅ ④ Continue button → one fresh `continue` turn, fresh budget, record intact (E2E) ✅ ⑤ flag survives refresh; shared chat never renders it (`shared.js` has no `budget_exhausted` path) ✅ ⑥ `max_rounds=0` byte-identical single `tools=None` request; default still 10 ✅ ⑦ full suite/coverage/lint green ✅ ⑧ `test_tool_budget_telemetry.py` **7/7** in isolation; all 6 regression E2E suites green in isolation ✅ ⑨ commit + phase move = harness (I make no git history/index changes).
- **Docs:** README.md — fixed: the "Continue researching" button and cap behavior were undocumented (added a Chat-section paragraph + an Agent-tools-section paragraph, incl. the phase-71 recorded-revision note); env-var table, commands, and architecture all verified consistent otherwise. AGENTS.md — verified consistent, no changes needed.
- **Decisions:** no code changes required — phase was fully implemented; only README docs added. No live-infrastructure touched.
- **Next pending phase:** `161_reasoning_bubble`.
TODO.md's two open items become executable phase directories under .agents/phases/todo/:
- 159_edit_and_resend_message (5 tasks): inline edit affordance on the last
user bubble, in-place resend that truncates the replaced turn, an editable
error turn after an oversize question, and the Playwright suite
tests/e2e/test_edit_and_resend_message.py.
- 160_tool_budget_telemetry (5 tasks): remaining tool-call count in every
tool result, tool calls rejected (never shown) once the budget is spent,
the additive done.budget_exhausted flag + rounds=/cap_hit= log fields,
the Continue researching affordance, and
tests/e2e/test_tool_budget_telemetry.py.
No application code changed; the TODO lines are recoverable from git history.
LLM-Generated: true
All criteria verified. The CLI path is hook-less (only `app/api/sync.py` passes the hook), and the byte-identity is pinned by `test_on_image_progress_none_run_is_byte_identical`.
## Final Report — Phase 152 final verification pass
- **Verified (no new code needed):** `SyncStatus.images_done/images_total` + reset/clear rules in `app/api/sync.py`; `on_image_progress` threaded through the importer's three PDF vision spans with the continuous per-file counter; the `_image_hook` closure; `sources.js` `· image n/m` label part (box + title + aria).
- **C1** status climbs 1→N + UI shows `· image n/m`: ✅ unit 3/15→15/15, integration 1/15→7/15, E2E 1/4→4/4 (title/aria ride the full string)
- **C2** never frozen: ✅ E2E asserts ≥3 distinct positions, starting at 1, non-decreasing, ≤ total, reaching it
- **C3** cleared at overview/summaries + all terminals; per-file reset via `_hook`; no stale position for image-less files: ✅ unit pins + E2E settle (image part gone in box/title/aria, endpoint 0/0)
- **C4** `/api/sync/status` additive-only: ✅ full-dict pin passes (all pre-existing keys unchanged + the two new 0/0 keys)
- **C5** hook-less caller byte-identical: ✅ CLI passes no hook; `test_on_image_progress_none_run_is_byte_identical` green
- **C6** `uv run pytest`: **3526 passed, exit 0** (95s); dedicated E2E in isolation: **2 passed** (95s); `uv run ruff check . && uv run pyright`: **clean**; coverage: **99% on `app/` (>90% gate)**
- Regression: all five neighbouring E2E suites green in isolation (progress_box 8, chunk_progress 2, label_mobile 4, pdf_support 6, image_documents 4)
- **C7** atomic commit: left to the harness (no git index/history touched per rules)
- **Docs:** README.md — sync-label paragraph already updated this phase, accurately; all `.env.example` vars documented; routes/commands verified — **no changes needed**. AGENTS.md — all references (PLAN, user_stories, test_smoke.py, .env.example, gpg config, .gitignore) verified — **no changes needed**
- **Defects found in prior work:** none (one prior env-leak defect was already fixed inside this phase's task 04, conftest)
- No live-infrastructure touched; no ntfy used. **Next pending phase:** none — `todo/` held only this phase
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
ducoterra