docs: close out session 0010's remaining sign-off items (session 0015)

Resolves the two items left open in ai-sessions/0010 after its Volume
Balance proposal was approved separately (DECISIONS.md ADR-026, session
0013):

- PROTOCOL.md §6: the CAP-037/CAP-048 dock-timing anomaly is confirmed
  resolved (a genuine real-time docking action, consistent with the
  existing DECISIONS.md ADR-016) — the "awaiting maintainer sign-off" hedge
  is removed.
- DECISIONS.md ADR-024: added a dated Update recording CAP-048's two
  counter-example Settable-toggles readings as a documented, unreconciled
  HYPOTHESIS exception, not a reversal of the ADR's own FACT.

Both approved by the maintainer directly in chat. ai-sessions/0010 and
ai-sessions/0015 both close as complete; nothing remains pending from
session 0010.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V2WfHWj4DFbq79FSae5KdV

Author: tedsluis

DECISIONS.md

@@ -1227,6 +1227,20 @@ motivated this).
   candidate cross-check for `ARCHITECTURE.md`'s connection/dock-state model. The exact bit-level
   meaning of `0xe8` beyond "not both docked" (e.g. whether it varies further for one-bud-docked
   states) remains unexplored and is not claimed by this ADR.
+- **Update (2026-09-13, maintainer sign-off, `ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`):
+  two counter-examples found in a single session, not yet reconciled.** `CAP-048`
+  (`CAP-048-FINDINGS.md` §5, a purpose-built repeat with continuous dock-state video) found two
+  fresh classic reconnects (`17:44:45`, `17:47:42`) reporting `Settable-toggles=0x00` (docked) while
+  the video, checked at essentially the same wire timestamp, shows the case visibly **empty**. Four
+  other readings in the same session (including two same-chandle DLCI reopens, not fresh
+  reconnects) are correct — this is not a reversal of this ADR's own dock-state-indicator finding,
+  which the same session's other readings continue to confirm. 🟡 **HYPOTHESIS, not confirmed:** a
+  fresh reconnect's own Get/Notify may occasionally return a value queried before the Buds' own
+  firmware has settled on an already-changed physical state — offered as a testable direction only;
+  does not by itself explain why the other four fresh reconnects in the same session read
+  correctly. Implementations reading this field on a fresh reconnect specifically (as opposed to a
+  same-chandle DLCI reopen) should treat it as usually, not unconditionally, reliable immediately
+  after connection.
 
 ## ADR-025 — Google Play Services (GMS) reverse-engineering is out of scope; DLCI 0x04/0x08 implementation proceeds clean-room, from wire evidence only
 

PROTOCOL.md

@@ -2496,16 +2496,16 @@ leaving them buried in prose elsewhere.
       (`CAP-032-FINDINGS.md` §5).
 
 - [x] **Added 2026-09-06, `CAP-037-FINDINGS.md` §5 (Group AD, `OBS-004` purpose-built repeat);
-      resolved 2026-09-12, `CAP-048-FINDINGS.md` §4 (PROPOSAL, awaiting maintainer sign-off):** on
-      one of 26 same-session `DECISIONS.md` ADR-022 replications, a chandle shows a **second**
-      "Notify ANC state" frame 18 seconds after the first, with no new `08 11` Get frame in
-      between, and its `Settable-toggles` value flips from `0xe8` to `0x00`. `CAP-048` (a repeat
-      with continuous physical dock-state video) reproduced this exact shape (chandle `0x0010`,
-      `17:52:25.14`) and resolved it directly: the video, extracted at the exact wire timestamp,
-      shows a hand actively placing a bud into the case at that moment — a genuine real-time
-      dock-state change while the ACL connection stayed open, **consistent with** (not in tension
-      with) `DECISIONS.md` ADR-016 — the second bud's own docking, 5.4s later, is what then triggers
-      the disconnect, matching ADR-016 exactly.
+      resolved 2026-09-12, `CAP-048-FINDINGS.md` §4; maintainer sign-off obtained 2026-09-13
+      (`ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`):** on one of 26 same-session
+      `DECISIONS.md` ADR-022 replications, a chandle shows a **second** "Notify ANC state" frame 18
+      seconds after the first, with no new `08 11` Get frame in between, and its `Settable-toggles`
+      value flips from `0xe8` to `0x00`. `CAP-048` (a repeat with continuous physical dock-state
+      video) reproduced this exact shape (chandle `0x0010`, `17:52:25.14`) and resolved it directly:
+      the video, extracted at the exact wire timestamp, shows a hand actively placing a bud into the
+      case at that moment — a genuine real-time dock-state change while the ACL connection stayed
+      open, **consistent with** (not in tension with) `DECISIONS.md` ADR-016 — the second bud's own
+      docking, 5.4s later, is what then triggers the disconnect, matching ADR-016 exactly.
 - [ ] **Added 2026-09-12, `CAP-048-FINDINGS.md` §5:** a genuine, video-confirmed counter-example to
       a simple reading of `DECISIONS.md` ADR-024: two fresh classic reconnects (`17:44:45`,
       `17:47:42`) report `Settable-toggles=0x00` (docked) while the video, checked at essentially the
@@ -2612,6 +2612,7 @@ leaving them buried in prose elsewhere.
 | 2026-09-08 | **`ai-sessions/0003_MAINTENANCE_PROMPT_2026_09_08.md` Phase 3/4 — APK reverse-engineering and capture cross-checks.** **§4.5.5 In-ear detection (`qhr` field 2)** promoted to 🟢 FACT for field-number/category-level identity, maintainer-approved (`DECISIONS.md` ADR-019 Update): the field's existing write site is also reached from the system Settings app's `MaestroDeviceSettingsProviderService` (case `2102`), logged there under the internal category name `"CATEGORY_OHD"` — the specific "In-ear detection" UI-label equivalence stays 🟡 HYPOTHESIS. **§4.2 EQ** — `fyd.d`/`fyd.e`'s call sites traced: field 16 confirmed fed from the slider-drag/preset path; field 18 found reachable *only* via a dedicated "Save EQ" button click handler, directly contradicting (not confirming) `CAP-015`'s own "fires on slider-release" wire-timing hypothesis — recorded as an open tension per the maintainer's own review, not resolved either way. **§6** — `MaestroDeviceSettingsProviderService`'s remaining 5 case IDs traced (field 27, field 11/Multipoint with a new internal-name confirmation and an unreconciled `fpm.ENABLED_HEAD_GESTURES` naming tension, field 5, a non-`qhr` "Feature A" toggle, and a new field 32); `MaestroEndpointService.onCreate()` read via `apktool` smali fallback (a Dagger-multibinding-based, per-call UID-authorization-gated service registry, service names not recovered); `gjv.p()`'s caller re-attempted and still not found (static analysis judged exhausted). **`CAP-041-FINDINGS.md` §8** — full byte-for-byte content diff of the DLCI 0x02 connect-time burst across 4 settings states: content-level clean negative for a settings-state read-back, closing `OBS-007` beyond the prior length-only result. **§6** — a plausible (unconfirmed) structural match found between `CAP-036`'s existing connect-time burst and `qjb`'s `qie`-shaped nested structure; `TrueWirelessHeadset.modelId` confirmed to need the maintainer's own device access, no existing data found | Claude (AI), APK-reverse-engineering + capture-analysis task; one item (`qhr` field 2) maintainer-directed sign-off, prompt `0003` |
 | 2026-09-09 | **`ai-sessions/0004_MAINTENANCE_PROMPT_2026_09_09.md` — connection-lifecycle analysis on existing captures.** **New §5.2**: DLCI 0x02 (`libmaestro`) reliably opens *last* of the five data-carrying RFCOMM channels on a fresh reconnect — 6 independent instances across `CAP-036`/`CAP-037`/`CAP-041`, zero counter-examples in that condition, one honestly-scoped exception during a mid-session RFCOMM channel-bounce (where the order differs). Maintainer reviewed this directly in the chat session that authored this prompt and explicitly chose to keep it at 🟡 HYPOTHESIS (strong) rather than promote, pending more evidence or an explanation for the one exception | Claude (AI), capture-re-analysis task; maintainer-reviewed, kept at HYPOTHESIS (not promoted), prompt `0004` |
 | 2026-09-13 | **`ai-sessions/0013_FEATURE_PROMPT_2026_09_13.md` — pending `0012` decisions resolved.** **§4.5.7 Volume Balance** — the ±100 range and `+100`=Left/`-100`=Right polarity promoted to 🟢 FACT (`DECISIONS.md` ADR-026), maintainer-approved in the same chat session that authored this prompt; matching §6 open item closed. **§4.4/§6 Behavior** — Find My Buds Case/"both simultaneously" scope decision resolved (`DECISIONS.md` ADR-027): v1 ships with Left/Right ring only, Case/"both" out of scope absent a future local mechanism; see `PROJECT.md`'s non-goals and `TODO.md`'s Phase 1 item for the corresponding updates. Also this session: mechanical count corrections to `CAP-036-FINDINGS.md`/`CAP-037-FINDINGS.md` (not a `PROTOCOL.md` change), a bounded APK research pass (`REVERSE_ENGINEERING.md`'s `frb`/`fuh`/`glk`/`gjv` entry and a new "GSND" naming-lead entry), and the first real, buildable/tested Android Studio project (`android/`, five Gradle modules, ANC `FrameEncoder`/`FrameDecoder` implemented and unit-tested against real capture fixtures) — none of which touch this document's own body | Claude (AI), maintainer-directed sign-off session, prompt `0013` |
+| 2026-09-13 | **`ai-sessions/0015_MAINTENANCE_PROMPT_2026_09_13.md` — resolved `ai-sessions/0010`'s two remaining sign-off items.** **§6** — the `CAP-037`/`CAP-048` dock-timing anomaly's "(PROPOSAL, awaiting maintainer sign-off)" hedge removed; the explanation itself (a genuine real-time docking action, consistent with `DECISIONS.md` ADR-016) was maintainer-approved, citing `ai-sessions/0015`. No new FACT beyond ADR-016 was introduced — this only closes a previously-open citation. `DECISIONS.md` ADR-024 gained a dated Update recording `CAP-048`'s two counter-example `Settable-toggles` readings as a documented, unreconciled 🟡 HYPOTHESIS exception, maintainer-approved | Claude (AI), maintainer-directed sign-off session, prompt `0015` |
 
 ---
 https://github.com/tedsluis/opencontrolpixelbudspro2/blob/main/PROTOCOL.md - https://tedsluis.github.io/opencontrolpixelbudspro2/PROTOCOL

ai-sessions/0010_CAPTURE_RESULT_2026_09_12.md

@@ -4,7 +4,10 @@
 **Category:** CAPTURE
 **Date:** 2026-09-12
 **Title:** Full video+log re-analysis and FINDINGS for CAP-018, CAP-026, CAP-028, CAP-029, CAP-045, CAP-046, CAP-048, CAP-049
-**Status:** awaiting maintainer sign-off
+**Status:** complete — all 3 originally-pending sign-off items resolved: item 1 (Volume Balance) via
+`DECISIONS.md` ADR-026 (`ai-sessions/0013`); items 2 and 3 (the `CAP-037`/`CAP-048` anomaly and the
+`DECISIONS.md` ADR-024 caveat) approved by the maintainer and applied via
+`ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`
 
 ---
 
@@ -93,15 +96,18 @@ connection-retry burst.
 (per `AGENTS.md` §6/§15 — none of these were self-promoted; all are labeled PROPOSAL in the affected
 documents):
 
-1. **`PROTOCOL.md` §4.5.7 (Volume Balance)** — promote the ±100 range and the
-   `+100`=Left/`-100`=Right direction mapping to 🟢 FACT (`CAP-046-FINDINGS.md` §2, 3/3
-   video-confirmed, zero counter-examples).
+1. ~~**`PROTOCOL.md` §4.5.7 (Volume Balance)** — promote the ±100 range and the
+   `+100`=Left/`-100`=Right direction mapping to 🟢 FACT.~~ **Resolved 2026-09-13** — approved by
+   the maintainer in the chat session that authored `ai-sessions/0013_FEATURE_PROMPT_2026_09_13.md`,
+   recorded as `DECISIONS.md` ADR-026. `PROTOCOL.md` §4.5.7 updated accordingly.
 2. **`DECISIONS.md` ADR-024** — record `CAP-048`'s two video-confirmed counter-examples (stale
    `Settable-toggles` readings on two fresh reconnects) as an explicit, documented exception —
    **not** proposed as a reversal of the existing FACT, proposed as a caveat needing the
-   maintainer's own read on how to qualify it.
+   maintainer's own read on how to qualify it. **Still pending** — see
+   `ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`.
 3. **`CAP-037-FINDINGS.md` §5 / `PROTOCOL.md` §6** — mark this specific anomaly class as resolved
-   (real-time dock-state change, ADR-016-consistent), citing `CAP-048`.
+   (real-time dock-state change, ADR-016-consistent), citing `CAP-048`. **Still pending** — see
+   `ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`.
 4. **`HOLD-005` (`PROTOCOL.md` §4.5.3 / `TESTPLAN_BLUETOOTH_HCI_SNOOP.md`)** — no promotion proposed;
    flagged instead that `CAP-045` did not close this question and a genuine re-run of Group AJ's own
    procedure (open the rotation-checklist screen, not physical long-presses) is still needed.
@@ -110,6 +116,10 @@ documents):
    Conversation Detection's wire-silent pause; the Balance↔Mono-audio timing correlation; the
    `CAP-048` connection-retry burst.
 
+**Update (2026-09-13, `ai-sessions/0015_MAINTENANCE_RESULT_2026_09_13.md`):** item 1 resolved (see
+above). Items 2 and 3 are this file's only remaining open sign-off items — surfaced again to the
+maintainer in `0015`.
+
 ## Uncommitted work
 
 Nothing committed yet this session (project convention: no auto-commits). Uncommitted changes as of

ai-sessions/0015_MAINTENANCE_PROMPT_2026_09_13.md

@@ -0,0 +1,43 @@
+# 0015_MAINTENANCE_PROMPT_2026_09_13.md — Investigate and resolve ai-sessions/0010's remaining sign-off items
+
+**Number:** 0015
+**Category:** MAINTENANCE
+**Date:** 2026-09-13
+**Title:** Investigate and resolve ai-sessions/0010's remaining sign-off items
+
+---
+
+## Mandatory reading order
+
+Per `AGENTS.md` §0.1 and `AI_SESSION_LOG_PROCEDURE.md` §8: `AGENTS.md`, `PROJECT.md`,
+`PROJECT_RULES.md`, and `DECISIONS.md` in full (already read earlier this same chat session, still
+current), plus `ai-sessions/0010_CAPTURE_PROMPT_2026_09_12.md`/`ai-sessions/0010_CAPTURE_RESULT_2026_09_12.md`
+(full), the 8 capture `CAP-NNN-FINDINGS.md` files that session covers (`CAP-018`, `CAP-026`,
+`CAP-028`, `CAP-029`, `CAP-045`, `CAP-046`, `CAP-048`, `CAP-049`), `PROTOCOL.md` §4.1/§4.5.7/§6,
+`DECISIONS.md` ADR-016/ADR-022/ADR-024/ADR-026, and `TESTPLAN_BLUETOOTH_HCI_SNOOP.md`'s matching
+rows.
+
+## Task (verbatim, as given by the maintainer in chat, translated from Dutch)
+
+> It appears that 0010_CAPTURE_PROMPT_2026_09_12.md still needs a sign-off from me. Find out what
+> still needs to happen and update the relevant documents.
+
+## Scope
+
+1. Re-read `ai-sessions/0010_CAPTURE_RESULT_2026_09_12.md` in full, including its "Final summary for
+   the maintainer" section's 5-item sign-off list, and independently verify against the 8 underlying
+   `CAP-NNN-FINDINGS.md` files' own "Proposed" sections that this list is exhaustive (nothing else
+   awaiting sign-off was missed).
+2. For each item already resolved by a later session in this same chat (specifically: Volume
+   Balance's FACT promotion, approved and applied as `DECISIONS.md` ADR-026 in
+   `ai-sessions/0013_FEATURE_RESULT_2026_09_13.md`), update `0010`'s own record to reflect that,
+   per `AI_SESSION_LOG_PROCEDURE.md` §4a.
+3. For each item genuinely still open, surface it to the maintainer as a compact, specific decision
+   with a recommendation — per `AGENTS.md` §6/§15, this session may draft exact proposed text
+   (a `DECISIONS.md` ADR update, a `PROTOCOL.md` edit) but must not commit either without the
+   maintainer's explicit, in-conversation approval.
+4. Once the maintainer answers, apply exactly what was approved and update `ai-sessions/0010`'s and
+   `ai-sessions/INDEX.md`'s status fields to match.
+
+---
+https://github.com/tedsluis/opencontrolpixelbudspro2/blob/main/ai-sessions/0015_MAINTENANCE_PROMPT_2026_09_13.md - https://tedsluis.github.io/opencontrolpixelbudspro2/ai-sessions/0015_MAINTENANCE_PROMPT_2026_09_13