forked from Blendman974/faceclaw
0db295d80293822e56bd66f9247fe4a2b543368d
19
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
c9e95a3f69 |
Refinements to bulitin games
All: settings persistence All: pause on menu Flappy: both swipe directions trigger flaps Freecell: skip irrelevant locations Blocks: Lower speed/difficulty Pinball: remove the half-implemented Nudge gesture. |
||
|
|
70d782a4f1 |
Build out the glanceboard settings app and widgets
<details> <summary>Prompts Used</summary> User: Thanks, looks pretty good. I notice that during the transition from the glanceboard back to off, the glasses display a flash of the main UI. Let's address that. AI: > Fixed and built. The cause was the hide order in the glance host: it hid the glance surface first, which made the compositor recomposite and transmit the sleeping UI's retained window frames, and only afterwards did the screen-off path blank the display. That one transmitted frame was the flash. > > The hide path in `app/g2/glance-host.ts` now blanks the compositor first and hides the surface second. Blanked, the surface change composites to the same black frame, so nothing extra goes to the glasses. The controller's screen-off path still runs afterwards to drop the wakelock and re-arm the 5-second suspend. Its own blank call is now redundant but harmless. > > The double-tap path is unchanged on purpose: there the surface hides while the shell is waking, so the retained UI appearing is the intended result. > > Typecheck and the full Android build both pass. I recorded the finding in `notes/glanceboard.md` with a new checklist item for the timeout and release transitions. Worth re-checking on hardware: both the 3-second timeout and the long-press release should now go straight to dark. <hr> User: Thanks. Next up, let's make a firmware mod so that we can capture tap and tab-and-hold from deep sleep. AI: > Done. Firmware revision 2 forwards tap, long-press, and long-press release from deep sleep, and the phone side consumes them. Everything builds and the tests pass, but nothing is flashed or hardware-tested yet. > > **How the firmware does it** > > Decompiling the display thread showed that with no app on screen, its touch branch launches the dashboard on double-tap or head-up, launches the stock Menu on tap-then-hold, and frees every other gesture unhandled. The call right after that idle gate at `0x45f01a` has the input record in r4 (raw source at +2, gesture subtype at +4). The new hook in `g2flash/patches/settings_ext.c` wraps that call. When Faceclaw holds the wake lease and the firmware is in the mode where a double-tap would have woken the dashboard, it reports subtype 0 (tap), 3 (long press) and 0xe (release) as settings-sid field-102 events 2, 3 and 4, carrying the raw source. The stock result is returned unchanged, so stock behavior is untouched. Unlike the double-tap wake, nothing stock is deferred, so there is no claim or fallback handshake. I verified in the patched image that the site is a branch into the blob, that the shim hands r4 to the C function, and that the function preserves r4. > > **Phone side** > > - Java parses the new events into ordinary sys-events with the protobuf source while the page is suspended, so TypeScript sees exactly the soft-sleep gestures and the Glanceboard logic needs no change. > - The firmware string is now `Faceclaw/2`, the app requires revision 2, and the embedded patch set was regenerated. Onboarding will offer the reflash. > - A Java test covers the event and source mapping, the wake event staying distinct, and malformed payloads. > > **Verification** > > | Check | Result | > |---|---| > | g2flash `build_cfw.sh` | verified, new output hash pinned | > | Faceclaw `build.sh` | success | > | `npm test` | new tests pass; only the pre-existing pinball and compass-style failures remain | > > **Two caveats** > > - I read "tap-and-hold" as press-and-hold, which is the long-press the Glanceboard uses. The firmware's distinct tap-then-hold gesture still opens the stock Menu app from sleep and is not forwarded. Say so if you wanted that one instead. > - Only the right lens notifies the phone. A double-tap on either temple wakes both lenses, so left-temple taps very likely reach the right lens's display thread while idle, but that is unverified until it runs on hardware. The checklist in `notes/glanceboard.md` has the new deep-sleep steps and the logcat line to look for. > > Nothing is committed in either repository. <hr> User: Thanks, that worked. Next up, there's also a screen-on trigger from the accelerometer detecting that you've tilted your head up 45deg. Let's make that trigger go to the glanceboard rather than the main app. (If this requires another firmware extension, go ahead and make it; otherwise use what's already there.) AI: > Done. It did need a firmware extension, so this is firmware revision 3 plus matching phone changes. Everything builds and tests pass; nothing is flashed or hardware-tested yet. > > **Why firmware was needed.** In deep sleep the head-up already reached the phone, but through the same deferred-wake event as a double-tap, so the phone could not tell them apart. In soft sleep, the first five seconds after the screen goes dark, the head-up never reached the phone at all: the display thread's idle gate drops it while an EvenHub page is on screen. > > **Firmware, revision 3** > > - **Deep sleep.** The idle policy's head-up display-start site now goes through its own wrapper. It runs the identical deferred-wake claim-and-ready handshake but reports field-102 event code 5 instead of 1. One deliberate difference: a head-up while a wake is already pending is ignored, instead of the double-tap's emergency stock-dashboard launch, so lifting your head right after a tap cannot flash the stock dashboard. > - **Soft sleep.** The idle-gate call is wrapped, ported from the old head-tilt branch with two extra guards mirroring the stock idle path: the glasses' head-up switch must be on and the stock busy check must be clear. It forwards the head-up as EvenHub sys-event 12 under the framebuffer lease. > - Both hooks and the two wrappers were verified by disassembling the patched image. The output hash is pinned and the embedded patch set in Faceclaw is regenerated. > > **Phone side** > > - Java decodes wake code 5 as a display-wake carrying the head-up event type, and rewrites the soft-sleep sys-event 12 into the same thing. The Glanceboard logic from earlier already treats that as a press, so a head-tilt now shows the board for the timeout instead of waking the main UI. With the Glanceboard toggle off, a head-tilt still wakes the regular UI as before. > - The app now requires firmware revision 3, so onboarding will offer the reflash. > - The Java test covers the new wake code alongside the tap, long-press, and release events. > > **One thing left as is.** Faceclaw does not push the head-up switch or angle to the glasses. The trigger uses whatever the Even app configured, which is what you have today. The old branch's setting for that is not merged. > > The hardware checklist in `notes/glanceboard.md` has the four head-tilt cases: deep sleep, soft sleep, screen on, and head-tilt right after a double-tap. <hr> User: Thanks. Next up, let's make a glanceboard widget for the Calendar. AI: > Waiting on the Android build; the widget, its registration, and the notes are done. <hr> User: Thanks. Next up, let's make a glanceboard widget for the Terminal app. This will show the same terminals (including, especially, activity indicators) as the terminal list window and reuse some code from it. If the window title is too long to fit, we truncate rather than wrap. Also, if a terminal has a window open, that window's number will be shown in a left column in the terminals list (both the terminal-list window version and the glanceboard version). This will replace the "[open]" tag currently at the end of the line. <hr> User: Continue AI: > The Terminal widget is in, the hub list has the new number column, and the build passes. Not yet tried on hardware. > > **Getting the list to the main thread.** The Terminal app lives in a worker, so the widget cannot read its state directly. I added a small generic channel: a worker can post a `publish-state` reply with a key and a JSON value, and the host stores it in a main-thread registry with change notifications. The Terminal worker publishes a session snapshot under `terminal:sessions` whenever the hub would repaint, deduplicated by content. Each row carries its label, the open view window's sidebar glyph, and an activity deadline in the phone's clock, so the widget can blink and expire indicators on its own 800 ms timer without further messages. > > **Shared row painter.** `app/apps/terminal/session-list.ts` now holds one `drawSessionRow` used by both the hub and the widget: activity square in the gutter, the window number column, then the label truncated to fit, never wrapped. The hub used to draw labels untruncated, so it gains that too. > > **The number column.** A session with an open view window now shows that window's sidebar glyph, "1", "2" and so on, in a column left of the label, in both the hub and the widget. The "[open]" suffix is gone from the list. The assistant's list-sessions tool text says "[open in window 2]" instead. > > **Widget layout** at 288x144: "Terminal" label, then host headings only when more than one host is connected, then session rows, as many as fit. Empty states cover no connections, connecting, and no live sessions. > > **One limitation to know about.** The snapshot exists only once the Terminal app has been opened in this app session, because that is when the worker and its g2mirror control clients start. Before that the widget says to open the Terminal app. Since the shell restores open apps at boot, a hub left open carries across restarts. Making the worker start its control clients at boot without a window is a possible follow-up if you want the widget live from launch. > > Checklist entry 7c in the design note covers the blink sync, the number column in both views, and truncation. Nothing is committed. <hr> User: Thanks. Next up, let's make it so that selecting a widget for a slot that's already used in another slot clears that slot, _except_ that certain widgets that support it can occupy both left slots or both right slots, in which case they render at double height and the line between the slots is removed. We'll implement double-height for the Terminal and Calendar widgets. AI: > Done. Slot uniqueness and double-height regions are in, with a node test for the pure part, and the build passes. > > **The rule** lives in two places that share one adjacency helper in the layout module: > > - **When a picker changes**, the config app clears every other slot holding the same widget, unless the widget is marked tall and that slot is vertically adjacent to the one just chosen. So picking Terminal for Bottom left while it is in Top left keeps both, and then picking it for Top right clears both left slots. This runs from the picker's change hook and goes through the settings broadcast, so the board and the other rows follow on their own. > - **When the board paints**, it resolves the slot choices into regions. A tall widget in two vertically adjacent slots becomes one 288x288 region and its widget gets the taller canvas. Dividers are drawn per region, so the line between the merged slots disappears. > > **Tall widgets.** Terminal and Calendar are marked tall. Both already lay out rows until they run out of height, so at double height they simply show more sessions or more events with no widget code changes. The other widgets stay single-slot. > > **Region diffing.** The board keys live regions by widget plus slots and restarts only what changed on a settings change. Switching a widget from single to tall restarts just that widget; unrelated widgets keep their subscriptions and hardware holds. > > **Verification.** `tests/glanceboard-layout.test.cjs` covers adjacency, left and right merges, non-spanning and diagonal duplicates staying separate, and empty boards. Typecheck and the Android build pass. The design note has a checklist step for the three picker cases. Nothing is committed. <hr> User: Thanks. Let's organize the Glanceboard configuration app into several screens. The entry page will have a title, a paragraph of text describing how the glanceboard works, and a menu with an "Enable Glanceboard" toggle, Preview, Select Contents, and Settings. Settings will contain: * "Show on tap", which instead of a toggle will be a duration (from a list of options 3s, 5s, 7s, 10s, default 5s) * "Show on long press", which will be a toggle * "Show on head tilt", which will be a toggle * "Show lines", which will toggle visibility of the quadrant-separator lines Fable 5.1: > The Glanceboard app is now three screens, the four settings are wired through, and the build and tests pass. > > **Entry page.** Title, a short paragraph on how the board works, and a menu drawn on the same page below it: Enable Glanceboard (toggle, the existing setting relabeled), Preview, Select Contents, Settings. Double-tap on the entry page yields to the sidebar as before; on the sub-screens it goes back. > > **Select Contents** is the slot pickers page from before, including the one-widget-per-board rule and double-height merging. > > **Settings** holds: > > - **Show on tap**: a duration picker, 3, 5, 7 or 10 seconds, default 5. The head-tilt uses the same duration since it behaves as a tap. > - **Show on long press**: toggle. Off means a hold while asleep does nothing. A release still passes through so a hold already in progress can end. > - **Show on head tilt**: toggle. Off sends the head-tilt wake to the regular UI, the pre-Glanceboard behavior. > - **Show lines**: toggle for the slot dividers. > > **Wiring.** The gesture policy moved out of the controller into the glance host, which asks the board provider for the four values. The timeout is handed to the state reducer per event, so the pure module stays testable; a new test covers the supplied timeout. The master toggle off still makes every sleep gesture a no-op. > > The design note's checklist has a step per setting. Nothing is committed. <hr> User: Thanks. Let's maket the menu half width, and use the space on the right for a preview with the quadrant-separator lines and the title of what's in each slot. Instead of "Select Contents" opening a separate page, it will move the focus to that view, so you can pick one of the quadrants there and tap to open a menu of what goes in that quadrant. The four-quadrants preview will show the lines between them; if the show-lines setting is disabled, they'll be reduced to min brightness and dotted (every other pixel). The preview will omit the line between quadrants as appropriate for double-height views. Fable 5.1: > The entry page now has the half-width menu on the left and the slot preview on the right, with Select Contents working inside the preview. Build and tests pass. > > **Preview.** The right half shows the board scaled down with its slot dividers and the name of the widget in each region, or "Empty". A double-height region shows one name and no line across it. With "Show lines" off, the dividers drop to the dimmest visible shade and light only every other pixel, so the layout still reads but signals off. > > **Select Contents.** Choosing it moves focus into the preview instead of opening a page. Scroll moves a highlight between the four quadrants, a tap opens a modal picker for that slot with the current choice marked, and picking applies the same one-widget-per-board rule as before. The preview updates as soon as a choice lands. Double-tap returns focus to the menu. While the preview has focus the menu's selection shows as outline only, following the shell's convention that a filled selection means it has input. > > **Shared geometry.** The divider layout moved out of the board into a pure helper in the layout module, so the live board and the preview draw the same lines, including the merged-region rule. A new test pins the four-slot and tall-Terminal cases. > > The design note's checklist has a step for the preview interactions. Nothing is committed. <hr> User: Thanks. One fix: while the quadrants-preview is selecte, double-tap back currently goes to the app-switcher, but should go to the glanceboard menu. We can also remove the gesture-help below the preview. Fable 5.1: > Fixed and built. The cause was the root wrapper that turns any double-tap at the app's root into a yield to the sidebar, which ran before the page could see the gesture. > > The home page is now the window's root without that wrapper and routes double-tap itself: with the preview focused it returns focus to the menu, with the menu focused it yields to the sidebar as before. The gesture hint under the preview is gone. > > Typecheck and the Android build pass. Nothing is committed. <hr> User: Thanks, looks good. Let's make the lines in the glanceboard (on the real glanceboard, not the configuration widget) dimmer. In the Terminal glanceboard widget, with my configured font size (Roboto Light 12), there is room for one more row. It does seem to be responsive (when I increased the font size to 18 the row count dropped accordingly) but the bottom boundary might be above where it could be. Let's add IOB to the Nightscout glanceboard widget. Also include any of cannula age, cartridge volume, battery voltage, and time since last loop that breach the limits configured in Nightscout settings (if they aren't already included), and double check that the glucose value is crossed out if it's too old. Fable 5.1: > All three done, typechecked and built. > > **Dimmer lines.** The live board's dividers dropped from shade 40 to 20, the dimmest level that survives the 4-bit quantization. The configuration preview keeps its own brighter lines. > > **Terminal rows.** The bottom bound was stricter than it needed to be: it required a full line step, which includes inter-line spacing, to fit above an 8 px bottom pad. Rows are still placed a step apart, but the last one now only needs its glyph line height to clear a 2 px margin, and the gap under the "Terminal" label lost two pixels. With a 12 px font that admits one more row. The Calendar widget got the same rule for consistency. > > **Nightscout widget.** IOB now follows the age line. Below that, only fields breaching the limits from Nightscout settings appear, inverted the way the app marks them: cannula age, reservoir volume, pump battery voltage, and loop age, one per line while room remains. Nothing shown means nothing is out of range. The strikethrough was already correct: the value is crossed at mid-height once the reading is older than the app's 15-minute limit, using the app's own helper. I added a comment saying so. > > Nothing is committed. </details> |
||
|
|
8a340fc4ad | First iteration of glanceboard | ||
|
|
b0cf1e4f67 | Switch from capability strings to numeric versioning for firmwares | ||
|
|
adf9fa89c4 | Add R1 ring battery indicator | ||
|
|
813668f850 | Merge branch 'main' of https://github.com/jimrandomh/faceclaw | ||
|
|
070c891577 |
Enhancements to Nightscout and Terminal apps
Nightscout app: Alert thresholds for canula age, cartridge volume, pump battery, time since last loop, shown in top bar. Option to always show in top bar when window is closed. Terminal app: Activity indicators in the app-switcher sidebar. </details> |
||
|
|
083628f37a | Display compass diagnostic information | ||
|
|
1524766996 | Add screen-size setting to Navigate and Terminal apps | ||
|
|
758cf7de3b | Add teleprompter app | ||
|
|
f601a62c75 | Rewrite the Timer app | ||
|
|
052398d401 | Update EvenHub compatibility layer to support new functionality (context menus and some other things) from 0.0.14 | ||
|
|
e1c4628566 | Merge branch 'main' of https://github.com/jimrandomh/faceclaw into calculator | ||
|
|
6cd7d5fff9 | Watch display shows if glasses are charging or silent mode | ||
|
|
20026c918a |
Replace Unicode property escapes, which crash the glasses' V8
The NativeScript Android runtime embeds a V8 built without ICU, so a regex
literal containing `\p{...}` cannot be parsed there. Because the app ships as a
single ES module, the three such literals added with the calculator and
microphone apps made the whole of bundle.mjs fail to compile:
com.tns.NativeScriptException: Cannot compile ES module .../app/bundle.mjs
SyntaxError: Invalid regular expression: /\p{L}/: Invalid property name
That throws inside Application.onCreate, so the app died on launch before any
of its own code ran — every screen, not just the two new ones. Neither tsc nor
the test suite caught it: the syntax is valid ES2018 and node has ICU.
app/util/unicode-class.ts replaces them with explicit ranges. The two uses pull
in opposite directions, so they are stated differently:
- isLetter (maths lexer) is a letter table. The lexer's alphabet is small and
known, and an unrecognised letter just becomes an identifier matching no
known function, which is already a handled error.
- NON_WORD_RUN (conversation search, sentiment) is a *separator* table rather
than the complement of that letter table. Complementing it would make every
letter the table omits — minority scripts, later Unicode additions — act as
a separator and silently shred that text; listing separators instead keeps
an unlisted character as word content. It also holds decomposed graphemes
together, which `\p{L}` did not.
Verified against the real properties under node's ICU: identical output on a
prose corpus except where the new split is better (a Lao vowel sign and a
combining acute now stay attached).
The new test's last case scans app/ for `\p{` outside comments — the check that
would have caught this before it reached a device.
|
||
|
|
fe85846e6f |
Add calculator and microphone conversation apps
Add symbolic math and graphing tools, dual-microphone audio processing, live captions, translation, speaker diarization, sentiment analysis, and searchable conversation history. Extend Android voice and BLE support for microphone control, recording, transcoding, and on-device speaker identification, with coverage for calculator and microphone workflows. |
||
|
|
fea29c5ff3 |
Add a bunch of refinements to the pairing process
<details>
<summary>Prompts Used</summary>
Thanks. Let's address 1-8. We can leave the setLegacy(false) in place as too-old phones are already unsupported for other reasons. Let's pause the scan and timer when the app is backgrounded and resume it when it's foregrounded again. Let's deduplicate and clean up the things mentioned in that section. We don't need to support single-arm pairing at all; the glasses themselves won't boot/function unless both temples are working.
I tested on-device and also noticed some dark-mode issues and minor UI cleanup. The instructional text at the top ("Take the glasses out of there case [...]") is dark-on-dark if in dark mode. The background behind the glasses, ring, and selected cards is light-blue (regardless of dark mode); some of the text on it is white and some is black. Let's keep the card background the same in light mode and make it dark-gray in dark mode.
> All fixes are implemented, tested, and committed as `1718253` on `bluetooth-pairing-improvements` — but one thing needs your decision before the PR itself updates (details at the end).
>
> ## What landed
>
> **Findings 1–8**, as requested:
>
> 1. **Auto-reconnect** — `onPairGlassesTap` now calls `resumeAutoReconnect()` right after the pre-scan disconnect (pairing is a detour, not a Disconnect), so the main page's `autoConnect` picks the glasses back up on return. The config page's "Scan for glasses" now also drops the live link first (lazy-required controller so onboarding still never instantiates the singleton).
> 2. **Mixed-arms warning** — `pairs()` groups by a new canonical `serialKey()`, and when exactly one lone left and one lone right with different serials are visible, both rows now carry the "arms from two different pairs" warning. (The old per-row check was provably unreachable, since a serial-keyed group can't contain two serials.)
> 3. **Degrading selection** — `refresh()` deselects a pair that regresses below complete, and `onPrimaryTap` refuses to save a one-armed pair instead of padding it with stored addresses. Since single-arm pairing is unsupported, the identity is now always saved on a pair save.
> 4. **ingest() clobbering** — a manufacturer-data-less record (bonded re-emit or split report) no longer overwrites note/flag/name learned from a full advertisement; additionally, a split report that fails to classify on its own is retried with the remembered name/manufacturer data, so a nameless half no longer drops the arm.
> 5. **TX power** — `estimateProximity` no longer takes a TX-power argument at all; the calibration table is the only reference, and confidence no longer rewards an advertised value.
> 6. **Ring identity** — a ring-only save updates `ringName`/`ringAddress` in the stored identity.
> 7. **Ring detection** — TS requires the stock `EVEN R1` prefix; Java admission tightened to match (still a strict superset).
> 8. **One-shot scans** — `scanCandidates` keeps every sample, and `buildAddressSet` runs them through `DiscoveryAggregator`: left/right come from the closest serial-joined *complete* pair. Bonded-only batches (no serials anywhere) keep the old per-role fallback so "Load paired devices" still works. `setLegacy(false)` left as-is per your call.
>
> **Backgrounding** — the pairing model hooks Application suspend/resume: scan + 500 ms timer stop on suspend and restart on resume, with the hooks detached when the page is truly left (back navigation, Save, Cancel).
>
> **Cleanup** — one MAC normalizer (`normalizeMacAddress`, now in the pure advertisement module, re-exported by device-addresses, used for the ring "Yours" compare); one serial-equality definition (`serialKey`/`serialsMatch`, containment fallback removed); shared `formatErrorMessage` replaces five copies (there were 5, not 3); shared `app/util/hex-util` replaces the duplicate TS hex codecs (firmware-builder keeps its strict validation as a thin wrapper); one Java `bytesToHex` in `FaceclawFirmwareUtil` replaces three; `glassesRow`/`ringRow` share a presentation-base helper; dead row-address fields, `glassesSectionVisibility`, the identical-branch ternary, and `zoneRank`/`ZONE_ORDER` deleted; `.test-build/` added to `.gitignore`.
>
> **Dark mode** — light mode is untouched; in dark mode the instructions and empty-state text get light grays, all cards go dark-gray (selected keeps a blue border on a blue-tinted dark gray), and every card text color has an explicit dark-mode counterpart so nothing mixes white and black on one card. Worth a quick on-device look since I can't verify colors visually.
>
> **Verification**: `npm test` — 60/60 pass including 5 new tests (mixed-arms warning, bonded-re-emit preservation, split-report merge, strict ring prefix, TX-power arity pin); `build.sh` and `tsc --noEmit` clean; Java compiles in the Gradle build.
>
> ## The catch: PR #13 is from a fork
>
> PR #13's head branch lives in **kalanihelekunihi/faceclaw**, not your repo. My `git push origin` created a same-named branch in *your* repo (which doesn't touch the PR), and when I then tried to push to the fork's branch (allowed — the PR has "maintainer edits" enabled), the permission gate blocked it, sensibly, since it writes into someone else's repository. Your options:
>
> - **Update the PR**: `git push https://github.com/kalanihelekunihi/faceclaw.git bluetooth-pairing-improvements:bluetooth-pairing-improvements` — the local branch contains their commit plus your merge of main plus the fixes.
> - **Or merge directly**: the fixed branch is already at `origin/bluetooth-pairing-improvements` in your repo; merge it to main and close PR #13 with a comment. (If you go this route, note the accidental branch on origin is the thing you'd merge — otherwise you may want to delete it.)
<hr>
Thanks. Next up, after selecting devices and clicking Continue and advancing to the "Checking Firmware" stage, the check fails with "no response to the device-info query". This was when testing on a device that hasn't previously been paired with the glasses (as opposed to the more common case of a device taking over an already-bonded connection that was created by the stock Even app and remembered in Android's paired devices list), when connecting to glasses with stock firmware 2.2.9. I believe this was preexisting and not introduced in this branch. I have a logcat from the run in ~/tmp/a9_logcat.
Possibly relevant: Firmware version 2.2.9 changed some details of connection and pairing, which broke `g2flash`. A writeup of what changed is in ../notes/ble-connections-2.2.9.md.
> Done. Here's the summary:
>
> ## Root cause — confirmed
>
> The logcat corroborated the 2.2.9 writeup exactly. At 14:09:43 the phone opened an ACL connection to `Even G2_32_R_820967` (the probe connecting to the right arm), and it dropped 5.5 s later — connect + discovery + prelude ack + the probe's 4 s query timeout, then the probe closing. Critically, **no SMP pairing or bonding activity appears anywhere in that window**: nothing ever asked the lens to authenticate or encrypt. On 2.2.9, the firmware acks the prelude but won't answer the settings query until the sid-0x80 security-auth exchange completes over an encrypted link — and on a never-bonded phone, that exchange is also what triggers SMP pairing in the first place. The probe (like every Faceclaw connection path) never sent it, so it only ever worked by inheriting a bond the stock Even app had created.
>
> ## The fix (committed as `1bde70a`, pushed to `origin/bluetooth-pairing-improvements`)
>
> Implemented the authentication exchange from `../notes/ble-connections-2.2.9.md` (the g2flash-validated wire format) across all four connection paths:
>
> - **`BleProtocol`**: `buildAuthenticationRequest(magic)` (f1=4, f2=magic, f3={f1=1,f2=4} on sid `0x80`, flag `0x00`) and `isAuthenticationSuccess` (strict per the writeup: command 4, matching magic, empty `1a 00` result — a completed GATT write is not success).
> - **Device-info probe** (the failing path): authenticates after subscribing, before the prelude, with a 30 s window since a first-time connection may sit waiting on the OS pairing dialog — the check page now shows *"Authenticating with your glasses... If Android asks to pair, tap Pair."* I made this one **soft**: the probe also runs against the custom firmware, whose response to the exchange isn't hardware-verified, so an unconfirmed auth falls through to the query as before — but a query timeout after unconfirmed auth now says the pairing didn't complete instead of the bare "no response" you saw.
> - **Flash-prompt communicator**: authenticates each arm before the prelude, mandatory (it only ever talks to stock firmware).
> - **Firmware flasher**: control-channel notifications are now mandatory, each lens authenticates before OTA `BEGIN`, and I removed the OTA-time heartbeat entirely per the writeup's follow-up list — official captures show no control traffic mid-transfer, heartbeats demonstrably don't satisfy the 2.2.9 deadline, and a concurrent control writer interleaves with the marker/data transactions. The envelope counter also resets after bring-up, mirroring the stock sequence.
> - **Main communicator**: authenticates both arms after connecting, before the prelude, with a short (6 s) soft wait that logs and continues on timeout — so firmware that never answers can't stall every reconnect, while stock 2.2.9 (e.g. the incompatible-firmware detection path) gets a working session.
>
> Build passes (webpack + Gradle/Java). Left `setLegacy(false)` and everything else untouched.
>
> **Hardware tests to run**: fresh-phone onboarding against stock 2.2.9 end-to-end (check → on-lens prompt → flash — expect one Android pairing request per lens the first time), and a regression pass on custom-firmware connect + re-check. One thing to watch: if the CFW turns out not to answer the auth request, the probe adds ~30 s per check on CFW glasses — if you see that, tell me and I'll gate the long wait on bond state.
<hr>
Hmm, that did make it pair fully (which if nothing else is necessary for the next step where we actually flash firmware), but I'm still getting "no response to the device-info query".
One thing to check: Are we sending the message and expecting the response on the correct lens? Some messages are right-lens-only and this might be one of them.
> Pushed as `a7684f6`. Here's where the investigation stands:
>
> ## Answer to your lens question
>
> I checked the routing against every reference we have, and the probe *is* doing what the pre-2.2.9 world says is correct:
>
> - The probe sends prelude + settings query to the **right** arm — same as Faceclaw's main communicator (`MessageBuilder.batteryQuery()` has `isLeftArmMessage=false`), which is the path that works when bonded.
> - `g2-kit-unofficial`'s `transport.md` is explicit: "For most things we only use the **right arm**… The L arm is silent on async channels," and its `settings.ts` sends the same query shape (commandId=2, `settingInfoType=BASIC`) to the right-arm session.
> - But: all of that predates 2.2.9, and `g2flash.py` — the only thing hardware-validated against 2.2.9 — never does a settings read at all (auth + OTA only). The 2.2.8-app capture slice also contains no settings read. So **nobody has a verified 2.2.9 settings-read exchange**, and your hypothesis can't be ruled out from references.
>
> One telling detail from your report: the error text you got was the *plain* "no response…" variant, which the probe only produces when the auth exchange **succeeded** (an unconfirmed auth appends a pairing hint). So on 2.2.9 the right lens acks the prelude, completes security auth, and still won't answer the settings read — the auth gate wasn't the (whole) story for this particular message.
>
> ## What I changed — one run should settle it
>
> Rather than guess again, the probe is now an instrumented experiment:
>
> 1. **Full frame tracing** — every control-channel frame in both directions (sid, flag, protobuf type, magic, fragment info, payload hex prefix) plus every write logs under the `FaceclawDeviceInfo` tag. If the lens is answering with an unexpected flag, a different magic, a fragmented frame, or a device-initiated push we've been dropping, it will be in the trace.
> 2. **Query retry** — the read is attempted twice per lens before declaring silence.
> 3. **Push acceptance** — any sid-0x09 frame that parses to firmware versions is accepted as the answer even if it doesn't match our magic (in case 2.2.9 pushes the snapshot on its own magic instead of acking reads).
> 4. **Left-lens fallback** — if the right lens stays silent, the probe runs the identical connect → auth → prelude → read against the **left** lens and uses its answer, logging which lens replied. That's your hypothesis tested directly, in the same run.
>
> Build passes. When you re-run the check, please grab the app-side log — last time's capture only had the system buffer, so none of the probe's own lines were in it:
>
> ```
> adb logcat -s FaceclawDeviceInfo
> ```
>
> That trace will show exactly what each lens said (or didn't), and whichever way it comes out, we'll know whether the fix is "query the left lens", "match the response differently", or something 2.2.9-new.
<hr>
Thanks. There's now a filtered logcat file at ~/tmp/logcat_deviceinfo and an unfiltered logcat at ~/tmp/logcat.
> Mystery solved — and the check is passing on your fresh device now. Here's what the trace showed:
>
> ## What the frames said
>
> 1. **The right lens is the correct endpoint after all.** Every successful read came from the right lens; the left-lens fallback never fired.
> 2. **The real culprit was a post-prelude drop window.** In each failing sequence: auth succeeds → prelude acked → our settings read (magic 101) goes out → and right around it the *lens* starts sending its own sid `0x80` notifications (flag `0x01`, command 4, device-chosen magics like 252/104, payload `{f1:1}` — a shape distinct from both our request and the success ack, repeating ~2 s apart). A read that lands inside that window is silently swallowed. The retry 4 s later (magic 102) was answered within ~100 ms, every single run. In the one run where the lens's notification arrived *before* our read, the first read succeeded immediately — so it's a brief busy window, not a rejection.
> 3. So the fresh-phone failure was two stacked problems: missing auth prevented pairing entirely (fixed last round), and once auth existed, the first read still intermittently fell into this window (fixed by the retry). The earlier `17:13:36` line in your log even shows one lucky success on the previous build — it was always timing-dependent.
>
> ## Follow-ups (pushed as `3e44083`)
>
> - **Flash-prompt page-create now retries once too** — it writes at exactly the same post-prelude moment, so it would have hit the same window intermittently when you proceed to the actual flash step.
> - **Documented the finding** in `../notes/ble-connections-2.2.9.md` as a new "Post-prelude drop window and device-initiated sid-0x80 notifications" section, including the observed frame bytes and the guidance to retry the first post-prelude request.
> - The probe's frame tracing is still in place — it'll be useful when you test the flash itself.
>
> One open question I noted in the writeup: we currently ignore the lens's own sid-0x80 notifications and saw no ill effect in these short sessions, but if a long-lived stock-firmware connection (the main communicator's incompatible-firmware detection) ever misbehaves, those unanswered notifications would be the first suspect — we don't know whether the stock app replies to them.
>
> Next step when you're ready: the flash path itself on this fresh device — the flasher now authenticates per lens and streams without heartbeats (matching the hardware-validated g2flash sequence), but that's the one leg still untested on hardware.
<hr>
Another developer reported running into a Samsung-device-specific issue where inbound (glasses-to-phone) messages larger than 64 bytes were truncated. The response to the Settings message (containing the firmware-extensiosn string) is larger than that, and it might be packaged in a way where truncation causes the packet to be dropped entirely. I tested on a different device and it looks like the no-settings-reply issue only replicates on the Samsung tablet.
> Pushed as `b952cc2`, and the workspace note is corrected. Summary of how the Samsung report changes the picture:
>
> ## Reconciling the report with the trace
>
> The 64-byte theory fits everything, with one important detail: nothing arrived at the app for the missing replies — the probe's tracing logs every value delivered on the control characteristic, even unparseable ones, and `FaceclawBleManager` filters nothing. So on this tablet, oversized values are being *dropped below the app layer*, not truncated-and-delivered.
>
> The size arithmetic supports it: every frame the tablet did deliver was ≤55 bytes (the steady-state settings reply is 8+47). The missing first reply would only trip a 64-byte limit if it were larger — either the firmware's first reply carries a fuller snapshot, or it gets coalesced into one notification value with one of those lens-initiated sid-0x80 notifies (11-byte frame + 55-byte frame = 66 bytes > 64). Both variants explain why the other device never reproduces it, why the retry (compact reply) always lands, and why the one run where the notify had already been delivered separately succeeded first try. If you still have the other device's `FaceclawDeviceInfo` trace, one line would settle which variant it is: the `len=` of its *first* settings reply (47 → coalescing; >55 → fuller first snapshot).
>
> ## What I changed
>
> - **`BleProtocol.splitFrames()`** — splits a notification value into its individual `aa21`/`aa12` envelope frames. This fixes a real latent bug the theory exposed: we only ever parsed the *first* envelope per value, so a coalesced second frame was silently dropped even on healthy devices. The probe, flash-prompt communicator, and flasher control channel now process every frame in a value.
> - **Better tracing** — the probe logs multi-frame values with the raw value size, and marks any frame whose actual length falls short of its declared length as `TRUNCATED`. If Samsung ever delivers a truncated value rather than dropping it, the next trace will say so explicitly.
> - The first-request retries from last round remain the workaround for values the Samsung stack drops outright — that's what already makes the check pass on the tablet, and the flash prompt has the same insurance.
>
> ## The residual exposure worth deciding on
>
> The onboarding flow itself should now be Samsung-safe: all flasher OTA acks are 12 bytes, the auth reply is 19, the prompt-page acks are small. But **after** flashing, the custom firmware's settings reply carries the capability string — well over 64 bytes in a single frame. On this tablet the main communicator would never see it and would report "firmware not detected", and no app-side code can recover bytes the stack never delivers. Since you control the CFW, the durable fix is firmware-side: have the CFW chunk its lens-to-phone notifications at ≤64 bytes (or split the caps into a separate small frame) — that work lives in the g2flash patches repo, not here. I've noted this in `../notes/ble-connections-2.2.9.md` and memory so it doesn't get lost when you hit it.
<hr>
Let's replace the single "Retry" option with three buttons "Retry", "Install", and "Skip" (Install proceeding as if we had detected stock firmware, skip proceeding as if we had detected compatible custom firmware).
<hr>
Continue
<hr>
Continue
> Done — pushed as `9adff01`.
>
> When the firmware check lands in the error state, the button row now offers four actions:
>
> - **Install / Skip** (new row, error phase only):
> - **Install** navigates straight to the flash page with `mode: "install"` — identical to what the "Install Firmware" button does after a real stock-flashable detection.
> - **Skip** routes through the same `applyClassification("custom", …)` path as a genuine custom-firmware detection, which matters for one subtlety: if the phone-side G2 fonts haven't been extracted yet, Skip still runs the font download/extraction step before showing "you're all set" with Finish, rather than completing onboarding with EvenHub fonts missing.
> - **Back / Retry** keep their existing places, with Retry remaining the primary action.
>
> Both new handlers are guarded on the error phase so a stale tap can't fire them from another state, and the row collapses everywhere else. Build passes; visual check on the tablet pending as usual.
<hr>
Let's make some refinements to the onboarding flow.
On the initial splash screen (Faceclaw / Perching on the faces of giants / logo), the logo is a black-on-transparent image. This looks reasonable in light mode on a phone-sized screen, but on a dark-mode tablet it's too low contrast, is too close to the top (we'd like it vertically centered), and is too small.
On the "Pair Your Glasses" screen, we will remove some unnecessary UI elements. In the list of glasses and list of rings, there's a "Closest" badge; hide that badge unless there is more than one entry in the list for it to be closer-than. Keep the signal-strength-out-of-four estimate, but remove the conversion to estimate distance in cm/m. Remove the line that says "Advertising" from the ring. Remove the log display from the bottom (it says "scan started (unfiltered, low latency)" and if you press the pause button also "scan stopped").
On the "Flashing Firmware" page, we have a progress bar with step-size based on the number of segments uploaded so far. Since the update package is one large segment and five small ones, this makes it progress very unevenly. Weight the sizes by segment size.
On the "Configure Devices" screen, the Save and Back button positions are swapped (Back should be on the left, Save on the right). If the device is in dark mode, the text boxes for right arm/left arm/R1 ring MAC addresses are white-on-white.
> All four refinements are in place; the build (webpack + Gradle) succeeds and all 59 node tests pass.
>
> **Splash screen** (`onboarding-page.xml`, `onboarding-view-model.ts`, `app.css`): Step 1 now renders as its own vertically-centered stack (headline, tagline, logo) instead of sharing the top-anchored ScrollView with steps 2–3. The logo height scales to ~40% of the screen height (capped at 480dp so the 306×512 PNG doesn't upscale into mush), and a new `.ns-dark .onboarding-logo { tint-color: #e6e6e6 }` rule tints the black-on-transparent art light in dark mode.
>
> **Pair Your Glasses** (`pairing-candidates.ts`, `ble-proximity.ts`, `pairing-view-model.ts`, `pairing-page.xml`): `nearestCandidateId` now returns null for a single-entry list, so the "Closest" badge only appears when there's something to be closer than (the "Yours" badge is unaffected). The proximity line keeps the ●●●○ glyph and zone label but drops the cm/m distance — I deleted `formatDistance`/`proximitySummary` from ble-proximity entirely since the pairing list was their only consumer. The ring's "Advertising" line is gone (rows only show "Paired with this phone" when bonded, with a visibility binding so empty lines don't take space), and the diagnostics log at the bottom is removed along with its view-model plumbing and CSS.
>
> **Flashing Firmware progress** (`FaceclawFirmwareFlasher.java`, `FaceclawFirmwareFlasherListener.java`, `firmware-flasher.ts`, `onboarding-flash-view-model.ts`): the Java flasher now reports `bytesSent`/`bytesTotal` across the whole lens image alongside the existing component/block indices, and the progress bar is driven by the byte ratio instead of stepping evenly per component — so the one large segment no longer makes the bar crawl and then sprint. The "part 2/6, block x/y" status text is unchanged.
>
> **Configure Devices** (`config-page.xml`, `app.css`): Back is now on the left and Save on the right. The white-on-white fields came from the app's unconditional `TextField { background-color: #ffffff }` colliding with the theme's `.ns-dark TextField { color: white }`; a new `.ns-dark TextField` rule gives dark fields with light text (placed before the `.system-name-modal` rule so that deliberately light modal still wins its tie).
>
> These are phone-UI changes verified by build and unit tests only — worth a quick visual pass on the dark-mode tablet, and the byte-weighted progress bar will only show its behavior during a real flash.
</details>
|
||
|
|
17182532f4 |
Address review findings for the proximity-pairing PR
Correctness: - Pair-glasses flows no longer strand the app in the manual-disconnected state: the pre-scan disconnect is followed by resumeAutoReconnect(), and the config page's scan hand-off drops the live link too. - The mixed-arms serial warning is reachable now: pairs() groups by the canonical serial key, and a lone left + lone right with different serials get the mismatch warning on both rows (it previously required two different serials inside one serial-keyed group, which cannot happen). - A selected pair that degrades to one arm (prune while the page is open) is deselected, and Save never pads a missing arm from stored addresses. - DiscoveryAggregator.ingest no longer lets a bonded re-emit or split advertisement overwrite the note/name/flag learned from a full advertisement, and reclassifies split reports using remembered fields so a nameless half doesn't drop the arm. - estimateProximity ignores the advertised TX Power Level (radiated power, not measured-power-at-1m); the calibration table is the only reference. - Saving a ring without a glasses pair updates the stored identity's ring name/address instead of leaving the previous ring on record. - Ring detection requires the stock "EVEN R1" name prefix in both the TS classifier and the Java pre-filter; a bare "R1" substring matched unrelated devices, and ring rows are always selectable. - One-shot scans keep every sample (buildAddressSet merges them through DiscoveryAggregator), and flash-flow address resolution takes left/right from one serial-joined complete pair instead of latest-per-role. Lifecycle: - The pairing scan and its refresh timer pause on app suspend and resume with the app, and the model's app-event hooks are detached when the page is left for good. Cleanup: - One MAC normalizer (even-advertisement.normalizeMacAddress, re-exported by device-addresses), used for the ring "Yours" comparison too. - One serial-equality definition (serialKey/serialsMatch); the containment fallback in isPreviouslyPaired is gone. - Shared formatErrorMessage replaces five per-view-model copies; shared hex-util replaces the duplicate TS hex codecs; one Java bytesToHex in FaceclawFirmwareUtil replaces three hand-rolled encoders. - glassesRow/ringRow share a presentation-base helper; dead row address fields, the constant glassesSectionVisibility, the identical-branch status ternary, and zoneRank/ZONE_ORDER are removed. - .gitignore now actually covers .test-build/ as tests/README claims. UI: - Dark-mode styles for the pairing page: readable instructions, dark-gray cards with consistent light text; light mode keeps its current look. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016ZqzwmRQ3HQxasBz5rYyZV |
||
|
|
aaaa7288ee |
Add proximity-based pairing for Even devices
Stream BLE advertisements into a dedicated pairing flow with arm, ring, serial, and hardware variant detection. Add proximity ranking, device artwork, pairing safeguards, and unit coverage for discovery and candidate grouping. |