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
All green — this was the final verification pass; everything from the four completed tasks was already in the working tree and verified.
**Phase 115 — Doc drafts: Discard + DELETE route + title fix — verification report**
- Verified all 4 task deliverables present: DELETE route (`app/api/doc_drafts.py`), Discard UI (`doc-edit.html` + `doc-edit.js` + `.discard-draft` CSS), title fix (`defaultDocTitle(wrap)` pairing + `saveAsDoc` call site), and all test pins (integration, frontend unit, E2E). No code changes needed.
- **Completion criteria:**
1. ✅ Orphaned draft discardable from edit screen; row gone — `test_delete_removes_row_and_invalidates_token` (204 → GET 404), unknown-token 404, admin-gate 403 on all routes, E2E `test_discard_draft_from_edit_screen` all pass.
2. ✅ Title after retry redo = redone answer's own question — E2E `test_save_title_is_the_redo_question_after_retry` passes.
3. ✅ Push flow byte-identical — `git diff` shows only the new DELETE route + module docstring; all 7 existing push tests green.
4. ✅ `uv run pytest --cov=app` → **2457 passed**, app coverage **99%** (>90%); `uv run pytest tests/e2e/test_save_doc_session.py -v --no-cov` → **4 passed**; `uv run ruff check .` → clean; `uv run pyright` → 0 errors.
5. ⏳ Commit + phase-dir move left to the harness (per executor rules, no `git` run; all changes left in the working tree).
- No defects found; no deviations.
- Next pending phase: none in `todo/` other than this one (`115_doc_draft_discard` is the last).
All gates green. Final report:
**Phase 109 — final verification pass (all 3 tasks were already complete; no re-implementation needed)**
- Verified D15 (thinking-handler re-open `block.open = true` after `ensureThinkingBlock`; delta keeps closing; "never reopens" narrative removed; restore path still collapses) and D16 (single static `#turn-loader` in composer row, `aria-hidden`, sole `turnLoader.hidden = !inFlight` write in `setUiState`; CSS reuses `typing` keyframes + reduced-motion override after the main rule + provenance; global `[hidden]` guard intact; mock `TURN_PROGRESS_TRIGGER` repro marker; `app/` untouched — pure UI phase).
- Unit pins: `tests/unit/test_frontend_turn_loader.py` (9 tests) — green via full run.
- `uv run pytest tests/e2e/test_turn_progress_loader.py -v --no-cov` → **3 passed** (isolation, DB up): loader visible send→tool-gap→final-thinking, hidden after done; re-opened scratchpad carries `marker-thought-42`/`marker-final-thought-42`; `#send-status` carries state text, back to empty idle; reduced-motion context stills dots (computed `animation-name: none`) with loader still visible.
- Regressions in isolation: `test_thinking_display` 5 passed, `test_stop_generation` 3 passed, `test_big_read_progress` 4 passed, `test_loading_feedback` 5 passed.
- `uv run pytest` → **2314 passed**; `uv run pytest --cov=app --cov-report=term-missing` → **TOTAL 99%** (>90%); `uv run ruff check .` clean; `uv run pyright` → 0 errors, 0 warnings.
- All terminal paths (done→idle L2554, stream error→error L2543, timeout→error L2247) funnel through `setUiState` — never-stale by construction.
- No defects found; no code changes made in this pass. Commit + phase-dir move left to the harness per pipeline rules (working tree carries all changes).
- Next pending phase: `108_history_wire_check` (still in `todo/`; out of scope here).
header.js's control bindings (sign-out, the mobile hamburger, the
SINGLE New chat button) ran at module import. The Containerfile stage-1
build inlines header.js into every bundle that imports it (the shell's
app.js, token-gate.js and the router's lazy views), so the shell page
registered the #nav-toggle click handler twice, and two toggle handlers
cancel each other — one tap = open + close = the mobile menu dead in
the deployed image only. The dev tree's single ESM instance (and every
test that runs against it) never showed it; a lazy view load adding a
THIRD copy made the menu work again, which is why the failure looked
state-dependent (chat cold boot dead, /sources.html alive).
- header.js: the three bindings move into an exported
bindSharedHeaderControls(), guarded by a marker on <body> (NOT module
state — every bundle copy has its own function instance), so later
bundle copies and repeated inits (the token gate's mid-page header
re-boot) are no-ops; header.js is now side-effect-free at top level,
which also lets esbuild tree-shake the dead copies out of the bundles
that do not need them (the token-gate bundle no longer carries the
binding code at all)
- app.js / login.js / shared.js / document.js: call
bindSharedHeaderControls() once at module top — import-time parity,
unconditional (no async boot path to miss); doc-edit.js ships no
header controls and calls nothing
- unit: tests/unit/test_header_bindings_once_per_document.py pins the
contract — the init export, the document-level idempotency marker,
all three bindings inside the init, NO top-level addEventListener
remaining, and exactly one module-top call in each header-carrying
page script; stale import-time docstrings in the legacy header pins
updated to the new contract
Verified: full unit + integration suite (1746 passed), the hamburger /
pinned-composer / smoke E2E stories green in isolation, ruff + pyright
clean. Containerfile-equivalent esbuild 0.25.5 rebuild probed in
Chromium: exactly ONE #nav-toggle click listener on chat cold boot,
/sources.html and login.html, and a touch tap opens the menu in all
three states (pre-fix production: two listeners on cold boot = dead,
three on sources = alive).
All completion criteria verified green. Final state confirmed: phase stays in `todo/` per A4 (owner device gate), task files in `complete/`, no `app/` changes, no commits made (harness commits).
## Phase 88 — final verification pass report
**Verified (all 6 tasks already complete):** `touch-action: manipulation` on mobile `#nav-toggle`; `#view-chat.chat-booted` double-rAF sticky handover (CSS gate + app.js boot IIFE); `body.nav-menu-open` marker in `setNavMenu` + ≤640px `visibility: hidden` rule; router boot contract (`wasMounted && !opts.boot` + `boot: true`); new unit module (10 pins) + 4-test real-touch E2E story.
**Test / lint / coverage:**
- `uv run pytest --cov=app --cov-report=term-missing` → 1741 passed, **99%** on `app/` (>90% ✓)
- `tests/e2e/test_mobile_chat_hamburger_boot.py` 4/4, `test_mobile_hamburger_nav.py` 8/8, `test_pinned_composer.py` 4/4, `test_smoke.py` 3/3 — each in isolation, `--no-cov` ✓
- `uv run ruff check .` clean; `uv run pyright` 0 errors ✓
**Completion criteria:** (1) 360px cold-boot touch-action + sticky handover + tap-opens-menu-with-cluster-hidden (E2E 1–2) ✓; (2) boot fires no `bor:view-refresh`, re-show fires exactly one, `/sources.html` regression (E2E 3–4) ✓; (3) full gate green ✓; (4) diff limited to 4 assets + 2 new tests + phase files, 0 changes in `app/` ✓; (5) commit deferred to harness per executor rules ✓; (6) owner device re-verification **pending** (A4 — gates the archive; no Owner report recorded yet).
**Deviations (both documented in-tree):** unit pins updated in `test_frontend_router.py`/`test_hamburger_nav.py` (their exact-text pins collided with the mandated new guard/marker text — without them the suite goes red); `boot: true` count pinned at 1 not 2 (codebase has one boot call site, no `history.state` branch — verified against git HEAD).
**Next pending phase:** none in `todo/` — pipeline awaits the owner's on-device report (archive, or `?dbg=nav` instrumentation follow-up if the menu is still dead).
The client-side TURN_TIMEOUT_MS was the binding constraint: turns with
slow prompt processing (no first SSE frame within 120 s of visible time)
errored with the 'stuck' copy even though nginx (300 s) and
BOR_LLM_TIMEOUT (300 s) would have let them run. Raise the guard to
300 s so the upstream timeouts are reachable, and re-pin the tests:
the unit constant pins and the fake-clock E2E timeline (295 s hidden
+ 290 s after the re-arm = 585 s: past the original 300 s deadline,
short of the re-armed 595 s deadline).
Verified: tests/unit (full, 100% pass), tests/e2e/test_hidden_tab_stream.py
and tests/e2e/test_loading_feedback.py in isolation.
Single consolidated commit for four completed, validated phases (77, 78,
79, 80). The pipeline run left all work uncommitted because the harness
commits only with PHASE_COMMIT=1 while child executors are forbidden from
committing; the phases themselves all passed validation and moved to
.agents/phases/complete/.
Phase 77 — navbar view refresh
- router.js dispatches bor:view-refresh on re-show / active re-click /
popstate (gated on wasMounted; first show and boot exempt)
- History / RAG / Sources / Tuning re-fetch on refresh (admin branch);
Chat deliberately excluded (stream survival)
- History "Refresh" button (admin-only, in-flight disable + status line)
- New story suite tests/e2e/test_navbar_refresh.py (7 tests)
Phase 78 — static background
- Removed the animated glow layers; static 44px grid over the flat --bg
canvas; default and reduced-motion renders byte-identical
- Updated background/theme E2E suites; removed bg-glow test pins
Phase 79 — API tokens
- api_tokens model + migration 0012; hash-only token service
- Admin tokens API + Tokens admin view; POST /api/token-auth;
live-revoking require_user on chat / suggestions / document content
- Frontend token gate with localStorage cache; anonymous E2E suites
migrated to token login
- New story suite tests/e2e/test_api_tokens.py (9 tests)
Phase 80 — history suggestion chips
- last_questions() endpoint with SEED fallback; startNewChat() refetch
- Seed-semantics docs (config.py, .env.example, README)
- Integration state matrix + E2E suite rewritten to the 4 chip states
Also included: phase-76 report artifacts and the repo restore-test-db
skill (previously untracked), scripts/* ruff fixes from phase 77.
Final gate state (phase 80 final pass, covers everything above):
- uv run pytest --cov=app → 1637 passed, 0 failed, app/ coverage 99%
- uv run ruff check . && uv run pyright → clean, 0 errors
- Per-phase story E2E suites green in isolation
Phase 75 (TODO.md L4): "Save as doc" now drafts a document from the
ENTIRE chat session — every question and answer up to the click, in
order — instead of only the clicked bubble's answer; the existing
doc-edit screen's free-form body editing is how the user edits out
anything they don't want to keep from previous replies (no new UI
surface).
Task 01 (frontend):
- app.js buildSessionTranscript(): walks the bor.chat.v1 conversation
record in order — a numbered section per user turn ("## N.
<question, raw>" + blank line + the raw answer text; more answers
join under the same heading), sections blank-line separated, all
trailing whitespace collapsed to one final newline. Only the raw
persisted text travels (m.who + m.text — no thinking blocks, no
source chips, no tune metadata); a brain record before the first
user record is skipped; a heading-only section marks a user turn
whose answer never landed (A6, owner-confirmed 2026-09-08).
- saveAsDoc(btn): the draft body is buildSessionTranscript(); the
dead single-bubble markdown parameter is dropped (the button's
appendSaveAsDocButton signature is unchanged — one button per
bubble). Title/path/double-click guard/hand-off are unchanged
(defaultDocTitle: the last question, whitespace-collapsed,
<=120 chars; docs/<slug>.md).
- Unit: the app.js source pins move to the transcript shape (whole
session, no thinking, no dead parameter).
Task 02 (E2E):
- tests/e2e/test_save_doc_session.py (bare-repo fixture, the
phase-59 convention — git as source of truth): three DISTINCT
on-topic turns in one session (turn 1 carries the phase-17
"think out loud" trigger so its record has a thinking block the
transcript must exclude) -> save on the LAST bubble -> the
prefilled body is ## 1./## 2./## 3. in order, byte-exact against
the deterministic mock, thinking-free -> edit the whole
section-2 block out of the body -> push -> git show
bor-docs:<path> equals the EDITED body byte-for-byte (section 2's
question and answer provably absent; sections 1 and 3 byte-exact;
the UI's sha prefix is git rev-parse bor-docs). Second test:
the button on the FIRST bubble still drafts the whole session
(A6 — the transcript is the session at click time, title stays
the last question); canceling leaves the branch tip untouched.
- tests/e2e/test_response_to_docs.py: the phase-59 single-turn body
expectation moves to the transcript shape ("## 1. <question>" +
the answer's markdown) — the rest of the suite unchanged.
Also lands the phase-74 file moves (00_phase.md /
03_mock_marker_e2e.md -> complete/) and the phase reports — the
house convention of committing .agents/ with the phase.
Phase 74 (TODO.md L4): a follow-up question now reaches the model WITH
the conversation so far — every prior user/brain turn and the prior
thinking blocks on brain turns (preserve-thinking) — while
POST /api/chat stays stateless (A10): the client provides the history
in the request body and the server stores nothing new.
Server (task 01):
- ChatRequest.history: optional list[HistoryTurn] (who: user|brain,
text, optional thinking) — absent/empty keeps the request
byte-identical to pre-phase-74 (the two-message [system, user]
request; the kill-switch semantics are pinned in the integration
suite).
- app.rag.prompts.history_to_messages: pure mapper — walks the turns
newest-first against the settings budgets (history_max_turns=40 /
history_max_chars=24000, BOR_HISTORY_MAX_TURNS /
BOR_HISTORY_MAX_CHARS); a capped turn is dropped WHOLE (never cut
mid-answer); the kept window is returned oldest-first; brain turns
carry their thinking as reasoning_content (A4) only when
non-empty.
- Both branches feed it: the deflected path splices it between the
system prompt and the current user message (the phase-71 recovery
still rebuilds from messages[1:]), the grounded agent receives
run_agent(..., history=hist); llm.py's message params widen to
list[dict[str, Any]] (string-only messages stay byte-identical on
the wire — the SDK passes message dicts through verbatim).
- The per-turn log line (PLAN §9) gains history_msgs=N after
kb_chars=N.
- Pins: tests/unit/test_history.py (mapper: mapping, reasoning
gating, both budgets, drop-whole, ordering, empty default),
tests/unit/test_config.py (the two settings + env overrides),
tests/unit/test_agent.py (the history splice + the default),
tests/integration/test_chat_api.py (deflected AND grounded forward
the history incl. reasoning_content, no-history byte-identity, 422
pins, the log field).
Client (task 02):
- runTurn — the single funnel for fresh send / phase-49 retry /
phase-53 stale-regen — sends history = the conversation record
minus the current question, with thinking only on brain records
that streamed one (undefined drops the key from the JSON, the
record's convention); the question is never duplicated into the
history.
Wire proof (task 03):
- The mock's echo my history marker (HISTORY_TRIGGER) answers with
the deterministic history echo — history: N prior messages; last
answer tail: <last 24 chars>; thinking: yes|no — checked BEFORE
the DEFLECT_MODE branch (like TABLE_TRIGGER), so it fires on both
turn branches whatever the gate says; the module docstring records
the user/assistant-only history invariant that keeps every
existing (tool-result-classified) marker flow unaffected.
- tests/e2e/test_llm_history.py (isolated): a grounded follow-up and
a deflected follow-up both receive history: 2 prior messages +
thinking: yes + the byte-exact tail of turn 1's answer (derived
from the persisted bor.chat.v1 record — the same array the client
maps into the body); a cold start receives history: 0 prior
messages / last answer tail: none / thinking: no.
- Regressions green in isolation: chat_rag, chat_history (phase 50),
agent_document_tools, harness_aligned_tools, stop_generation,
retry_answer, response_to_docs.
Root cause (task 01): none of C1-C3 - in Chromium 151 (real mode) a
merely-hidden tab neither stops the stream (frames arrive at full rate;
turn completes) nor fires pagehide on tab switch; C1's double-record
path was proven latent via a synthetic pagehide (trigger is
browser-dependent, e.g. Safari) and C2 (the 120s pre-token guard) was
confirmed to fire while hidden.
- C1: the pagehide partial-persist is correlated with the turn's settle
(leavePartialIndex) - the done/stop settle REPLACES it in place
(identity-guarded rememberBrainTurn in-place mode), so bor.chat.v1
and the auto-saved saved_chats row keep exactly ONE brain turn per
question; a real navigation never runs a settle, so the leave-save
is unchanged.
- C2: the visibility re-arm gives the still-armed pre-token guard a
fresh TURN_TIMEOUT_MS when the tab returns to visible - hidden time
no longer counts toward the 120s guard.
- Phase-48 teardown contract untouched: Stop / tab close / real
navigation still cancel the fetch and stop the model.
- Unit pins: tests/unit/test_frontend_hidden_tab.py (the app.js
mechanisms without a browser).
- E2E pins: tests/e2e/test_hidden_tab_stream.py - synthetic pagehide
mid-stream completes exactly once with one brain turn (localStorage
+ auto-saved row), reload restores one bubble, no-event baseline,
and the fake-clock pre-token guard re-arm (discriminating: fails
with the re-arm disabled).
- scrollReveal lands at the document bottom (window.scrollTo) instead of
scrollIntoView({ block: 'end' }): the old alignment sat above the
in-flow composer, so every Enter hopped the page up by the
composer+footer height and pushed the composer below the fold.
- The thinking window's pin state is now captured BEFORE the re-render
(const pinned = block.open && isThinkingNearBottom(textEl)): the
post-render distance read the new chunk's rendered height, not the
user's position, so any chunk taller than the 32px band (real-model
deltas, '\n\n' paragraph breaks) killed the follow at the first
2-newline gap.
- Mock LLM: new 'think in paragraphs' trigger (scratchpad with real
blank-line breaks, 60-char frames) — the 12-char mock frames never
rendered past the band, which is why the bug survived the E2E gates.
- E2E (both verified red against the old code):
test_submit_does_not_hop_up, test_thinking_window_follows_across_paragraph_breaks.
- Unit source-marker tests updated to the new contracts.
TODO.md L7: "Add scrolling back to the thinking block, but have it
autoscroll while thinking content is generating." Owner direction
2026-08-27 (roadmap A2) reverses the phase-21 no-scroll choice
(2026-08-24): details.thinking .thinking-text is user-scrollable again
(overflow-y: auto — the 320px clip stays, owner-confirmed), and the
phase-17 per-chunk bottom-pin is GATED: the window follows the live
tail only while the user is pinned near its bottom (THINKING_NEAR_
BOTTOM_PX = 32); scrolling up pauses the follow, returning to the
bottom re-arms it on the next chunk (the gate re-runs on every frame).
- frontend/assets/styles.css: .thinking-text overflow-y: hidden ->
auto; the phase-21 owner-choice comment is replaced with the
2026-08-27 direction; max-height: 320px and every other declaration
in the rule byte-identical.
- frontend/assets/app.js: export const THINKING_NEAR_BOTTOM_PX = 32 +
isThinkingNearBottom(textEl) (scrollHeight - scrollTop -
clientHeight <= band); the thinking-handler pin becomes
`if (block.open && isThinkingNearBottom(textEl))` — a scrolled-up
reader is never re-pinned and a closed (restored) block is never
pinned; everything else in the handler (and phase 42's no page
scroll) untouched.
- tests/unit/test_thinking_scroll.py (new, replaces the deleted
tests/unit/test_thinking_no_scroll.py): pins the CSS contract (auto
+ 320px + owner-direction comment, no hidden/scroll left), the
exported 32px band, the gate math, the gated pin (no unconditional
`if (block.open)` remains), and the surviving collapsed-restore pin.
- tests/e2e/test_thinking_scroll.py (new, mock-only, replaces the
deleted tests/e2e/test_thinking_no_scroll.py — its pins asserted the
reversed phase-21 behavior, so both phase-21 files are deleted in
this commit): user scroll restored on the frozen 4s-hesitation tail
(wheel is 1:1; click+Home keyboard — the plain div is not
keyboard-focusable by design, tabindex is test scaffolding; the
literal drag holds the user's position — headless Chromium's
overlay scrollbars are not grabbable by synthetic mouse events,
documented in the suite), follow-while-pinned at the 2nd-to-last
and last chunk (±1px) with the last chunk's text inside the visible
rectangle, no re-pin over ≥5 mid-stream chunks after a
half-window scroll-up, re-pin on the next chunk after returning to
the bottom, the CSS contract, plus the phase-11 (long answer: page
scrolls, bubble overflow untouched) and phase-17 (restored
collapsed block with full text) regressions.
- tests/unit/test_chat_persistence.py: the CSS pin flips with the
contract (auto in, hidden out — owner direction 2026-08-27).
- tests/unit/test_frontend_scroll.py: the "page-level band constant is
gone" pin now excludes the phase-43 window-level
THINKING_NEAR_BOTTOM_PX (a different band — the window's, not the
page's).
E2E (isolation): test_thinking_scroll 7/7 (twice); regressions
test_thinking_display 5/5, test_chat_persistence 4/4,
test_no_reply_autoscroll 5/5, test_smoke 3/3; unit+integration 725
passed, app/ coverage 99% (unchanged — frontend-only phase);
ruff + pyright clean.
TODO.md L5: "Get rid of the chat reply autoscroll, it's breaking things
like making it impossible for the user to scroll while a reply
generates." Owner direction 2026-08-27 (roadmap A1) revises the
phase-18 follow-the-bottom choice: the page NEVER auto-scrolls while a
turn streams. Kept (owner decision): the submit reveal (the user's own
message) and the one-shot phase-14 restore landing.
- frontend/assets/app.js: delete NEAR_BOTTOM_PX + isNearBottom;
scrollReveal becomes the one unconditional scrollIntoView (still
smooth, still "auto" under prefers-reduced-motion via SCROLL);
addMessage(who, html, scroll = false) carries an explicit scroll
intent — only the submit (", true") and the two restore landings
scroll. The thinking/tool/delta handlers and the typing indicator
drop their page-scroll calls; the thinking block's INTERNAL
bottom-pin (textEl.scrollTop, phase 17 — reworked separately in
phase 43) and the turn-end focus({ preventScroll: true }) survive.
- tests/unit/test_frontend_scroll.py: rewritten pin for the new
contract — phase-18 gate absent, helper unconditional, explicit
intent at submit/restore, no page-scroll call in the streaming
handlers, typing bubble scroll-free, SCROLL reduced-motion intact.
- tests/unit/test_chat_persistence.py: restore-landing pin updated to
the new signature (the old forced "auto" is gone; the landing
rides the default SCROLL — noted at the call site).
- tests/e2e/test_no_reply_autoscroll.py (new, replaces the deleted
test_follow_bottom_scroll.py): no autoscroll across >=10 samples
(1px tolerance) during a long answer and during the thinking stream;
submit-from-the-top still reveals the user message; the restore
landing lands one-shot on the latest message and stays; long answer
+ sources and the collapsed thinking block persist and restore.
E2E (isolation): test_no_reply_autoscroll.py 5/5; regressions
test_chat_rag 3/3, test_thinking_display 5/5,
test_chat_persistence 4/4, test_long_answers 2/2, test_smoke 3/3;
unit+integration 723 passed, app/ coverage 99%; ruff + pyright clean.
One env var (BOR_APP_NAME, default "Brain of Reese") now drives the app's
display name everywhere (TODO.md L12 — owner ask: "a way to customize the
name for 'Brain of'. Should be an env var."). The existing app_name setting
is the source of truth (phase locked decision — no new variable, no rename);
with the variable unset the app is byte-identical to before.
Endpoint (A10 public/stateless, no secrets):
GET /api/config → exactly {app_name, version} (app/api/config.py, the
health.py pattern; registered before the static mount). Integration tests:
anonymous 200, default values, a Settings override follows, key set is
exactly two keys — no other setting may leak in later.
Frontend brand layer (A11 — runtime fetch, static templates stay static):
assets/brand.js — a CLASSIC script, first on all six pages, so its top
level runs at parse time: window.BOR_BRAND = "Brain of Reese"
synchronously (the default renders immediately, no blank flash), then a
no-store fetch of /api/config applies the name — document.title (global
replace), every .brand-text (a name starting "Brain of " keeps the bold
split Brain of <strong>rest</strong>, any other name renders plain; the
operator-controlled name is HTML-escaped before innerHTML), a TreeWalker
over text nodes (script/style rejected — page source never rewritten),
and the aria-label/placeholder/meta-content attributes. Fetch failure
keeps the default + console.warn (the loadHealth house style).
app.js (status labels, typing label, elapsed-hint aria, tool labels) and
document.js (viewer titles) read window.BOR_BRAND at CALL time via
brand() — a label set after the fetch lands carries the configured name.
Containerfile: esbuild minify line for brand.js (classic, like markdown.js);
the phase-33 ?v= cache-busting picks the new asset ref up automatically.
E2E (A16 — one story, one file, isolated): test_configurable_brand.py boots
a SECOND app instance (same DB/mock-LLM/admin-auth env block, port APP_PORT+1,
BOR_APP_NAME="Brain of Testy") — the shared conftest server keeps the
default name so every other suite's title/label assertions stay untouched —
and asserts /api/config on both instances, the index title/brand/greeting/
#messages aria-label, the sources + login page titles, and one pre-token
chat turn (think out loud marker) whose #send-status reads "Brain of Testy
is thinking"; the no-op regression pins the shared server's default bytes.
Docs: .env.example App section + README configuration reference — what it
affects (titles, header brand, status labels, aria text), the default, the
bold-split rendering rule.
Gates: 695 unit+integration passed, app/ coverage 99% (>90%), story E2E
green in isolation (two consecutive runs), brand-string suites (smoke,
shared header, header consistency, chat persistence) green, ruff + pyright
clean.
Grounded chat turns now run the agent loop (app/rag/agent.py) instead
of a bare chat_stream: while the per-turn budgets last
(BOR_AGENT_LIST_CALLS / BOR_AGENT_READ_CALLS, default 1 each) the model
gets list_documents (the indexed catalog, /api/docs order) and
read_document (full text, never truncated — A7-revised contract); once
both budgets are spent the tools key is dropped from the request and
the model must answer. Rejected calls (unknown tool, unknown/missing
path, document already in context, spent budget) consume no budget.
Budgets 0/0 make exactly one tools=None request — byte-identical to
the pre-phase path (budgets-as-kill-switch). Deflected turns keep the
direct chat_stream (A8 unchanged; the LOW prompt never carries the
<tools> section).
SSE contract gains {"type":"tool","name":...,"argument":
"source/path"|null} frames ahead of the answer deltas (PLAN §4
extension, owner permission 2026-08-26); done.sources, query_log.sources
and the per-turn log line (gains tool_calls=N) report the retrieval
docs + read docs, deduped. The UI shows a "calling tool"
button/label state and one visible .tool-call line per call above the
answer; the lines persist with the chat record and re-render on
reload. chat_stream passes tools through and accumulates streaming
tool_calls deltas into ToolCallPiece (tools=None stays byte-identical).
E2E: deterministic mock tool flow ("use your tools" + <tools> marker:
list -> read first catalog line -> quoted answer) plus the story suite
(marker flow, reload re-render, plain/deflected no-tool regressions).
Docs: .env.example + README (the two tools, the budgets, the SSE tool
frame, the "calling tool" UI state).
probe: turbo tool_calls=supported 2026-08-26 (uv run python -m
scripts.llm_probe --tools — non-streaming + streaming
finish_reason=tool_calls, indexed delta.tool_calls partials)
ducoterra