296 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
ducoterra	c6ffa050a6	phase: 190_app_name_settings_fix ... All gates re-verified green. Report: - **Verified (all 4 tasks already complete; this was the final pass):** `effective_settings` resolves the 3 brand strings panel-row → tab-row → env (`applied_override_keys`, presence-not-value); `PUT /api/ui-settings` ignores string body fields; Theme-tab form is colors-only (17 pickers, no `#theme-app-name`/`#theme-placeholder`/`#theme-footer`); the ONE shared `applyBrandFromConfig` re-applies title/`.brand-text`/footer/placeholder after a panel save-reset and a tab save-reset; boot path byte-identical (single `/api/config`). - **Completion criteria:** - strings order panel→tab→env, both branches — ✅ `tests/unit/test_theming.py::test_effective_app_name_prefers_settings_panel_row_over_ui_settings_row`, `..._fall_back_to_ui_settings_row_without_panel_row`, `..._per_field_panel_then_tab_then_env`, `..._ignore_panel_rows_when_the_overlay_is_off` - PUT ignores string fields + no 3 inputs in the tab — ✅ `tests/integration/test_ui_settings_api.py::test_put_ignores_string_fields_in_body` (+2) and the E2E `test_theme_tab_dom_is_colors_only` - live apply without reload + incident regression — ✅ `tests/e2e/test_app_name_settings_fix.py` tests 1–4 - byte-identical boot, no double-apply — ✅ `tests/unit/test_brand_live.py` markers + E2E "exactly one /api/config" - suite green, coverage >90%, ruff+pyright clean — ✅ - no behavior change in prior phases — ✅ (palette, phase-168 panel, env fallback suites all green) - atomic commit — **left to the harness** (pipeline rule overrides per-phase committing; no git write run) - **Gates:** `uv run pytest --cov=app --cov-report=term-missing` → **4630 passed, TOTAL 6941 16 99%**, exit 0 · `uv run pytest tests/e2e/test_app_name_settings_fix.py -v --no-cov` → **6 passed** in isolation · regression E2E (isolated, one process each, all exit 0): `test_smoke` `test_configurable_brand` `test_admin_theme_tab` `test_theme_save_and_coverage` `test_theme_semantic_completion` `test_themed_favicon` `test_dark_tech_theme` `test_admin_settings_panel` `test_admin_settings_layout` `test_settings_mobile_value_width` · `uv run ruff check .` → All checks passed · `uv run pyright` → 0 errors. - **Documentation:** README — fixed "saving one repaints *every* open page" (only the open document repaints; other pages on next load) and a broken paragraph wrap in *Customizing the look*; AGENTS.md rule 16 — `test_chunks_hnsw_recall.py` now described accurately (index paths forced with `enable_seqscan`/`indexonlyscan`/`bitmapscan` off, unforced plan asserted only on a pristine relation); `tests/unit/test_theme_frontend.py` — two stale section headers ("20 form fields"/"20 inputs" → 17 color). No AGENTS.md settings-overlay/resolution-order clause exists, so per the phase none was added. Full env-var cross-check (`BOR_*` in `app/config.py` vs README) → 0 gaps; 0 missing file references. - **Notable:** the working tree also carries this phase's flake hardening of the phase-188 `tests/integration/test_chunks_hnsw_recall.py` (verified legit and green). Live infra untouched; shared DB left clean (0 `app_settings`, 0 `ui_settings`). **Flagged, not changed:** `settings_overlay.applied_override_keys` lets a `ProgrammingError` (missing `app_settings`) propagate from public `GET /api/config`, where `load_overrides` deliberately fails soft — only reachable on an un-migrated (0027) DB, outside this phase's pinned A1 semantics, so left for the owner to rule on rather than silently deviating. - **Next pending phase:** `191_source_name_labels_tags`.	2026-10-18 02:59:19 -04:00
ducoterra	47456a44df	chore(agent): phase roadmap from TODO.md, 4 phases (190-193) ... Convert the four open TODO items into executable phases (append mode, starting at 190 after the completed 189): 190_app_name_settings_fix - the Settings-panel app name wins over the Theme tab; the three brand strings stripped from the Theme tab (colors-only); live brand re-apply on save, no reload 191_source_name_labels_tags - source_labels table + admin API + Sources page editor; the separate bounded source_name_hit_bonus retrieval boost; label surfacing in the <document> blocks and KB overview 192_verbatim_inline_midturn - an additive verbatim_block SSE frame at the show_text success moment; in-place mid-turn fence hydration; the done/restore per-locator dedupe; the done frame, record key, restore and shared page stay byte-identical 193_sync_remaining_count - the running sync/upload label counts down: "N remaining" (N = total - done), hidden at the final file; the chunk/image/summaries/terminal parts untouched TODO.md is cleared (its items now live in .agents/phases/todo/). LLM-Generated: true	2026-10-17 19:35:55 -04:00
ducoterra	140a343b92	phase: 189_chat_save_long_turns ... **Phase 189 final verification — all green** - **Verified (all 4 tasks already implemented):** A1 caps in `app/schemas.py` — `sources`/`related`/`tools` 200, `suggestions` 100, `segments` 450; `text`/`thinking` 600 000, `error`/`image` 500, `answer_text` 50, `messages` 500, 8 M budget all UNCHANGED; rationale docstrings rewritten to `merge_cited_docs`/`agent_max_rounds`. A2 `shareCurrentChat` linked branch upserts (PUT, 404→create+re-link) before `POST /{id}/share`, aborts on failure (banner, no token); unlinked branch byte-identical. A3 `savePending` + `finally` re-run. A4 `saveFailedSticky` + one 5 s `setTimeout` retry on network/5xx only, 4xx never retries. - `uv run pytest --cov=app --cov-report=term-missing` → **4609 passed, 1 warning, EXIT=0**, `TOTAL 99%`, `app/schemas.py 100%` (>90%). - `uv run pytest tests/e2e/test_chat_save_long_turns.py -v --no-cov` → **4 passed, EXIT=0** (isolation). - Regression green & **unedited** (`git status` clean): `test_chat_save_payload_limits.py` 2, `test_chat_history.py` 5, `test_share_chat.py` 4. Extra blast-radius sweep (share/save/persist/segments surface, all EXIT=0): `test_save_share_ux`, `test_stale_saved_chats`, `test_history_pagination`, `test_history_copy`, `test_bottom_chat_actions`, `test_reasoning_bubble`, `test_tool_budget_telemetry`, `test_verbatim_show_text`, `test_smoke`. No leaked `saved_chats` rows (`save-long-%` = 0). - `uv run ruff check .` → All checks passed; `uv run pyright` → **0 errors**. - **Completion criteria:** caps ✓ · incident payload 22/33/51 → 201/200 anonymously + 201 tools/451 segments/101 suggestions → 422 naming the offender, row unchanged ✓ · share-saves-first + abort + unlinked byte-identical ✓ · overlap re-run + sticky note + one-shot retry ✓ · phase E2E in isolation + 3 regression suites unedited ✓ · full suite / coverage / lint / types ✓ · `git diff --stat` = `app/schemas.py`, `frontend/assets/app.js`, 3 test files, `README.md` + new E2E & phase files (no `app/api/chats.py`, no migration, no new dependency) ✓ · commit + `todo/`→`complete/` move left to the harness (rules forbid git index writes). - **Docs:** full README review (all 2 258 lines) + machine cross-check — all 85 settings documented in the Configuration reference, all 34 `.env.example` vars documented, documented defaults match `app/config.py`. Fixed 2 inconsistencies: (1) the 117-char prose line task 04 left when reflowing the Saved-chats pager paragraph; (2) the phase-189 sentence implying the 8 M total bounds the widened arrays — now states precisely that the total counts `text`/`thinking`/verbatim-block text only, and that the arrays are bounded by fixed item COUNT (matches `_require_within_total_budget`). AGENTS.md verified consistent — it enumerates no save contract or list cap (rule 5's phase-166 in-flight-turn clause untouched), so **no AGENTS.md change** per the phase mandate. - **Notable/deviation:** the wider caps raise the *theoretical* anonymous-POST worst case (arrays are outside the 8 M char budget); left as designed (A1 fixes every other bound), documented honestly in README — realistic payloads stay ~10 MB, so the existing `client_max_body_size ≥ 16 MB` guidance still holds. No live-infra changes were made (data-repair of the two stale shared rows stays owner action). - **Next pending phase:** none — `189_chat_save_long_turns` is the last entry in `.agents/phases/todo/`.	2026-10-17 07:36:28 -04:00
ducoterra	f20d40e4fe	phase: 188_chunks_hnsw_index ... **Phase 188 — final verification pass: all criteria green.** - **Verified (all 5 tasks already in `complete/`)**: migration `0029` (`CONCURRENTLY` in an autocommit block, INVALID pre-drop, post-validate, tested downgrade) — manual `alembic downgrade -1` → index absent, `upgrade head` → `indisvalid = t` (72 kB); `retrieval_ef_search` = **400** with `SET LOCAL` + clamp-and-WARN in `_vector_candidates`; CATALOG group *"Retrieval & honesty"*; D5 runbook in README. - `uv run pytest --cov-reset` then `uv run pytest tests/unit tests/integration -q --cov=app --cov-report=term-missing` → **exit 0, TOTAL 99 %** (6 946 stmts / 16 miss) — gate >90 % met. (A stale `.coverage` left by an earlier session produced a spurious 90.00 %/3-failure reading; `--cov-reset` cleared it.) - `uv run pytest tests/e2e/test_vector_index_recall.py -v --no-cov` → **4 passed in isolation**; retrieval/chat/recall neighbours (`test_retrieval_quality`, `test_chat_rag`, `test_search_recall_small_sources`) → exit 0. - `uv run ruff check .` → **All checks passed**; `uv run pyright` (whole repo) → **0 errors**. - **Completion criteria**: 0029 DDL + tested downgrade ✅ · ef_search SET LOCAL/clamp/negative-refusal/CATALOG/.env.example/README ✅ (400 everywhere, no stale 100/150 pins) · plan pin + deterministic recall pin (≥0.99 @400, cosine ≤1e-6, monotonicity, vacuity guard) ✅ · live battery off/on recorded (`benchmarks/phase188_live_gate/task05_battery_index_{off,on}.txt` byte-identical, `deterministic_gate_recall.txt`, build 161 s / 1 625 MB / 81 MB RSS, phase report `.agents/reports/188_chunks_hnsw_index/`) ✅ · pytest/coverage/ruff/pyright ✅ · phase E2E ✅ · docs ✅ · commit left to the harness. - **Documentation**: reviewed README + AGENTS end-to-end — all 85 `Settings` fields documented in README *and* `.env.example`, every path referenced by both docs exists (0 broken), `BOR_SETTINGS_DB` real, `BOR_THEME` correctly described as retired, runbook matches the measured `/dev/shm` = 63 MB finding, ef_search default consistent → **verified consistent, no changes needed**. - **Notable**: built and ran a temporary offline synthetic recall gate (`--docs 1000`, 8 000 chunks) to re-check A7 without an endpoint; on near-orthogonal synthetic vectors exact parity only arrives at `ef_search ≈ 700` (400 → 0.91), which is a property of that corpus distribution, not of the index — exactly the counter-case already recorded in `tests/integration/test_chunks_hnsw_recall.py`. Because a synthetic corpus can't be calibrated to the real embedding cone without the endpoint, I **deleted the script** rather than ship a verdict that could be misread as production. `AIPI_KEY` is absent in this environment (and `100.117.2.24:1219` /embeddings times out), so the live battery could not be re-run — its recorded task-04/05 captures stand. Scratch DB `brain_of_reese_hnswgate` dropped; repo left clean. - **Next pending phase**: `189_chat_save_long_turns`.	2026-10-17 03:18:23 -04:00
ducoterra	c054b47df5	phase: 187_sync_peak_memory_line ... **Phase 187 — final verification pass: all criteria met, repo 100% green.** Verified (all four tasks already in `complete/`) - `app/core/memory.py`: `rss_mb` / `rss_peak_mb` / `cgroup_peak_mb` / `fmt_mb`, pure stdlib, never-raise, **100%** coverage, 24 branch tests. - Lifecycle lines append-only: `sync: started … rss_mb=`, all three terminals `… rss_mb= rss_peak_mb=` (failed = sanitized one-liner beside the surviving `logger.exception`), `import: summary … rss_mb=`; prefixes byte-identical. - `GET /api/sync/status`: additive `rss_mb`/`rss_peak_mb` (`int|null`), keyed off the ONE `_sample_rss` (run start, phase transitions, forced terminals, 5 s-throttled hook), `peak >= current` invariant, anonymous 403. - `sources.js` `fmtSyncPeakClause`: ` · peak <N> MB` trailing the counts line / "Sync cancelled", nothing when null, no new control/live region. Gates (exact commands) - `uv run pytest --cov=app --cov-report=term-missing` → **4570 passed**, TOTAL **99%**, `app/api/sync.py` **100%**, `app/core/memory.py` **100%** - `uv run ruff check .` → clean · `uv run pyright` → **0 errors** - `uv run pytest tests/e2e/test_sync_peak_memory_visible.py -v --no-cov` → **5 passed in isolation** (ran twice) - All 27 touched E2E families re-run **in isolation**, all green (progress_box 8, cancel 3, status_freshness 4, summary_visibility 3, sync_button 3, session_reset 4, git_freeze 2, git_log_stream_dates 5, PDF/image suites, …) Completion criteria: every checkbox ✅ except the commit + phase-dir move, which belong to the harness. Documentation - README reviewed in full (pages, commands, config tables cross-checked against `app/config.py` — 85 env rows, all defaults match; phase-187 ops section, greps, process-vs-cgroup caveat): consistent, no changes needed. - `AGENTS.md`: **fixed one pre-existing inconsistency** — rule 6 claimed the no-CDN test covers "the index page"; it actually parametrizes 10 pages (all but `/doc-edit.html`). Notable - Two failures early in the pass were self-inflicted by running the E2E module concurrently with the full suite on the shared Postgres (TRUNCATE deadlock + one order-dependent `test_overview` flake); both vanish under the documented serial isolation — no code defect, no change made. - **PLAN §9 still needs the owner's reconciliation** (phase 187 adds the sync memory fields + two status keys; PLAN is never agent-edited — AGENTS rule 10 carries the spec). `TODO.md` holds an unrelated owner note, left untouched. Next pending phase: `188_chunks_hnsw_index`.	2026-10-16 15:22:51 -04:00
ducoterra	644f7de696	phase: 186_git_log_streaming_dates ... ## Final report — phase 186 `git_log_streaming_dates` **State found:** all three task files were already implemented and in `.agents/phases/complete/186_git_log_streaming_dates/`, so this run was the final verification + documentation pass. ### Verification (all green) | Gate | Result | |---|---| | `pytest --cov=app --cov-report=term-missing` | **4531 passed, exit 0** · coverage `TOTAL 6872 stmts → 99%` (gate >90%) | | `tests/e2e/test_git_log_stream_dates.py -v --no-cov` (isolation) | **5 passed** | | `ruff check .` | All checks passed | | `pyright` | 0 errors | Implementation shape confirmed against the phase contracts: `_parse_commit_dates(str | Iterable[str])` (existing string pins untouched — only 3 non-test lines removed from `test_git_sync.py`), `stream_git_lines` (`Popen` + daemon stderr drain + per-line stdout + terminate-on-abandon, `run_git`-shaped `GitSyncError`), `file_commit_dates` on the stream with byte-identical dates and the fail-soft funnel unchanged, `async_sync` propagating the `to_thread` errors to the existing `except`. A11 holds: two `subprocess.` sites, both in `scripts/git_sync.py`, both off-loop. ### Documentation-consistency pass Verified (clean): all ~100 `BOR_*` README defaults against a bare `Settings()` (the local `.env` produced false positives — none real), `.env.example` completeness, every module/route/page/test path referenced, `compose.yaml`/`Containerfile`/`entrypoint.sh` claims, E2E port conventions (8901 / 8123), palette count (17), chip cap (90), token format, payload limits, retrieval battery + audit commands. Fixed (both files, prose only): - **Page-naming drift** — README/AGENTS called the sync/catalog page "the Sources page" in 5 places, contradicting the README's own convention (and `frontend/index.html`): the **Sync sources** button and the document catalogue are the **RAG** page (`/sources.html`); "Sources" is `/git-sources.html`. Now `RAG page (/sources.html)` in README:186, 376, 418, 682, 713, 745, 1006, 1057 and AGENTS:19, 38, 183. - **Phase-186 AST-pin wording** — "fails if a third spawn appears anywhere in `app/` or `scripts/`" overstated it (the pin *enumerates* the spawns, including the non-git Valkey probe in `app/core/caching.py`); rewritten to describe the enumeration. - Moved `00_phase.md` into `complete/186_git_log_streaming_dates/` (AGENTS rule 2 moves the whole directory); `todo/` now starts at 187. ⚠️ **One mistake to disclose:** while tidying line wraps I ran `git checkout README.md`, which discarded task 03's uncommitted phase-186 README bullet. I restored it verbatim from the full `git diff` captured earlier in this session (plus the two corrections above) and re-verified the section renders as intended — no other README content was uncommitted, and AGENTS.md was untouched by the checkout. A blanket line-length rewrap also reflowed 4 unrelated lines; all four were restored to their exact original text (`git diff` now shows only intended changes). Nothing was committed or staged — the working tree is left for the harness: modified `scripts/git_sync.py`, `app/api/sync.py`, `app/rag/git_sources.py`, `tests/unit/test_git_sync.py`, `tests/integration/test_git_file_dates.py`, `README.md`, `AGENTS.md`; new `tests/e2e/test_git_log_stream_dates.py`, `.agents/phases/complete/186_git_log_streaming_dates/`, `.agents/reports/186_git_log_streaming_dates/`.	2026-10-16 07:50:16 -04:00
ducoterra	632fb88e43	phase: 185_sync_defer_content_fast_path ... All gates green. Report: **Implemented / verified (phase 185)** - `_doc_row_stmt` is the ONE deferral helper for all four fast-path row loads; only `Document.content` is deferred, no `raiseload`/`noload` (LOCKED A1/A2) — pinned by `tests/unit/test_importer_defer_content.py`. - `tests/integration/test_import_fast_path_columns.py` (5), `tests/e2e/test_fast_path_deferred_content.py` (3, isolation) green; added 2 constraint pins to `test_import_session_retention.py` (summary-NULL backfill survives the cadence; both prune guards cost the same statement budget). - **Fixed 6 pre-existing E2E failures** (all reproduce at HEAD with this phase's importer reverted): stale pins from phase 168 `Settings` nav link (`test_nav_rename_sources`), phase 182 `verbatim.js` script count (`test_steering`), phase 175 `/api/chats?limit=…` pagination breaking `endswith` counting (`test_navbar_refresh`), phase-167 lazy-drill race in the breadcrumb read (`test_modal_back_button`), nav-length tab budget (`test_suggestion_chips`). - **Fixed a genuine flake** in `test_source_chip_quality` (passed/failed across identical runs): `ORDER BY embedding <=> q` is not a total order, so equal-cosine fixtures get a different RRF rank each run. Pinned it as an explicit tie-group (`_assert_ranked` / `_assert_related_pair`) instead of an exact order. **Tests / lint (all 100% green)** - `uv run pytest --cov=app --cov-report=term-missing` → **4519 passed**, `app/rag/importer.py` **99%**, `TOTAL` **99%** (>90%). - `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors. - Full E2E sweep, one pytest process per file (the README's sanctioned loop) → **167/167 files OK, 0 FAIL** (re-run after the fixes). **Completion criteria**: helper shared by 4 loads ✅ · column-list + 1-SELECT + backfill pins ✅ · `test_importer_unchanged_fast_path.py` 24 passed, zero expectation edits ✅ · full suite + coverage + lint/types ✅ · phase E2E in isolation ✅ · docs accurate ✅ · commit left to the harness (no git commands run). **Documentation**: README + AGENTS.md already carry the phase-185 rule; full pass found and fixed no doc inconsistencies (env vars: all 85 `Settings` fields documented in `.env.example` + README, no ghosts; every `app/… tests/… scripts/…` path referenced in both files exists). **Deviations**: (1) the ranking non-determinism behind the chip-quality flake is real in `app/rag/retriever.py` — a SQL tie-break would cost pgvector index usage, so I kept the fix test-side; a follow-up phase should make vector-candidate ranking a total order. (2) Two tracked E2E screenshots were regenerated by the sweep (artifacts, left modified). **Next pending phase**: `186_git_log_streaming_dates`.	2026-10-16 04:54:01 -04:00
ducoterra	065304b52f	phase: 184_sync_bounded_session ... All gates green; no code changes were needed — the prior failure was a missing final report, not a test failure. **Verified / implemented (phase 184 final pass)** - All 4 tasks present in `.agents/phases/complete/184_sync_bounded_session/`; confirmed their output in the worktree: `sync_session_reset_files=200` / `sync_prune_batch=500` on `Settings` (+ non-negative validators), both `SettingMeta` rows under `"Import & sources"`, `.env.example` + `README.md` entries. - `import_sources` expunges at **exactly two** sites (per-file loop top L972, source boundary L1012) — grep proves no third `expunge`/`expire_all` anywhere in `app/`; `app/db.py:30` untouched. - `_prune` uses `load_only(id, source, path, is_image, image_path, page_count).order_by(Document.id)` + per-batch commits, with the phase-122/126 guards and `changed_paths` intact. **Tests / lint / coverage (all 100% green)** - `uv run pytest --cov=app --cov-report=term-missing` → **4506 passed**, `app/` TOTAL **99%** (>90%). - `uv run pytest tests/integration/test_import_session_retention.py -v --no-cov` → **12 passed**. - `uv run pytest tests/e2e/test_sync_session_reset.py -v --no-cov` → **4 passed in isolation**. - Regression sweep of neighbouring sync suites (each isolated): `test_sync_changed_only` 3, `test_sync_summary_visibility` 3, `test_prune_cascade_cleanup` 3, `test_sync_git_freeze` 2 — all passed. - `uv run ruff check .` → All checks passed. `uv run pyright` → 0 errors, 0 warnings. **Completion criteria** 1. Settings + CATALOG + `.env.example` + README; `test_settings_catalog.py` → ✅ green 2. Retention test green with the post-fix bound and both measured numbers in the docstring (pre-fix 12-row monotone staircase / ≈265 MB extrapolated; post-fix ends at 0, add-path peak 14 vs 21→49) → ✅ 3. Expunge only at the two documented-safe points; light-row batched prune with guards intact → ✅ 4. Every existing importer/sync/removal test green with unchanged expectations → ✅ 5. Full suite green, coverage >90%, ruff + pyright clean → ✅ 6. Phase E2E green in isolation → ✅ 7. README + AGENTS accurate/consistent → ✅ 8. Atomic commit — left to the harness (I ran no git write commands). **Documentation** — Full README (1886 lines) + AGENTS.md (189 lines) review: **verified consistent — no changes needed.** Programmatic cross-checks: every `Settings` field appears in `.env.example` and in the README config reference; every `.env.example` var is documented in that reference; every `tests/…` and `app/…` path cited in README/AGENTS exists; all 10 README page URLs are registered in `app/main.py`; documented E2E port vars (`E2E_APP_PORT_SYNCRESET[_ZERO]`) exist in the test. The only reference-var without a `Settings` field is `BOR_THEME`, which the README explicitly documents as retired (correct as written). **Notable decisions/deviations** — None. No code, test, or doc edits were made this pass; changes remain entirely in the working tree for the harness to stage. `00_phase.md` still sits in `todo/` while tasks 01–04 are in `complete/` — harness-owned, so I left it untouched. **Next pending phase:** `185_sync_defer_content_fast_path`.	2026-10-15 23:19:27 -04:00
ducoterra	7b5ea7c2ee	phase: 183_sync_passive_delete_cascade ... All gates green. Final state verified. **Implemented / verified** - Task 03's work was **never actually done** (its report was a stub, `tests/e2e/test_prune_cascade_cleanup.py` did not exist) → wrote it: 3 tests — 9-file local source synced from the Sources page (`9 added`), 6 files deleted upstream, re-sync (`0 added · 3 unchanged · 6 pruned`), documents vanished from the tree + `GET /api/documents/content` 404 + total 3, **0 orphan chunk rows** via the test's own SQL, survivor chunk total unchanged; partial-prune chat turn (grounded, non-deflected, `query_log` names the survivor and no pruned doc); total source removal (`DELETE /api/git-sources/{id}`) wipes every doc+chunk of the source with 0 orphans, sibling source untouched. Mock-only (`E2E_REAL_LLM=1` skipped), own port 8199, truncate before/after. - Tasks 01/02 re-verified: `passive_deletes=True` + mapper pin, probe flipped to `EXPECTED_CHUNK_SELECTS_PER_PRUNED_DOC = 0`, `_prune`/`delete_git_source` docstrings. - **Drift guard proven non-tautological by my own one-off run**: scratch DB (`alembic upgrade head`) → FK `confdeltype='c'`, guard PASSES, CASCADE delete leaves 0 chunks; FK recreated `ON DELETE NO ACTION` → guard FAILS verbatim and a `passive_deletes` delete raises `ForeignKeyViolation` (never silent orphans). Scratch DB dropped; shared test DB untouched (`'c'`). **Gates** - `uv run pytest --cov=app --cov-report=term-missing` → **4488 passed**, `app/` TOTAL **99%** (>90%) - `uv run pytest tests/integration/test_prune_cascade_statements.py -v` → 4 passed - `uv run pytest tests/e2e/test_prune_cascade_cleanup.py -v --no-cov` → **3 passed in isolation**; `test_source_removal_cleanup.py` 6 passed, `test_force_push_resync.py` 2 passed (both isolated) - `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors **Completion criteria**: passive_deletes+pin ✅ · probe post-fix ✅ · drift guard green + proven-failing variant ✅ · full suite/coverage/lint ✅ · E2E in isolation ✅ · docs consistent ✅ · commit = harness-only (per pipeline rule I ran no git write commands). **Docs**: fixed 4 pre-existing README inconsistencies — per-module E2E ports (claim of "one pair of fixed ports" predates phase 79), debugpy `launch.json` snippet vs the shipped file (`name`/`remoteRoot`), and the page-naming wobble (navbar labels `/sources.html` **RAG**, `/git-sources.html` **Sources** — the Sync button's home is now named correctly in 4 places); added the phase-183 E2E pointer. AGENTS.md verified accurate (rule 12 matches the delete-site audit). **Deviation**: none from the locked decisions; the E2E is a behaviour pin (byte-identical owner-visible behaviour), the statement-count probe remains the memory teeth, as phase 183 D1/A4 specify. **Next pending phase**: `184_sync_bounded_session`.	2026-10-15 16:00:28 -04:00
ducoterra	b34b8ca672	phase: 182_verbatim_show_text ... **Phase 182 — final verification pass (all 8 tasks already complete; this was verification + docs + one defect fix).** - Verified: `app/rag/verbatim.py` (locator grammar, `splitlines()` slice, line-boundary cap, `resolve_answer_blocks`), `SHOW_TEXT_TOOL` + `shown_texts`, `SHOW_TEXT_CLAUSE`, `done.answer_text` (9 fields, key dropped when empty) + `ChatMessageRecord.answer_text` (≤50, 600 000-char cap counted in the 8 M budget), `verbatim.js` + 4 `{verbatim:true}` renderers, `Containerfile` minify step, `.env.example` 3 vars. - `uv run python -c "…answer_text, show_text_max_chars, show_text_max_blocks"` → `True 12000 5`; each negative refuses startup naming its field; `0` accepted as inert ✅ - `bash .agents/validate.sh` → **validation OK**: 4320 unit+integration tests green, `TOTAL 6849 17 → 99%` (gate app/ >90% OK), `ruff check .` "All checks passed!", `pyright` 0 errors (re-run after my edits, 08:28). - E2E, each in isolation `--no-cov`: `test_verbatim_show_text.py` 13 passed (panel bytes == `documents.content`, server caption, clipboard == server string, `/document.html?source=…&path=…`, honest unresolved state, reload+share, `show_image` regression, flag-off app) ✅; green: `test_answer_images` `test_harness_aligned_tools` `test_agent_document_tools` `test_markdown_tables` `test_markdown_inline_links_images` `test_svg_document_preview` `test_smoke` `test_document_viewer` `test_markdown_blockquotes` `test_chat_persistence` `test_thinking_timeline` `test_chat_rag` `test_settings_mobile_value_width`. - **Defect found & fixed (pre-existing, not phase 182):** `tests/e2e/test_admin_settings_panel.py::test_admin_sees_groups_and_source_badges` failed — its whole-page `assert "reese" not in page.content()` tripped on the shell's onboarding chips, which follow the newest saved chats in the one shared E2E DB (a leftover `reeselink.json` question from a tool suite). Scoped the strict sweep to `.settings-shell` and kept a whole-page `reese:reese` credential needle → 12 passed with the leftovers still present. - Docs: README fixed 2 inconsistencies — Quick Start omitted the **required** `BOR_ADMIN_PASSWORD`/`BOR_SESSION_SECRET` (the app fail-loud refuses boot) and the broken anchor `#chat--` → `#chat-`; full re-read of README (1816 lines) + AGENTS confirmed the phase-182 feature/settings/log/UI-contract text matches the code, and every `.env.example` var + every `Settings` field is documented. - Notable: kept `resolve_answer_blocks` synchronous on the SSE terminal path (bounded indexed SELECTs, matching the existing `query_log` precedent and the phase's documented fence-lookup bound); no live-infra changes made. - Next pending phase: none — `todo/` holds only 182 (its 8 task files are in `complete/`; the harness commits + moves `00_phase.md`).	2026-10-15 08:33:12 -04:00
ducoterra	814a400e6d	phase: 181_svg_document_preview ... **Phase 181 — final verification pass (all tasks already complete; verified + docs pass)** - Verified: `app/rag/svg_text.py` (100 % cov), vector branch in `_index_image_file`, `_row_kind_mismatch` text→image migration, `IMAGE_MIMES[".svg"]`, sandboxed CSP on `GET /api/documents/{id}/image`, `.doc-image-img--vector` in `document.js`/`styles.css`, figure/thumbnail deliberate non-changes. - Tests/lint (exact commands): `uv run pytest --cov=app --cov-report=term-missing` → **4265 passed, TOTAL 99 %** (exit 0) · `uv run pytest tests/e2e/test_svg_document_preview.py -v --no-cov` → **5 passed in isolation** · `uv run ruff check .` → clean · `uv run pyright` → **0 errors**. - Regression (each run in isolation, `--no-cov`, all rc=0): `test_image_documents`, `test_chat_image_questions`, `test_answer_images`, `test_chat_answer_clusters`, `test_image_anchor_context`, `test_image_upload_feedback`, `test_markdown_inline_links_images`, `test_prose_word_wrap`, `test_pdf_support`, `test_pictorial_pdf`, `test_garbage_pdf`, `test_pdf_image_extraction`, `test_pdf_image_context`, `test_pdf_pages_in_sources`, `test_pdf_strip_additive_selfheal`, `test_sync_image_progress`. - Completion criteria: ①SVG→`is_image`+`image_path`, no vision call, own `<title>/<desc>/<text>` — **met**; ②`image/svg+xml` + `default-src 'none'; sandbox` + `private, max-age=3600`, raster headers byte-unchanged — **met**; ③chat figure → modal `<img>`, no XML — **met**; ④`/document.html` full-width vector in `.doc-image` + text below — **met**; ⑤`` paints — **met**; ⑥raster/PDF unchanged — **met**; ⑦all gates green — **met**; ⑧commit + phase-dir move — harness-owned. - Documentation: found and fixed README inconsistencies — stale forward reference "left to phase 181 / is phase 181's job" → completed-tense sizing note; "Updating the documents" standalone-image list missing `svg`; new **Raster only** bullet for question uploads (`.svg` → 422) documenting the `chat_images` guard; missing `svg_indexed=N` / `import: svg indexed` log contract; env-table heading `122/123/124` → `122/123/124/181`; new troubleshooting entry for an `.svg` showing raw XML. Full audit: every `Settings` field and every `.env.example` var is documented; pages/commands/scripts all exist. AGENTS.md verified accurate (phase-181 §5 clause present) — no changes needed beyond what the phase wrote. - Notable deviation (kept from task 02): `app/api/chat_images.py` subtracts `_VECTOR_IMAGE_EXTENSIONS` from the question-image accept set — a required consequence of LOCKED A7 (`svg` in the default image set) since `_CHAT_IMAGE_FILENAME_RE` refuses to *serve* `.svg`; the regex itself is untouched, as the phase specified. - Note for the commit: changes include `README.md`, `AGENTS.md` and `.env.example` — the phase file's `git add app/ frontend/ tests/ .env.example .agents/phases/` line omits the two markdown files; stage them too. - Next pending phase: `182_verbatim_show_text`.	2026-10-14 22:54:43 -04:00
ducoterra	6880bd0866	phase: 180_markdown_inline_links_images ... All verification complete. Final state summary: **Report — phase 180 final verification pass** - Verified (all already implemented in working tree): `inline()` chain = code→strong→em→linked-image→image→link→headings→lists in `frontend/assets/markdown.js`; `allowLinkUrl`/`allowImageUrl` allowlists (A5), shared `mdAnchorOpen` (target/rel only for absolute http(s)); `####`→`<h5>`, `#####`/`######`→`<h6>`, `#`/`##`→`<h3>`/`###`→`<h4>` unchanged; `.md-link`/`.md-img`/h5-h6 scale in `styles.css` (palette vars only). All surfaces (chat, thinking, restore, viewer, modal) route through the one renderer (pinned in `app.js`/`document.js`). - Completion criteria: - `[text](url)`→`a.md-link`, `javascript:`/`data:` inert — ✅ (node probe + unit + E2E) - ``→`img.md-img loading="lazy"` with `alt`; bad src inert — ✅ - `####`/`#####`/`######` ladder; shallow rungs unchanged — ✅ - Fenced link/image/`####` stay code; cell-level link renders in `.md-table` — ✅ (node probe) - Byte-identity fixture + phase-44/138 suites pass unedited (git-verified untouched; 6 + 3 E2E pass in isolation) — ✅ - `uv run pytest --cov=app --cov-report=term-missing`: **4198 passed, TOTAL 99%**; `uv run pytest tests/e2e/test_markdown_inline_links_images.py -v --no-cov`: **4 passed**; `uv run ruff check .`: clean; `uv run pyright`: **0 errors** — ✅ - Docs: full README/AGENTS.md review vs the whole project — env-example↔README table complete, page routes match `app/main.py`, AGENTS quick-ref artifacts exist. Fixed 1 inconsistency: README understated the image allowlist (impl per task 02 accepts first segments ≤2 chars, `^.{0,2}/`, not only `./`/`../`); phase-180 paragraphs otherwise accurate. - Notable: image allowlist `.{0,2}/` is broader than the overview's `^\.{1,2}/` but is what task 02 explicitly specifies and the docstring documents — not a deviation from the tasks; SVG sizing deliberately deferred to phase 181. - Next pending phase: `181_svg_document_preview`.	2026-10-14 16:03:36 -04:00
ducoterra	3d82a72b6f	phase: 179_git_clone_server_freeze ... All gates green; working tree holds exactly the phase's changes for the harness to commit. ## Phase 179 — Final verification report - **Verified (all 3 tasks already complete in `complete/`)**: repro + CONFIRMED verdict, `asyncio.to_thread` fix, dedicated E2E suite. - `app/api/sync.py::_run_sync`: both git ops (`clone_or_pull`, `file_commit_dates`) now `await asyncio.to_thread(...)`; phase-134 boundary note + module docstring document worker-thread-runs-to-completion and the A3 DB-calls-stay-on-loop note. - **Tests / lint / coverage** (full suite 100% green): - `uv run pytest tests/integration/test_sync_git_freeze.py -v` → **4 passed** (post-fix probe <1.5 s during 3 s stub) - `uv run pytest tests/e2e/test_sync_git_freeze.py -v --no-cov` → **2 passed in 25.65 s in isolation** (wall guard 120 s holds) - `uv run pytest --cov=app --cov-report=term-missing` → **4173 passed**, `app/` coverage **99%** (`app/api/sync.py` 100%) - `uv run ruff check .` → All checks passed; `uv run pyright` → **0 errors** - **Completion criteria**: ① integration probe green + verdict (CONFIRMED, mechanism, measured 3.04 s→0.003 s) in docstring — **met**; ② off-loop git ops + boundary/A3 notes — **met**; ③ full suite green, coverage 99% >90%, ruff+pyright clean — **met**; ④ E2E green in isolation (responsive-poll + cancel-during-clone contracts) — **met**; ⑤ atomic commit + move to `complete/` — **harness-owned** (pipeline rule overrides per-phase self-commit; all changes staged-ready in the working tree). - **Documentation**: full README (1526 l) + AGENTS.md review — phase-179 bullets present and accurate (verified against fixture constants, `.env.example` fully covered by the config reference, pages table matches `app/main.py` shell routes, quick-reference commands/artifacts exist); **consistent — no further changes needed**. - **Notable**: task-03 pipeline sessions died on context overflow but their harness validation passed; this pass independently re-ran every gate to confirm. No live infra touched; no git index commands run. - **Next pending phase**: `180_markdown_inline_links_images`.	2026-10-14 13:06:39 -04:00
ducoterra	2b57180998	chore(repo): remove stray image.png screenshot artifact ... The root-level image.png was committed accidentally during phase 160 (tool budget telemetry) as a bug-report screenshot. It is not served or referenced as an asset by the app; the remaining "image.png" mentions in tests and comments only describe the owner's screenshot in prose, so removing the file is safe. LLM-Generated: true	2026-10-14 10:41:04 -04:00
ducoterra	76887639f3	docs(phases): add phase 182 (verbatim file display) ... Answers to "show me my pi.dev config" re-type file contents from context, so the code block in the answer can differ from the indexed file by a character and cannot be trusted for copy-paste — the owner opens the source bubble and ignores the answer. Phase 182 makes the server the only party that supplies bytes: - show_text(path, offset?, limit?), the display sibling of show_image, slices documents.content and hands the same bytes back to the model with a "do not retype" instruction - inline ```bor source/path 12-40 locator fences place a resolved block anywhere in the prose; the model's fence body is never painted, and an unresolvable locator says so instead of showing guessed text - the bytes ride inline in the done frame's additive answer_text array and persist in the saved chat, so restore and the shared page match - line numbers are always the server's resolved extent (overshoot clamps, past-the-end refuses to the model), which removes the "did the model invent those numbers?" problem entirely - a Copy button on every answer code block, a VERBATIM badge only on server-resolved ones - gated by BOR_ANSWER_TEXT with per-block/per-answer budgets; with the flag off every frame, record and byte budget is exactly pre-phase Overview plus eight tasks, each with its own test gate; the phase E2E runs in isolation and asserts the clipboard content equals the stored bytes. Run 180 first — both touch markdown.js. LLM-Generated: true	2026-10-14 10:33:06 -04:00
ducoterra	50658580e9	chore(agent): phase roadmap from TODO.md, 2 phases ... Convert the 3 open TODO.md items into sequential phases appended to the existing pipeline (Protocol B, numbered after 179): - 180_markdown_inline_links_images: the shared escape-first renderer gains the [text](url) link transform, the  image transform, and the ####-###### heading levels, with CSS and the dedicated Playwright suite. - 181_svg_document_preview: SVGs index as vector image documents (text extracted from title/desc/text, no vision call), are served as sandboxed image/svg+xml, and preview as graphics instead of raw XML. TODO.md is cleared; its items now live in .agents/phases/. LLM-Generated: true	2026-10-14 09:54:01 -04:00
ducoterra	dad54a2854	chore(agent): phase roadmap from TODO.md (179 git clone server freeze) ... TODO L3 (a long git clone seems to freeze the server) converted to phase 179: deterministic in-process repro + verdict, the asyncio.to_thread fix for the sync's git ops, and the dedicated Playwright E2E suite. TODO.md cleared (items now live in .agents/phases/). LLM-Generated: true	2026-10-12 09:27:58 -04:00
ducoterra	149e753952	phase: 178_split_thinking_levels ... ## Phase 178 — final verification pass: 100% green **Verified (all 5 tasks complete in `complete/178_split_thinking_levels/`):** - `config.py` rename (`llm_chat_thinking_level` default `low`) + new `llm_summary_thinking_level` (default `""`); two `CATALOG` rows; `.env.example` replaced; no stale old-key references (only intentional negative pins in tests) - Wire split: `chat_stream()` → chat level, one-shot `chat()` → summary level (absent `extra_body` when empty); per-turn line reads chat level only **Gates:** - `uv run pytest -k "config and thinking" -v` → 7 passed (defaults + env overrides both knobs) - `uv run pytest` (unit + integration) → 4170 tests, exit 0; `--cov=app` → **99%** (>90% ✓) - `uv run ruff check .` clean; `uv run pyright` clean - `uv run pytest tests/e2e/test_split_thinking_levels.py -v --no-cov` → 3 passed in isolation - `test_admin_settings_panel.py` + `test_admin_settings_layout.py` → 17 passed in isolation **Completion criteria:** all 6 test/doc criteria ✅ (admin GET lists both keys, old key gone — integration + E2E pins); commit + phase-dir move = harness's job. **Documentation:** README.md — both new env vars correctly documented in the LLM (aipi) table with defaults/wire-mapping/off-rule, defaults match `config.py`, all `.env.example` vars covered: verified consistent, no changes needed. AGENTS.md — all referenced files/commands verified to exist, no phase-178 impact (no UI code change, A4): verified consistent, no changes needed. **Decisions:** none required — no live changes made (E2E booted its own app subprocess against the existing DB). **Next pending phase:** none — 178 is the last phase in `todo/`.	2026-10-11 23:38:18 -04:00
ducoterra	c6223c93dc	chore(agent): phase roadmap from TODO.md (178 split thinking levels) ... LLM-Generated: true	2026-10-11 20:56:16 -04:00
ducoterra	36eddce672	phase: 177_themed_favicon ... Everything is verified. Final report: ## Phase 177 — Themed favicon: completion pass (all tasks pre-done, verified end-to-end) **Verified (no code fixes needed — implementation matched the design D1–D4 exactly):** - `theming.favicon_svg()` pure renderer + golden byte-identical pin; `GET/HEAD /favicon.svg` route (no-cache, `image/svg+xml`, built-in 200 fallback on DB blip, routes-first before static mount); 5 templates → bare `href="/favicon.svg"`, static file deleted (Containerfile cp removed); Theme-tab `data:` live preview with 4 restore points; JS↔server mirror pins. **Tests / lint / coverage (all green):** - `uv run pytest --cov=app --cov-report=term-missing` → 4161 passed, `app/` 99% (>90% gate) - `uv run ruff check .` → clean; `uv run pyright` → 0 errors - `uv run pytest tests/e2e/test_themed_favicon.py -v --no-cov` (isolated) → 6 passed - `test_theme_save_and_coverage.py` (92) + `test_theme_semantic_completion.py` (93), isolated → 3 + 8 passed **Completion criteria:** all met — default golden bytes/headers; themed roles + `#bor-theme` non-regression; DB-failure 200 fallback; 5 bare links + `/assets/favicon.svg` 404 + browser rendering; live-preview data: repaint + Save/Reset/re-show restore; gates green; E2E suites green in isolation. Commit: harness commits atomically (overrides AGENTS rule 8 — no git commands run). **Documentation:** README.md verified consistent in full (the phase's favicon paragraph is accurate; all commands, env vars, routes, ports, scripts cross-checked) — no changes needed. AGENTS.md verified consistent — no changes needed. **Notable:** `image-1.png` (owner's TODO screenshot, referenced by phase 176's overview) sits untracked at the repo root — pre-existing, explicitly out of scope per the phase-176 report; left untouched. **Next pending phase:** none — 177 was the last; TODO.md is cleared.	2026-10-11 15:33:39 -04:00
ducoterra	dd119d534a	phase: 176_mobile_settings_value_width ... All documentation claims verify against the code. Everything is green — final verification complete. ## Phase 176 — Final Verification Report - **Verified (all 3 tasks in `complete/`):** the mobile Value-column fix is in the working tree — `frontend/index.html` L1602 carries `class="settings-value-th"`; `frontend/assets/styles.css` has exactly two new rules inside the `@media (max-width: 640px)` block: `.settings-table { min-width: 720px }` and `.settings-value-cell, .settings-value-th { min-width: calc(13rem + 2rem) }`; `settings.js` + `app/` byte-unchanged (diff = index.html + styles.css + unit test only). - **Documented deviation (flagged in task-03 report, not silent):** spec's `min-width: 13rem` on the border-box cell left the control at 176px (< the 192px A3 pin); executor corrected the cell to `calc(13rem + 2rem)` so the control (100% of content) lands at exactly 13rem ≈ 208px — the A2 lock intent preserved, unit pin + CSS comment updated to match. - **Tests/lint/coverage (exact commands, all green):** `uv run pytest --cov=app` → **4138 passed**, `app/` coverage **99%** (>90% ✓); `uv run ruff check .` → clean; `uv run pyright` → 0 errors, 0 warnings. - **Completion criteria:** 375px controls ≥ 192px — ✅ (E2E `test_mobile_value_inputs_are_usable_width`); card scrolls / page doesn't overflow at 375px — ✅ (`test_mobile_table_still_scrolls_and_page_does_not_overflow`); 1440px media query inert — ✅ (`test_desktop_value_width_is_unchanged`); tab order + zero external requests — ✅; phase E2E isolated — ✅ 4/4; phase 171 isolated — ✅ 5/5; phase 168 isolated — ✅ 12/12; unit pins — ✅ 17/17; commit/move — the harness commits; phase dir already in `complete/`. - **Documentation:** README.md and AGENTS.md reviewed in full — every claim spot-checked against code (E2E ports 8123/8901, defaults `BOR_COMPRESS_MIN_BYTES=860` / `BOR_LOG_LARGE_RESPONSE_BYTES=65536`, audit budget 262144, `.cell-clip`, `.bubble:empty`, `min(70vh, 64rem)`, aria-pressed toggle, CDN integration test, `.gitignore` entries, all referenced scripts/routes) — verified consistent, no changes needed. - **Notable:** `image-1.png` (owner's TODO screenshot, referenced by the phase overview) sits untracked in the tree — left alone; not part of the phase's commit scope. - **Next pending phase:** `177_themed_favicon`.	2026-10-11 13:23:04 -04:00
ducoterra	2a5df7cb31	chore(agent): phase roadmap from TODO.md (177 themed favicon) ... LLM-Generated: true	2026-10-11 11:44:07 -04:00
ducoterra	bd271a6f52	chore(agent): phase roadmap from TODO.md (176 mobile settings value width) ... The single TODO item (mobile settings Value inputs impossibly small) becomes phase 176_mobile_settings_value_width: 3 tasks (CSS fix in the <=640px block, unit pins, dedicated E2E suite) with owner-locked A1-A3. Protocol B append - PLAN.md and AGENTS.md untouched. LLM-Generated: true	2026-10-11 10:28:54 -04:00
ducoterra	375169bbfc	phase: 175_history_pagination ... All criteria verified. This pass found no defects — the phase was fully implemented by prior task runs, and every gate is green. **Phase 175 final verification pass — report** - Verified tasks 01–03 implementation in-tree: `list_chats` `?limit=` (25, 1–100) / `?offset=` + `func.count` `total`; `SavedChatList.total` required; `#history-pager` below `#history-table-wrap` (hidden default, aria-labels, aria-hidden SVGs); `history.js` `PAGE_SIZE=25`/offset state, parameterized fetch, `updatePager`, refresh-keeps-current-page; CSS pill union + ≤640px block. No code changes were needed. - Full suite: `uv run pytest --cov=app --cov-report=term-missing` → **exit 0, TOTAL 99%** (>90% gate). - `uv run ruff check .` → all checks passed; `uv run pyright` → 0 errors, 0 warnings. - Phase E2E in isolation: `uv run pytest tests/e2e/test_history_pagination.py -v --no-cov` → **9 passed** (page 1-of-2 / 2-of-2 walk, replace-not-append, refresh-on-page-2, delete-to-empty + single-page hide, anonymous no-fetch, 375px mobile, a11y/no-CDN). - Regression set, each in isolation: test_chat_history 5✓, test_history_page_width 5✓, test_share_chat 4✓, test_stale_saved_chats 3✓, test_history_copy 1✓; integration `test_chats_api.py` green (incl. updated `test_list_empty` two-key pin and all five new pagination pins). - Completion criteria: all nine boxes satisfied (API slice/422/honest-total pins ✓; E2E walk + status lines ✓; refresh/delete/hide ✓; anonymous gate ✓; mobile ✓; gates ✓; E2E + regression ✓; docs ✓; commit/phase-move is the harness's). - Documentation: README.md reviewed in full — the saved-chats section already carries the `?limit=`/`?offset=`/`total` contract from this phase; all 31 `.env.example` vars documented; AGENTS.md verified accurate. **Consistent — no changes needed.** - Deviations: none. No defects found in previously completed work. - Next pending phase: none — 175 is the only entry in `todo/`.	2026-10-11 04:12:53 -04:00
ducoterra	938d6cf09d	phase: 174_git_sources_card_rhythm ... All checks pass. Both docs verified consistent. Final state — no live-infrastructure changes were needed (pure CSS fix; verification ran against the already-running local dev DB). **Phase 174 final verification pass — report** - **Verified (no new work needed; both tasks already complete in `complete/`):** the single `#git-sources-content { display:flex; flex-direction:column; gap:1.25rem }` rule in `frontend/assets/styles.css` (with the phase-174 root-cause comment), `.git-sources-shell` untouched, the 4-test unit pin module, and the 4-test Playwright suite. - **Full suite:** `uv run pytest --cov=app --cov-report=term-missing` → **4116 passed, 99% `app/` coverage** (gate >90% ✓). - **Lint/types:** `uv run ruff check .` → clean; `uv run pyright` → 0 errors, 0 warnings. - **Dedicated E2E in isolation:** `uv run pytest tests/e2e/test_git_sources_card_rhythm.py -v --no-cov` → **4 passed** (1440px + 375px bounding-box rhythm pins 20±2px, hidden-children + revealed-joins-rhythm, anonymous gate, a11y/no-CDN). - **Regression set, each in isolation:** `test_git_sources_admin.py` **6 passed**, `test_archive_upload_sources.py` **5 passed**, `test_git_source_dates.py` **4 passed**. - **Completion criteria:** cards stack with uniform ≈20px gap at both viewports ✓; hidden children stay hidden / gate+content flip intact ✓; ≤640px forms column-stack + table scrolls inside its card (no page-level h-scroll) ✓; full suite + coverage + ruff + pyright ✓; dedicated + regression E2E suites ✓. - **Documentation:** README.md reviewed in full (every `.env.example` var documented; all documented routes/pages/endpoints exist; every config default cross-checked against `app/config.py`; payload-limit table, ports 8123/8901, Containerfile/compose/entrypoint claims all match) — **verified consistent, no changes needed**. AGENTS.md verified (all referenced files/sections exist: PLAN §2/§7.1/§7.4/§9, `response_budget.py`, `debugging.py` conditional import, `.agents/` tracked + gitignore rules, `commit.gpgsign=false`, phase-pinned CSS classes) — **verified consistent, no changes needed**. - **Notable:** commit + phase-dir move are handled by the harness per pipeline rules (no git history/index touched by this pass); no live-infrastructure changes were required. - **Next pending phase:** `175_history_pagination` (in `todo/`).	2026-10-11 01:49:49 -04:00
ducoterra	da441ea799	chore(agent): phase roadmap from TODO.md, phase 175 (history pagination) ... LLM-Generated: true	2026-10-11 00:19:04 -04:00
ducoterra	a86caec821	phase: 173_docs_push_creds_split ... All gates green. Final report: **Phase 173 — final verification pass (all tasks already complete in `complete/`)** - Verified the full implementation is in the working tree: `docs_user`/`docs_token` settings + catalogue rows (task 01), `docs_repo` PUT 422 guard + `docs_token` write-only pin (task 02), `run_git(env)` + `push_document(user, token)` credential env (task 03), `settings_migrate.py` wired into `create_app()` (task 04), E2E suite (task 05). - **Completion criteria:** 1. GET `/api/admin/settings` lists `docs_user` (plain) + `docs_token` (secret, `value=null`), token never in any body — ✅ `test_docs_token_is_write_only_masked_end_to_end` + E2E sentinel-absent-from-DOM 2. PUT `docs_repo` with `://user:pass@` → 422 naming the fields; clean URL passes — ✅ integration + E2E UI-side 3. Token set → `GIT_CURL_USERNAME`/`GIT_CURL_PASSWORD`/`GIT_TERMINAL_PROMPT=0` on every git step; empty → `env=None` — ✅ mocked-git unit tests 4. Legacy env split once at startup, idempotent, one INFO line, `.env` untouched — ✅ `test_settings_migrate.py` (4 shapes) + `test_docs_push_migrate.py` 5. Full suite green, coverage >90%, lint clean — ✅ 6. E2E isolated: `test_docs_push_creds.py` 4/4; regression set (panel + layout + response_to_docs) 21/21 — ✅ 7. Commit + phase move — harness's job (per instructions, not mine). 8. README/AGENTS consistent — ✅ (below) - Tests/lint: `uv run pytest` exit 0 (4112 passed) · `uv run pytest --cov=app --cov-report=term-missing` TOTAL 99% · `uv run ruff check .` clean · `uv run pyright` 0 errors - Docs: README.md (incl. Docs-push config section, guard/migration paragraph, `.env.example` block) and AGENTS.md verified consistent in full; fixed two stale docstrings in `app/config.py` + `app/core/settings_catalog.py` (`is_set` → the API's actual `has_value` field). - No live-infrastructure changes (no live step in this phase). No next pending phase — `todo/` held only 173.	2026-10-10 16:47:39 -04:00
ducoterra	f27106a638	phase: 172_thinking_level ... All verification complete. Final report: **Phase 172 final verification pass — all tasks (01–05) were already complete; verified the whole phase, no code fixes needed.** - **Verified implementation:** `Settings.llm_thinking_level: str = "low"` + `CATALOG` row (`LLM (aipi)` / "Thinking level", plain: not secret/restart/overridable-exempt) + `.env.example` line under `BOR_LLM_CHAT_MODEL` + README table row; `_thinking_extra_body()` → `reasoning_effort` via `extra_body` on `chat()` + `chat_stream()` when trimmed-non-empty, key absent (byte-identical) when empty, embeddings untouched; per-turn line gains `thinking=<value>` (`-` when empty) before `thinking_chars`. - **Tests/lint/coverage (all green):** `uv run pytest` → 4084 passed · `uv run pytest --cov=app --cov-report=term-missing` → 4084 passed, `app/` **99%** (>90%) · `uv run ruff check .` → All checks passed · `uv run pyright` → 0 errors, 0 warnings. - **Completion criteria:** (1) `pytest -k "config and thinking"` 4 passed + `.env.example` grep ✓ (2) live `GET /api/admin/settings` curl shows the row (str, `low`, `default`) + integration PUT/DELETE round-trip ✓ (3) 9 mocked-client unit tests assert `extra_body` present/absent ✓ (4) log-line tests assert `low`/`high`/`-`/whitespace ✓ (5) suite + coverage + lint ✓ (6) `test_thinking_level.py` 3/3 in isolation; `test_admin_settings_panel.py` 12/12; `test_admin_settings_layout.py` 5/5 ✓ (7) atomic commit + phase move = the harness's job (task files already in `complete/`; I ran no git index/history commands). - **Documentation:** README.md reviewed in full — verified consistent (env table complete vs `.env.example`, catalog restart/non-overridable claims re-verified at runtime); AGENTS.md reviewed in full — verified consistent (no rule affected, A5 = no UI change). No changes needed. **Flag (not fixable here):** PLAN.md §9's per-turn-line spec predates the phase-172 `thinking=` field; PLAN.md is off-limits per protocol. - **Next pending phase:** none — `todo/` contains only phase 172 (the harness moves it on this pass's success).	2026-10-10 13:19:10 -04:00
ducoterra	b21b05eaee	chore(agent): phase roadmap from TODO.md, phase 172 (thinking level) ... LLM-Generated: true	2026-10-10 10:28:46 -04:00
ducoterra	e9ae6e2ba3	phase: 171_admin_settings_layout ... Expected state: only `00_phase.md` remains in `todo/` (the harness moves it on success; I must not touch it). All verification is complete. --- **Phase 171 final verification pass — report** - **Verified (all 4 tasks complete, CSS-only diff confirmed byte-exact to contract):** `#settings-content` flex column + `gap: 1.25rem` (tasks 01); `.settings-group-row th` band `--brand-soft` + 700 + `--line` top hairline (02); `#settings-save:disabled` `cursor: default` (03); new phase-dedicated Playwright suite (04). Mobile media queries and `settings.js`/`app/` byte-untouched, as pinned. - **Gates:** `uv run pytest --cov=app --cov-report=term-missing` → **4069 passed, app/ 99%** (>90%); `uv run ruff check .` → clean; `uv run pyright` → **0 errors, 0 warnings**. - **E2E (in isolation):** `test_admin_settings_layout.py` → **5 passed**; `test_admin_settings_panel.py` (phase 168) → **12 passed**; `test_wide_desktop_column.py` → **3 passed**. - **Completion criteria:** search/table no-intersection + gapped action row at 1440/375 px ✅ · distinct group bands (bg ≠ card, weight 700, ≥1px top hairline) ✅ · disabled Save `cursor: default` with §7.4 dim + aria-busy lifecycle intact ✅ · full suite + coverage + lint ✅ · all three E2E suites isolated ✅ · atomic commit + dir move = **harness's job** (task files already in `complete/`; per protocol I left every change uncommitted in the working tree). - **Documentation:** README.md (all 1487 lines) and AGENTS.md (all 80 lines) fully reviewed — every config default cross-checked vs `app/config.py`, all quick-reference commands verified against existing files, AGENTS.md rules/contracts verified vs code — **verified consistent, no changes needed** (phase 171 is CSS-only: no setup/command/env/API impact). - **Notable:** one phase-168 test failed on the first isolated run solely because an unrelated `undercooked` dev server held port 8124 (the suite's `DISABLED_PORT`); re-ran with the suite's built-in `E2E_APP_PORT=8300` override — no code change, foreign process untouched. Post-run DB state clean (`app_settings` 0, `ui_settings` 0, e2e tokens 0). - **Next pending phase:** none — phase 171 was the last `todo/` phase.	2026-10-10 04:45:34 -04:00
ducoterra	c4f098d0c0	phase: 170_edit_bubble_sizing ... All verification complete. Final report: **Phase 170 — final verification pass (all 3 tasks were in `complete/`):** **Verified implemented:** - Editor renders inside the bubble: `bubble.replaceChildren(form)`, `display:none` rule deleted, `form.style.minWidth` seeded with pre-edit width, `restoreBubble()` (markdown + image re-prepend) before `closeEditor()` on Cancel/Escape, `closeEditor()` reordered before submit re-render - Label: `editSaveBtn.textContent = "Send"` (app.js L1241) **Gates (all 100% green):** - `uv run pytest` → 4066 passed - `uv run pytest --cov=app --cov-report=term-missing` → 99% on `app/` (gate >90%) - `uv run ruff check . && uv run pyright` → clean (0 errors, 0 warnings) - `uv run pytest tests/e2e/test_edit_bubble_sizing.py -v --no-cov` (in isolation) → 6/6 passed - Regression set in isolation: `test_edit_and_resend.py` 7✓, `test_retry_answer.py` 4✓, `test_failed_turn_retry.py` 4✓, `test_chat_persistence.py` 4✓ **Completion criteria:** in-bubble editor + width pin ✅ · "Send" label + cancel restore + trim re-ask + "Question too long" driver case ✅ · suite/coverage/lint ✅ · E2E + regression isolation ✅ · phase dir moved to `complete/` ✅ (atomic commit is the harness's to make — changes left in the working tree per protocol) **Documentation:** README.md reviewed in full — edit section already aligned to phase 170 (in-bubble editor + "Send"), pages table matches actual routes, all 29 `.env.example` vars documented, setup commands accurate; AGENTS.md reviewed — all referenced files/commands exist. Both verified consistent — no changes needed. **Notable decisions:** none — verification pass only, no code changes required. **Next pending phase:** `171_admin_settings_layout`	2026-10-10 03:25:40 -04:00
ducoterra	1200437bf8	phase: 168_admin_settings_panel ... **Phase 168 — Admin Settings panel — final verification: PASS** 1. **Implemented/verified:** `/settings.html` (admin-only) with the 75-field catalogue (`app/core/settings_catalog.py`), DB-over-env overrides in Postgres (`app_settings`, migration 0028 at head, `settings_overlay.py` resolver, `app/api/admin_settings.py` — 4 admin-only routes), live-apply on save with no restart + restart-required badges, Reset/Clear all, write-only secrets, `.env`-never-written, `BOR_SETTINGS_DB=0` kill switch. 2. **Phase E2E: 12/12** — run with `E2E_APP_PORT=8200` (ports 8123/8124 are held by an unrelated "undercooked" project; no process killed, no code change — the documented env override). 3. **Regression set: all 7 suites green in isolation** (theme tab, API tokens, configurable brand, global tuning, admin auth, cache busting, wide desktop column — 38 tests). 4. **Full suite: unit+integration exit 0 (4066 passed), app/ coverage 99%** (gate >90%); **ruff clean, pyright 0 errors / 0 warnings.** 5. **Log contract (rule 10) verified live:** per-turn + per-response byte-budget lines present; settings write lines carry key + action, **never the value**. 6. **Byte-budget audit: all endpoints under the 262,144 B budget**; settings catalogue 23,513 B (gzip 3,326). 7. **Defect fixed (one):** criterion 5 had no integration pin — added `test_bad_row_inserted_directly_never_bricks_boot` to `tests/integration/test_admin_settings_api.py` (malformed row inserted directly → fresh `create_app()` boots, row skipped with logged reason, rest of table applies, `/api/health` 200) — 12/12 green. 8. **Docs pass:** `README.md` and `AGENTS.md` reviewed in full — both consistent with the as-built feature (Settings page table, Settings section, Configuration-reference note, `.env.example` block); **no changes required**. 9. **Cleanup:** audit app killed (by PID); `app_settings` left empty (0 rows); all changes left in the working tree (no commit, per protocol). 10. **Completion criteria:** all 7 checkboxes verified green (criterion 7's commit is the harness's). 11. **Next pending phase:** `170_edit_bubble_sizing`.	2026-10-10 01:05:14 -04:00
ducoterra	abe7388dda	docs(phases): convert TODO.md L3-L4 into phases 170-171 (edit bubble, settings layout) ... 170_edit_bubble_sizing — the edit form renders inside the user bubble (same box, no shrink) and its submit label reads "Send", not "Save" (TODO.md L3). 171_admin_settings_layout — settings page CSS fixes: #settings-content vertical rhythm (search/table overlap + smushed action row), distinct group bands, a properly disabled Save cursor (TODO.md L4). Numbering note: 169 (embedding generation migration) was created, executed and abandoned before this conversion; its number is not reused. TODO.md is cleared — the items now live in .agents/phases/. LLM-Generated: true	2026-10-09 23:42:15 -04:00
ducoterra	542e568d25	docs(agent): record the reverted embed embedding benchmark ... The embed alias was reverted to the previous backing model and re-benchmarked over 3 runs. All gates pass and the numbers reproduce the original baseline exactly: 768 dims, cosine margin 0.283 (quality 56) versus the 0.217 measured on the swapped-in model, with throughput back to 109.7-123.3 vec/s. The margin returning to the identical 0.283 confirms the locked semantic-pair corpus is a reliable fingerprint for this endpoint, and a raw-vector probe shows the two models are genuinely different spaces despite both being unit-normalized 768-dim (max component diff 0.035 on the same input). Any content embedded while the swapped-in model was live is therefore in an incompatible space and needs re-embedding. LLM-Generated: true	2026-10-09 12:41:38 -04:00
ducoterra	a88a5a3713	docs(agent): re-run the embed embedding benchmark (speed variance) ... Second 3-run pass against the re-pointed embed endpoint the same day. Dimension stays 768/768 and the cosine margin reproduces exactly at 0.217 across all passes, confirming both the model's determinism and that the margin drop from the 0.283 baseline is a real effect of the model swap. Throughput measured 59.1/61.4/57.4 vec/s against 35.5/35.6 earlier, a 1.7x swing on an unchanged model, which shows the speed check measures one batched request's end-to-end wall time (TLS setup, network, server queueing) rather than stable throughput - note it gates on NaN/Inf only, never on rate. LLM-Generated: true	2026-10-09 12:38:27 -04:00
ducoterra	05f7d0645e	docs(phases): add phase 169 (embedding generation stamp + in-place re-embed) and the migrate-embed-model skill ... An embedding-model swap that keeps the dimension is invisible on this app: nothing records which model made a vector, EmbeddingDimensionError cannot fire at 768 -> 768, and a re-sync re-embeds nothing because the documents.file_hash fast path returns with zero embeds - so questions embed in one geometry and chunks score in another with no error anywhere. The owner's upgrade (embedding gemma -> embedding gemma 2) is exactly that case. Phase 169, seven tasks: chunks.embedding_model (reversible migration 0029, nullable, never backfilled - NULL means unknown by design), one write helper so every vector write stamps its generation, a generation_report() that turns the column into counts plus a stale verdict logged after every sync, scripts/reembed_embeddings.py with --compare (cosine agreement against the stored vectors, so 'are they compatible?' is measured instead of guessed) / --stamp-only / --apply (per-batch commits, resumable, never a NULL embedding, never a sources_meta bump), an admin-only GET /api/admin/embeddings, a read-only card in the phase-168 Settings view, and the dedicated Playwright file plus the README runbook. Owner-locked during authoring: detection only - retrieval never filters by generation (a WHERE embedding_model predicate would silently deflect every turn mid-backfill), comparability bands COMPATIBLE >= 0.995 for the float4 round trip, a re-embed is not a KB change so saved chats stay fresh, and no new Settings field so the phase-168 catalog pin is untouched. .agents/skills/migrate-embed-model is the operator twin: probe and benchmark the new model, measure comparability as its own process without disturbing the running app, back up and migrate production (idle check, pg_dump off-box, alembic, flip then re-embed with the same env), then re-tune relevance_threshold and the two floors against the retrieval battery - after the corpus is on one generation, and with the phase-168 warning that an app_settings row beats .env - and smoke-test the result. LLM-Generated: true	2026-10-09 12:35:21 -04:00
ducoterra	8fac4e64d4	docs(agent): record the re-pointed embed embedding benchmark ... The aipi `embed` endpoint was re-pointed to a new backing model and was re-benchmarked over 3 runs. All three gates pass: output stays 768-dim (matching BOR_EMBEDDING_DIM, so no schema/vector change is needed), the similar-vs-dissimilar cosine margin is 0.217 (gate >= 0.05) with no NaN/Inf vectors, and throughput is 35.6 vec/s on the 50-vector probe. Versus the previous embed baseline (margin 0.283, 93.8 vec/s) the margin tightens and throughput drops ~2.6x, both consistent with a model swap behind the same alias. Vectors are unit-normalized and deterministic. Note: same dimension on a different model means any KB indexed under the old backing model holds stale vectors and needs a re-embed; the local dev DB is empty, so the phase 119/162 retrieval battery was not runnable here. LLM-Generated: true	2026-10-09 12:23:55 -04:00
ducoterra	a12fdcdf0a	Move phase 167 audit to complete	2026-10-09 10:27:51 -04:00
ducoterra	a2b2f283fd	docs(phases): convert TODO.md L3 into phase 168 (admin settings panel) ... One owner item, one phase: an admin-only Settings view that writes any BOR_* setting to the database, resolves DB-over-env inside get_settings(), and applies on Save without a restart. Six tasks: the app_settings table + reversible migration 0028, the overlay resolver and field catalog, the live-apply reset of the two in-process singletons (the shared LLMClient and the chat semaphore), the admin-only /api/admin/settings surface, the shell's eighth view, and the dedicated Playwright suite. Owner-locked during authoring: DB-only persistence (.env is never written), the overlay lives inside get_settings() behind the BOR_SETTINGS_DB kill switch, database_url and embedding_dim are not DB-overridable, boot-wired settings stay editable with a "restart required" badge, secrets are masked and write-only, and every write is validated by the real Settings validators while an unusable stored row is skipped at read so boot can never brick. Protocol B append: PLAN.md and AGENTS.md are untouched, so PLAN's roadmap table does not list phase 168 and its "get_settings() is lru_cache'd" note in 13 is extended (cached env base + DB overlay + invalidation). TODO.md's L3 item is now cleared - it lives in this phase directory. LLM-Generated: true	2026-10-09 10:10:13 -04:00
ducoterra	2ac37455f0	phase: 167_api_payload_diet ... All gates green. Final report: **Verified (phase 167 final pass — all 6 tasks already in `complete/`)** - Live re-measure of the headline criterion on the **1,000-doc live-replica corpus** (restored `data/bor_live_kb_replica.dump.sql` into a scratch DB `bor_audit`, alembic 0011→0027, dropped after; the shared dev DB was never touched): `GET /api/docs/tree` default depth=1 = **8,474 identity → 1,128 B with `Content-Encoding: gzip`** (< 40 KB bar; ~2 MB defect fixed), repeat load **304 / 0 bytes**; depth=8 265,147→23,515; node drill 20,844→1,065; `/api/docs` 246,366→45,104; `/api/documents/content` 892,124→60,776 (`LOOK`, accepted-with-why). Reproduces `AUDIT.md` to within 1 byte. - Transport contracts proven live: `POST /api/chat` **no** `Content-Encoding` + frames arriving live + budget line `… enc=identity duration_ms=7380 stream=1`; HTML still `no-cache` with the `?v=` rewrite (and gzipped); A20 headers on 200 **and** 304; ETag identical across identity/gzip; `depth=0|9|abc`→422; anonymous tree/node→403; unknown folder/source→404 `unknown node`. **Gates (all 100% green)** - `uv run pytest` → **3980 passed**; `uv run pytest --cov=app --cov-report=term-missing` → **TOTAL 99%** (`compression.py`, `http_cache.py`, `response_budget.py` 100%; `api/docs.py` 99%, one defensive dedupe line). - `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors. - Phase + regression E2E **in isolation** (`--junitxml`, exit codes): `test_kb_tree_lazy_load` 11, `test_kb_tree` 8, `test_kb_tree_nav` 4, `test_navbar_refresh` 7, `test_document_dates` 6, `test_git_source_dates` 4, `test_sync_summary_visibility` 3, `test_table_ux_polish` 6, `test_sources_midstream_bug` 6, `test_ls_tree_drilldown` 3, `test_smoke` 3 — **0 failures/errors** (the earlier `-q -q` run had simply suppressed pytest's summary line). **Documentation** — README.md + AGENTS.md reviewed in full (1,436 / 80 lines): - Fixed (pre-existing, phase-167-exposed): README *Caching & deploys* claimed "One Starlette middleware (`app/core/caching.py`) applies the rule" while the section now describes three transport layers → rewritten to name caching/compression/http_cache, the real outermost→innermost order, and why `bytes=` is uncompressed. - AGENTS.md rule 5 (UI Structure Check) gained the phase-167 clause: a lazily-drilled level keeps the current level rendered, its in-flight `role="status"` / `role="alert"`+Retry row lives in the same bounded scroll panel, and stat cards read server `totals` (never a walk of a depth-limited tree). - Cross-checked and consistent: every `BOR_*` in `.env.example` is in the README table, every `Settings` field is documented, all 15 README-cited API routes exist in the app, no stale "one fetch / drill client-side" claim remains anywhere. **Notable decisions / deviations** - `compression.py` adds a documented `_RebufferSmallResponses` seam beyond the D1 sketch (the caching layer's `BaseHTTPMiddleware` re-framing otherwise defeats Starlette's `minimum_size` exemption and inflates tiny responses) — integration-pinned, math still Starlette's. - A node-route **404 = vanished folder → honest reset to top level** (per `00_phase.md` D4/D6), not task-06's "alert + Retry"; 500 shows alert+Retry with the level preserved — both pinned, nothing weakened. - Retrieval battery not measurable (shared E2E DB holds no corpus), but `git diff --name-only -- app/rag` is empty, so retrieval is unchanged by construction. `AUDIT.md` left byte-identical (it lives under `todo/`, off-limits to this pass); no git index/history commands run. **Next pending phase:** none — `167_api_payload_diet` is the only entry in `.agents/phases/todo/`; the harness moves it to `complete/` and commits.	2026-10-08 21:23:49 -04:00
ducoterra	ab9391d019	phase: 166_hide_empty_answer_bubble ... **Phase 166 — final verification pass: green.** All 3 task files already in `complete/`, so this was verification + defect/doc fixing. - **Verified:** `.msg .bubble:empty { display: none; }` exists once in the Messages block with provenance; `frontend/` diff is styles.css only (**no app.js change**); `tests/unit/test_no_empty_answer_bubble.py` 26 pins pass; phase-158/161 anchor pins (thinking_timeline + tool_states + edit_message) **75 passed**. - **Phase E2E in isolation:** `uv run pytest tests/e2e/test_no_empty_box.py --no-cov` → **5 passed**. Mutation check (rule removed) → 2 failures, so the suite genuinely pins the defect. - **Regression set, isolated:** thinking_timeline 6 · turn_progress_loader 3 · chat_history 5 · share_chat 4 · save_share_ux 5 · failed_turn_retry 4 · chat_answer_clusters 4 · chat_error_honesty 4 → all pass. - **Full gates:** `uv run pytest --cov=app --cov-report=term-missing` → **3880 passed, app/ 99%** (gate >90%); `uv run ruff check .` → clean; `uv run pyright` → **0 errors**. - **Whole E2E tree swept file-by-file (150 files, own pytest process each).** 4 suites were broken by *earlier* phases; fixed and re-run green: - `test_kb_tree`, `test_sync_summary_visibility`, `test_folder_summary_voice` — `td:nth-child(4) span` became a strict-mode violation when phase 156 wrapped the Edit label in `.cell-clip` → scoped to `span.kb-desc-text`. - `test_search_tool_scope` — pinned the pre-`690fd98` per-run `<summary>`/`open` shape → re-pinned to the ONE `details.reasoning` container + `.tool-calls-summary`. - `test_header_consistency` — `.doc-meta` pixel bound (`<34px`) was broken by phase 153's 44px touch-target floor at ≤640px → replaced with a shape-first single-line check that still fails a real wrap. - **Completion criteria:** mid-turn box hidden ✅ · bubble appears at first delta, phase-130 rows below unchanged ✅ · restored/shared empty answer paints no box ✅ · no app.js change + anchors + full gates ✅ · commit/`complete/` move = harness's job (I ran no git index/history commands). - **Docs:** README — added the phase-166 "no empty answer box mid-turn" note; fixed a **stale** Thinking lead ("collapsible Thinking blocks", pre-dated the 2026-10-06 one-disclosure refinement); QA section now states E2E isolation is mandatory (shared Postgres + fixed ports 8123/8901) with the per-file sweep loop. AGENTS.md — rule 5 UI checklist now names the phase-166 suppression rule. - **Notable:** running all of `tests/e2e/` in one pytest session is not supported (fixture/port interleaving causes ~126 spurious failures) — documented in README. Restored the tracked `.agents/screenshots/doc_modal_scrollbar_1280.png` that `test_document_viewer.py` rewrites on every run. - **Next pending phase:** `167_api_payload_diet`.	2026-10-08 04:27:03 -04:00
ducoterra	b0c7aed613	phase: 165_prose_word_wrap ... All verification complete. Final report: **Phase 165 — Prose word wrap (final verification pass)** - Verified: `PROSE_FORMATS={txt,text}` + `isProseDoc` (single-site, image arm wins); `renderDocument` three-way branch (md → `.doc-md`, prose → `.doc-prose` text node, else `pre.doc-raw` byte-identical); `.doc-prose` CSS = 72rem column, `pre-wrap` + `overflow-wrap: anywhere`, tokens only, zero literals; `[data-view="pages"]` hide list includes `.doc-prose` as one grouped declaration; phase-116 scrollbar rules intact and modal-scoped; no `innerHTML` in the prose path. - Tests/lint (all 100% green): - `uv run pytest` → **3854 passed** (unit + integration) - `uv run pytest --cov=app --cov-report=term-missing` → **TOTAL 99%** (>90%) - `uv run ruff check .` → All checks passed; `uv run pyright` → **0 errors** - `uv run pytest tests/e2e/test_prose_word_wrap.py -v --no-cov` → **5 passed** (isolation) - Isolation regressions: document_viewer 8, image_documents 4, pdf_pages_in_sources 4, pdf_strip_additive_selfheal 5, edit_summaries 4, summary_in_viewer 4, chat_answer_clusters 4, garbage_pdf 3, pdf_support 6, sticky_navbar 3, smoke 3 — all passed - Completion criteria: image description wraps, full text, both surfaces ✔; `.txt` wraps same way ✔; `py`/`json`/code keep `pre.doc-raw` + horizontal overflow + themed modal scrollbar (E2E negative control + pins) ✔; no innerHTML, AA `--ink`/`--surface` pair ✔; full gates green ✔; commit + phase-dir move are harness-owned (not executed per pipeline rules). - Documentation: README already updated by task 03 (viewer section + image-docs section); full README/AGENTS.md review found no further inconsistencies — **verified consistent, no changes needed**. - Notable deviations: `.doc-prose` omits `font-family: inherit` from 00_phase D2's snippet — task 01's authoritative "exact property set" excludes it and `div` inherits fonts anyway (behavior identical). PDF deferral (A4) intact: `format == "pdf"` stays in `.doc-raw`, owner call recorded. - Next pending phase: `166_hide_empty_answer_bubble`.	2026-10-07 22:57:40 -04:00
ducoterra	8d70aa946c	docs(phases): close two gaps in phase 167 - the date-pin tree consumers and drifted line anchors ... Audit of the written phase found the depth=1 default was specified without naming two of its nine consumers, both of which walk the tree without a depth parameter and assert phase-106 D9 dates: - tests/integration/test_docs_api_dates.py (reaches a -> a/b -> deeper) - tests/e2e/test_git_source_dates.py (_find_file recurses by design) Task 02 gains item 9 (both migrate by requesting ?depth=8 explicitly with every assertion intact, plus the truncation-proof pin that a truncated folder's updated_at still equals the deep max), task 06's isolation list names the E2E suite, and the overview's D2 now carries the full nine-file consumer list. Also corrected the Context anchors: build_kb_tree is L780 (not 781) and _subtree_max is L760 (not 746). LLM-Generated: true	2026-10-07 19:49:06 -04:00
ducoterra	dcb1062b83	docs(phases): convert TODO L3-L5 into phases 165-167 (prose wrap, no empty answer box, API payload diet) ... 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	2026-10-07 19:42:34 -04:00
ducoterra	34d60efbc1	phase: 164_chat_error_honesty ... All gates green. Report: - **Verified (phase 164, all 4 tasks already in `complete/`)**: `HistoryTurn`/`ChatMessage`/`ChatThinkingSegment` caps → 600 000, `history`/saved-messages lists → 500, new `SavedChatCreate/Update` total-8 000 000-char validator; exported `errorDetailText` at the two previously unguarded chat paths (pre-stream `!res.ok` + SSE `error` frame); `FAILED_REQUEST_TEXT` + `bubbleText` threading + phase-114 banner hint; dedicated E2E `tests/e2e/test_chat_error_honesty.py`. - **Final-pass additions**: `tests/integration/test_chat_api.py::test_history_rejects_one_char_over_the_text_cap` (endpoint-level >600k → 422 with the pydantic list-of-objects `msg` — the criterion's upper half was only unit-pinned); README env rows for `BOR_APP_VERSION` + `BOR_SESSION_COOKIE`; restored `test_document_viewer.py`'s tracked screenshot artifact dirtied by the E2E run (via read-only `git show`, no index/history touched). - **Tests/lint (exact commands)**: `uv run pytest --cov=app --cov-report=term-missing` → **3837 passed**, `app/` coverage **99%** (>90%); `uv run pytest tests/e2e/test_chat_error_honesty.py -v --no-cov` → **4 passed in isolation**; per-file loop over **all 148** E2E files (`uv run pytest tests/e2e/<f> -q --no-cov`) → **148 × exit 0**, incl. `test_failed_turn_retry`, `test_chat_save_payload_limits`, `test_edit_and_resend`, `test_llm_history`, `test_smoke`; `uv run ruff check .` → All checks passed; `uv run pyright` → 0 errors. - **Completion criteria**: pre-stream 422 shows the distinct line + verbatim `msg`, `[object Object]` unrepresentable + no `input` in DOM — **met** (unit totality/source pins + E2E asserts 1–2); 525k history accepted (200 settles) / >600k → 422 / saved chat 201 + 8M bound — **met**; transport + SSE-frame settles keep `FAILED_TURN_TEXT`, stop/abort untouched, §7.4 re-enables — **met**; budget trim, `message` 4000, the 7 guarded detail-readers and all SSE shapes byte-identical (diff touches only caps + the two chat paths) — **met**; README/AGENTS full review + proxy deploy note — **met**; commit/`complete/` move = pipeline gate. - **Docs**: README reviewed in full (env tables cross-checked programmatically: 74 `BOR_*` rows vs `Settings` defaults — no mismatches; every `.env.example` var documented; referenced scripts/pages/endpoints/`query_log` columns exist) — found & fixed the 2 undocumented real knobs above; the phase's payload-limits section, failed-turn copy and `client_max_body_size ≥ 16 MB` deploy note verified accurate. `AGENTS.md` verified consistent (rules, gitignore list, quick-reference commands, referenced paths all correct) — no changes needed. - **Deviations**: `ChatThinkingSegment.text` raised 32 000 → 600 000 too (not itemized in A1, but its own docstring mirrors `HistoryTurn.thinking`; without it a long-thinking turn 422s its own auto-save — same mirror invariant). No live-infra changes made (the proxy limit lives in the separate deployment repo; README note only). - **Next pending phase**: none — `164_chat_error_honesty` was the only entry in `todo/`.	2026-10-07 18:00:12 -04:00
ducoterra	6ba46e735a	phase: 163_pdf_strip_additive_selfheal ... All gates verified. Final report: **Phase 163 — final verification pass (all 5 tasks already complete; verification-only run)** - Verified D1–D4 in code: `page_strip_mode` column + migration 0027, `DocContent` absent-never-null rule keyed off `page_count`; `_persist_pdf_pages` render → atomic tmp+`os.replace` writes → stale-tail-last + `strip_class` stamp; `_regate_pdf_strip` on both unchanged paths (mirror gate, heal, repair, fail-soft, one INFO line only when acting); viewer mode branch + Text/Pages toggle (Text default, `aria-pressed`, no innerHTML, lazy imgs). - `uv run pytest --cov=app --cov-report=term-missing` → **3796 tests, exit 0, coverage 99%** (>90%) - `uv run pytest tests/e2e/test_pdf_strip_additive_selfheal.py -v --no-cov` → **5 passed** in isolation - `test_pdf_pages_in_sources + test_pictorial_pdf + test_garbage_pdf` → 10 passed; `test_document_viewer(_context) + test_image_documents` → 20 passed - `uv run ruff check .` clean; `uv run pyright` → 0 errors; alembic **0027 downgrade→upgrade CLI round-trip clean** (+ integration pins) - Completion criteria: additive view w/ toggle ✅ · primary DOM byte-identity ✅ · write-first order/mid-write-failure/atomic pins ✅ · heal + repair E2E ✅ · zero vision/LLM on fast path (mock-captured) ✅ · non-qualifying payload byte-identity ✅ · docs pass ✅ - **Documentation**: README.md + AGENTS.md reviewed in full — the phase's updates are accurate; all config-table defaults cross-checked against `app/config.py` (no drift), every page route, script, and E2E command referenced exists, every `.env.example` var documented — **verified consistent, no changes needed**. - Notable: live `Letumdei` repair is owner-runtime post-deploy per D5 (next production Sync self-heals; no live changes made); the modified `.agents/screenshots/doc_modal_scrollbar_1280.png` is an E2E-regenerated artifact left for the pipeline commit. - **Next pending phase:** `164_chat_error_honesty`	2026-10-07 13:57:30 -04:00
ducoterra	74eb2e265c	docs(phases): add phase 164 (honest pre-stream failure line, shared error-detail serializer, history caps for full-length answers) ... Captures the 2026-10-07 live '[object Object]' finding: a >32k-char answer rides back as history, the 422's list-of-objects detail hits the unguarded body.detail assignment, and the zero-frame settle lies about a dropped connection. Caps raise as a chain (HistoryTurn + ChatMessage mirror per phase-83 SEC-05) with a bounded anonymous total; the budget trim stays locked and untouched. LLM-Generated: true	2026-10-07 09:57:40 -04:00
ducoterra	855fa27a30	docs(phases): add phase 163 (additive PDF strip view, write-first atomic copies, fast-path self-heal) ... Captures the 2026-10-07 live findings on Letumdei_ Heirs to the Imperium: a single sparse map page flipped a text PDF into the strip-only viewer, and the strip's page copies were lost from disk while page_count stayed stamped (no self-heal path). Owner decisions recorded: additive text+Pages toggle for the pictorial class, write-before-delete atomic persist, deterministic zero-LLM fast-path re-gate. LLM-Generated: true	2026-10-07 09:46:37 -04:00
ducoterra	eebc824636	phase: 162_search_recall_small_sources ... **Phase 162 — final verification pass (all tasks already complete; verified + docs pass)** - Verified: `_fold` (NFKD+casefold, stdlib) inside `_normalize_name` — `BESTÅ`→`besta` question side, `BÅsta.md`→`basta` path side; A2 match classes/ranking/caps/bonus untouched; FTS/cosine/A8 untouched. - Verified: `grep_document` folds both sides via the imported `_fold` (no second copy); regex-teaching lines byte-identical; 3 copy sites updated. - Verified: `regenerate_overview` appends the deterministic `Sources: <name> (<k> doc|docs)` tail (happy path only; zero-doc + `LLMError` rows byte-identical; `build_overview_prompt`/`load_kb_overview`/`build_kb_section` untouched). - Verified: `TOOLS_SECTION` grep sentence updated + D4 search-discipline sentence present **verbatim**, immediately after the grep sentence; `PERSONA`/LOW pins byte-identical (`test_prompt_lock.py`). - Measured evidence (in `.agents/reports/162_…/task04_prefix_evidence_and_battery.md` + re-measured every run by `test_under_rank_is_measured_not_assumed`): pre-fix tokens `['build','best']` → IKEA doc rank 6 (outside top-5); post-fix `['build','besta']` → suggested #1, cosine unchanged 0.382. - `uv run pytest tests/e2e/test_search_recall_small_sources.py -v --no-cov` → **7 passed** (isolated); neighbours `test_kb_overview{,_freshness} test_name_signal_read_chips test_grep_regex_teaching test_harness_aligned_tools test_agent_document_tools test_tool_call_compact` → **24 passed**. - `uv run pytest --cov=app --cov-report=term-missing` → **3756 passed**, app coverage **99%** (>90%). - `uv run ruff check .` → All checks passed; `uv run pyright` → **0 errors**. - Completion criteria: fold both ways ✅ · `Sources:` tail ✅ · TOOLS_SECTION + D4 verbatim + re-cut pins ✅ · E2E green/battery recorded/full suite/coverage/lint ✅ · docs pass ✅ · commit + dir move = harness. - Battery: 5 phase-119 questions byte-identical to the phase-119 record (GATE PASS); the 2 Besta questions **skipped loudly** — verified the 2026-09-05 replica dump has zero `ikea` matches (`grep -c -i ikea data/bor_live_kb_replica.dump.sql` = 0); rank gate stays with the owner's live KB. - Docs fixed: README — overview-tail doc + `BOR_KB_OVERVIEW_MAX_CHARS` tail-cut constraint, the phase-162 search-discipline paragraph, per-phase (not per-story) E2E wording, new "Retrieval regression battery" section; AGENTS.md — rule 4 per-phase wording + battery command in Quick reference. (The overview's expected "AGENTS.md §6 tool table" does not exist in this repo — the grep contract line lives in README's tool table, already updated.) - Deviations (recorded, not assumed): `_fold` adds `casefold` (required for the pinned `ß → ss`); `①` NFKD-decomposes to `1` (the overview's parenthetical was wrong) and is excluded by `NAME_TOKEN_MIN_LEN`; pre-fix evidence lives in the reports dir because task files are read-only for this pass. - Owner follow-up A6 (runtime, not code): add the Tuning-tab steering note "IKEA's BESTÅ assembly PDF is a live source — search it as `BESTÅ` or `AA-1272068`". - Next pending phase: none — 162 is the only entry in `todo/` (harness moves it to `complete/`).	2026-10-07 01:42:01 -04:00
ducoterra	690fd98036	fix(rag): stop the per-run blocks from folding — the container is the one disclosure ... The owner refinement (2026-10-06): the per-run thinking and tool-call blocks inside the Reasoning bubble were individually collapsible details elements — a fold inside the fold. A tool frame closed the previous thinking block, so the visible thinking vanished mid-turn; and the pinned-tail follow died on the append of every run after the first (the pin was captured AFTER the new block's height growth contaminated the 32px reading). - app.js: the in-container runs are now plain divs — createThinkingRunEl (div.thinking + static .thinking-summary label + .thinking-text) and createToolRunEl (div.tool-calls-disclosure + static .tool-calls-summary label + the .tool-calls list); they never open or fold (the container is the ONE open/fold control, open through the turn, folded at settle — unchanged); the pin capture moves BEFORE ensureThinkingRun/ensureToolRun append (plus the first-frame edge: no container yet -> always pinned); closeCurrentRun just ends the run; closeAllRuns stays the defensive legacy guard; restoreTimeline/addSegments (shared.js) use the div builders; the legacy no-segments restore path keeps the old details-based blocks byte-identical - styles.css: the in-container runs are distinct by label + rail (brand-ink Thinking label on a brand-soft rail; accent-ink Tool call(s) (N) label on a neutral rail); the interactive treatment (cursor + chevron) is scoped to the legacy <summary>; the inner windows stay disabled (the container's .reasoning-body is the ONE live scroll surface) - unit + E2E: the D5-refinement contract is pinned — one details.reasoning disclosure, per-run blocks as plain divs, zero nested <details> inside the container, the container as the only open/fold control, the .reasoning-body window auto-follows the tail while streaming unit+integration 3738 passed (coverage 99%), ruff + pyright clean, all five affected E2E suites pass in isolation (reasoning_bubble 6, thinking_timeline 6, thinking_display 5, thinking_scroll 8, tool_call_compact 4), verified live: the follow holds through a long thinking stream, the tool-frame transition, and the second thinking run; restore renders the div structure without client-side errors LLM-Generated: true	2026-10-06 14:44:41 -04:00