From e161941672b5d600e7c8bcbcd78c2ccf4d101f99 Mon Sep 17 00:00:00 2001 From: Krzysztof Kallas Date: Sat, 26 Sep 2026 17:14:37 +0200 Subject: [PATCH] Technician tool v0.3 Imported from the Google Drive folder 004-technician_tool/v0.3. --- docs/firmware-diagnostics-proposals.md | 90 ++ kota_tech/__init__.py | 2 +- kota_tech/diag/engine.py | 24 +- kota_tech/diag/guides.py | 400 +++++++++ kota_tech/diag/guides.toml | 715 +++++++++++++++ kota_tech/diag/rules.toml | 1137 ++++++++++++------------ kota_tech/ui/cheatsheet.py | 3 +- kota_tech/ui/guide_panel.py | 216 +++++ kota_tech/ui/main_window.py | 29 +- pyproject.toml | 2 +- run_macos.command | 2 +- run_windows.bat | 2 +- tests/test_guides.py | 231 +++++ 13 files changed, 2280 insertions(+), 573 deletions(-) create mode 100644 docs/firmware-diagnostics-proposals.md create mode 100644 kota_tech/diag/guides.py create mode 100644 kota_tech/diag/guides.toml create mode 100644 kota_tech/ui/guide_panel.py create mode 100644 tests/test_guides.py diff --git a/docs/firmware-diagnostics-proposals.md b/docs/firmware-diagnostics-proposals.md new file mode 100644 index 0000000..2750fa6 --- /dev/null +++ b/docs/firmware-diagnostics-proposals.md @@ -0,0 +1,90 @@ +# Firmware diagnostics improvement proposals + +> **Status: draft proposal, AI-generated (Claude) for review by the firmware team.** +> Nothing here is implemented. The firmware source was only read for analysis; +> no firmware was changed. Every item links to an observation from bench +> testing box `A4:CB:8F:C9:46:F8` (firmware v1.0, build `45fa9d5b9`) or from the +> sample logs, so the value of each change can be judged. + +## Why + +Troubleshooting currently depends on reverse-engineering free-text log lines and +on a status LED whose states overlap. Observed problems: + +| # | Observation | Effect for technicians | +|---|---|---| +| O1 | A new, uncommissioned box shows **green** for about 60 s, then purple | Looks healthy during installation | +| O2 | Three different states share **white** (SD error, factory reset, setup portal) | Needs serial or guesswork | +| O3 | **Blue** means "RTC did not answer", but the RTC is just the first I2C device | A loose I2C cable is misreported as an RTC fault | +| O4 | Every build reports `App version: 1.0` | Builds are told apart only by ELF SHA | +| O5 | Restarts after 150 s in an error state happen **without any log line** | A self-restart looks like a crash | +| O6 | With the RTC not running and no Internet, sensor tasks **loop forever** on `RTC is uninitialized` | An offline box records nothing, and it isn't obvious why | +| O7 | The OTA token is printed in plain text (`OTA token loaded from NVS: %s`, `received token: %s`) | Secrets end up in technician logs | +| O8 | Native USB loses output while no host is reading; a stale FIFO fragment is glued to the next line | The early boot after a power cycle is lost, and lines get corrupted | +| O9 | The microphone reports "shutdown state" (GPIO3) with no hint of the cause | A technician can't tell a switch from a fault | +| O10 | The deployed build logs some messages under different tags than the source (e.g. SD mount under `INFLUX_BUFFER`) | Parsers must ignore tags | + +## Serial output + +Priority: **P1** = large gain for little effort, **P2** = valuable, **P3** = nice to have. + +### P1 + +1. **One structured boot line** with a fixed prefix, printed right after `app_init`: + ``` + KOTA: boot fw=1.0.15 build=45fa9d5b hw=2 mac=A4CB8FC946F8 reset=USB_UART_CHIP_RESET mode=matter commissioned=0 last_restart=status_watchdog + ``` + The tool can then identify firmware, hardware and mode from a single line (fixes O4 and O10). Fill `PROJECT_VER` from `FIRMWARE_VERSION` (currently `15` in `pinout.hpp`) so every build has a unique version. +2. **Log every status change** inside `Status::set_status()`, with a reason argument: + ``` + KOTA: status OK -> CONNECTION_ERROR reason=influx_flush_failed + ``` + This is the exact LED colour. Today the tool has to infer it from about 15 different messages. +3. **Log the reason before every `esp_restart()`** and store it (RTC memory or NVS) so it can be printed at the next boot as `last_restart=`. Values: `status_watchdog_150s`, `out_of_resources_30s`, `button_factory_reset`, `setup_portal_toggle`, `ota_done`, `init_failed:` (fixes O5). +4. **Stop printing secrets**: print only the first and last 4 characters of the OTA token, or `token=present` (fixes O7). +5. **Warn once and continue when the time is unset**, instead of the `while (now == 946684800)` loops in `device_status.cpp` and the sensors. Record data with a `time_valid=false` field or buffer it with uptime, then correct it after SNTP (fixes O6). This is a behaviour change, but the biggest data-loss risk found. + +### P2 + +6. **I2C bus scan at boot**, before any sensor init: + ``` + KOTA: i2c SDA=1 SCL=1 0x39=AS7341 0x68=DS1307 0x6B=SEN66(missing) 0x76=BME688 + ``` + Reading the SDA/SCL levels first detects a stuck-low bus (shorted or broken cable). The scan then separates "whole cable" from "one sensor" (fixes O3). +7. **RTC detail**: at init, print the DS1307 clock-halt (CH) bit and the raw time (`KOTA: rtc running=0 time=2000-01-01 (coin cell?)`). After SNTP sets the time, re-read it 2 s later to verify it's ticking. +8. **SD card detail**: card type, size, FAT type, free space, which `ENV.TXT` keys are present (names only, never values) and the buffer size in lines. Example: `KOTA: sd type=SDHC size=7.4GB fs=FAT32 free=7.3GB env_keys=INFLUX_URL,INFLUX_TOKEN buffer_lines=42`. +9. **Periodic health line** every 60 s. `DeviceStatus` already computes almost everything: + ``` + KOTA: health up=312s status=CONNECTION_ERROR wifi=disconnected rssi=0 time_valid=0 sd=ok buffer=42 heap=81234 psram=6.1M last_upload=never ota=unregistered + ``` +10. **Matter commissioning status at boot**: `KOTA: matter fabrics=0 window=open` plus the QR payload and manual code, so the tool can show the QR code on screen when the sticker is missing. +11. **Microphone enable reason**: `KOTA: mic enabled=0 (GPIO3=1, expected 0)` once at boot, instead of a warning every 10 s (fixes O9). +12. **Stable error IDs** in messages, e.g. `[E-SD-01] Failed to initialize the card`, documented in one table shared by the firmware, the technician tool and the service docs. + +### P3 + +13. **Console commands** over USB (the firmware already runs a `console` task): `diag` (full health dump), `i2cscan`, `sdinfo`, `ledtest` (cycles all colours so the technician can confirm the LED hardware), `version`, `bootlog`. The tool could then run checks without a reboot. +14. **Boot-log ring buffer** in RAM, dumped with `bootlog` or on first host connect. This recovers the early boot lost on native USB after a power-switch cycle (fixes O8). +15. **Button events**: log the press start and release with duration (`KOTA: button press 1.2s -> setup_portal`). This allows a safe button test and shows accidental factory resets. + +## RGB LED + +1. **Separate "not connected yet" from "OK"** (fixes O1): **cyan breathing** while the box is uncommissioned / advertising over BLE, fast cyan while a phone is connected, and a green flash when commissioning completes. +2. **Split the white states** with patterns (fixes O2): + - SD card / `ENV.TXT` error: white, fast blink (2 Hz) + - factory reset in progress: white, solid + - Wi-Fi setup portal: white, slow breathing +3. **Blink codes for red and blue** (fixes O3): N short pulses followed by a pause identify the part. + - Red: 1 = BME688, 2 = SEN66, 3 = AS7341, 4 = microphone, 5 = flicker, 6 = self-check failed + - Blue: 1 = RTC not responding, 2 = I2C bus stuck low +4. **Split purple**: solid = no network/DNS; blinking = Internet works but the server rejected the box (InfluxDB 401/404, OTA 401). These need different fixes (network vs SD card settings). +5. **Show the cause before a self-restart**: flash the error colour 3 times before `esp_restart()`. After boot, show the previous boot's error colour for 3 s (from RTC memory), so a reboot loop has a visible cause. +6. **Update progress**: yellow blinking while downloading (faster as progress grows); orange stays solid for the self-check. +7. **Brightness and distinguishability**: colours are set at 10 % (`255/10`). Yellow and orange, and white and cyan, are hard to tell apart in daylight. Prefer fewer colours plus patterns, and raise brightness for error states. +8. **Heartbeat LED (GPIO6)**: keep 1 Hz for "running", add a double-blink when offline, so the heartbeat alone gives a rough state even when the RGB LED is faulty. + +## What changes in the technician tool + +- The structured `KOTA:` lines (items 1, 2, 3, 9) would replace most regex rules in `rules.toml` and make the LED model exact rather than inferred. +- The console commands (item 13) would let guided checks test hardware directly (I2C scan, LED test) instead of asking the technician to power-cycle. +- The new LED patterns would add answers to the Quick check (e.g. "white, blinking fast") and remove the follow-up questions currently needed to separate the white states. diff --git a/kota_tech/__init__.py b/kota_tech/__init__.py index 11aff0d..cc64a07 100644 --- a/kota_tech/__init__.py +++ b/kota_tech/__init__.py @@ -1,3 +1,3 @@ """KOTA sensorbox technician tool.""" -__version__ = "0.2.0" +__version__ = "0.3.0" diff --git a/kota_tech/diag/engine.py b/kota_tech/diag/engine.py index 693582c..3d8b28c 100644 --- a/kota_tech/diag/engine.py +++ b/kota_tech/diag/engine.py @@ -59,6 +59,7 @@ MILESTONES = [ ("sd_mounted", "SD card mounted", False), ("env_loaded", "ENV.TXT read (InfluxDB settings)", False), ("matter_started", "Matter started", True), + ("matter_commissioned", "Paired in Matter", True), ("local_wifi_mode", "Local Wi-Fi mode (SSID from SD card)", True), ("sensors_ready", "All sensors started", False), ("wifi_connected", "Connected to Wi-Fi", False), @@ -215,6 +216,7 @@ class Report: boots: list[BootRecord] lines: int mid_run: bool # no boot seen yet + technician: list[str] = field(default_factory=list) # guided-check answers def to_text(self) -> str: out = [f"VERDICT: {self.verdict}", @@ -243,6 +245,10 @@ class Report: out.append("Resolved during this session:") for f in self.resolved: out.append(f" - {f.title}" + (f" (by: {f.resolved_by})" if f.resolved_by else "")) + if self.technician: + out.append("") + out.append("Technician checks:") + out += [f" - {t}" for t in self.technician] return "\n".join(out) @@ -271,6 +277,7 @@ class DiagnosticsEngine: self.lines = 0 self._tool_reset_at: float | None = None self._panic_tail = 0 # RAW lines after a panic line to keep + self.technician: list[str] = [] @property def boot(self) -> BootRecord: @@ -369,7 +376,22 @@ class DiagnosticsEngine: # Reached milestones in the order they happened, then the pending ones. ms.sort(key=lambda m: (m[2] is None, m[2] or 0)) return Report(verdict, vsev, self.led, self.led_reason, self.firmware, ms, roots, - earlier, resolved, list(self.boots), self.lines, mid_run) + earlier, resolved, list(self.boots), self.lines, mid_run, list(self.technician)) + + def add_confirmed(self, key: str, severity: Severity, title: str, meaning: str, + actions: tuple[str, ...]) -> Finding: + """A finding established by a guided check (technician answer + log).""" + f = self.findings.get(key) + if f is None: + f = self.findings[key] = Finding(key, key, severity, title, meaning, tuple(actions)) + f.count += 1 + f.boot = self.boot.index + f.resolved = False + f.evidence.append("confirmed by the technician during a guided check") + return f + + def note_technician(self, text: str) -> None: + self.technician.append(text) # ------------------------------------------------------------ internals def _new_boot(self, host_time: float, explicit: bool) -> None: diff --git a/kota_tech/diag/guides.py b/kota_tech/diag/guides.py new file mode 100644 index 0000000..cb4d5e0 --- /dev/null +++ b/kota_tech/diag/guides.py @@ -0,0 +1,400 @@ +"""Guided troubleshooting: executes the decision trees in guides.toml. + +GUI-independent. The runner is fed the same LogLines as the diagnostics +engine, reads the engine's report to route and to skip questions the log +already answers, asks the host to perform tool actions (board reset), and +records every answer and conclusion in the engine so they appear in the +report and the session log. +""" + +from __future__ import annotations + +import re +import time +import tomllib +from collections.abc import Callable +from dataclasses import dataclass, field +from pathlib import Path + +from ..core.logline import LogLine +from .engine import LED, DiagnosticsEngine, Severity + +GUIDES_PATH = Path(__file__).with_name("guides.toml") +# LED answers a technician can give (engine colours + a reboot-loop pattern). +LED_ANSWERS = ["GREEN", "PURPLE", "RED", "BLUE", "WHITE", "YELLOW", "ORANGE", "OFF", "CYCLING"] +LED_ANSWER_LABELS = {**{k: v[0] for k, v in LED.items()}, + "CYCLING": "Keeps changing / goes dark every few seconds"} +STEP_TYPES = {"led", "question", "info", "wait", "route"} +END_SEVERITY = {"ok": None, "info": Severity.INFO, "warning": Severity.WARNING, + "error": Severity.ERROR, "critical": Severity.CRITICAL} + + +@dataclass(frozen=True) +class Option: + label: str + next: str + + +@dataclass(frozen=True) +class Step: + id: str + type: str + text: str = "" + options: tuple[Option, ...] = () + route: dict[str, str] = field(default_factory=dict) # led colour -> target + routes: dict[str, str] = field(default_factory=dict) # rule id -> target + default: str | None = None + next: str | None = None + tool_action: str | None = None + until: re.Pattern[str] | None = None + until_milestone: str | None = None + fail_on: re.Pattern[str] | None = None + timeout_s: float = 60.0 + pass_on_timeout: bool = False + on_ok: str | None = None + on_fail: str | None = None + on_timeout: str | None = None + skip_if_finding: str | None = None + skip_unless_feature: str | None = None + skip_to: str | None = None + + def targets(self) -> list[str]: + t = [o.next for o in self.options] + list(self.route.values()) + list(self.routes.values()) + t += [x for x in (self.default, self.next, self.on_ok, self.on_fail, self.on_timeout, self.skip_to) if x] + return t + + +@dataclass(frozen=True) +class End: + id: str + severity: str + title: str + text: str + actions: tuple[str, ...] = () + + +@dataclass(frozen=True) +class Guide: + id: str + title: str + summary: str + recommend: tuple[str, ...] + start: str + steps: dict[str, Step] + ends: dict[str, End] + + +def load_guides(path: Path = GUIDES_PATH) -> dict[str, Guide]: + data = tomllib.loads(path.read_text(encoding="utf-8")) + guides: dict[str, Guide] = {} + for g in data["guide"]: + steps = {} + for s in g.get("step", []): + steps[s["id"]] = Step( + id=s["id"], type=s["type"], text=s.get("text", ""), + options=tuple(Option(o["label"], o["next"]) for o in s.get("options", ())), + route=dict(s.get("route", {})), routes=dict(s.get("routes", {})), + default=s.get("default"), next=s.get("next"), tool_action=s.get("tool_action"), + until=re.compile(s["until"]) if "until" in s else None, + until_milestone=s.get("until_milestone"), + fail_on=re.compile(s["fail_on"]) if "fail_on" in s else None, + timeout_s=float(s.get("timeout_s", 60)), pass_on_timeout=bool(s.get("pass_on_timeout", False)), + on_ok=s.get("on_ok"), on_fail=s.get("on_fail"), on_timeout=s.get("on_timeout"), + skip_if_finding=s.get("skip_if_finding"), skip_unless_feature=s.get("skip_unless_feature"), + skip_to=s.get("skip_to"), + ) + ends = {e["id"]: End(e["id"], e["severity"], e["title"], e["text"], tuple(e.get("actions", ()))) + for e in g.get("end", [])} + guides[g["id"]] = Guide(g["id"], g["title"], g["summary"], tuple(g.get("recommend", ())), + g["start"], steps, ends) + _validate(guides) + return guides + + +def _validate(guides: dict[str, Guide]) -> None: + for g in guides.values(): + if g.start not in g.steps: + raise ValueError(f"guide {g.id}: start step {g.start!r} missing") + for s in g.steps.values(): + if s.type not in STEP_TYPES: + raise ValueError(f"{g.id}.{s.id}: unknown step type {s.type!r}") + if s.type == "led" and set(s.route) - set(LED_ANSWERS): + raise ValueError(f"{g.id}.{s.id}: unknown LED colours {set(s.route) - set(LED_ANSWERS)}") + if s.type == "wait" and not (s.until or s.until_milestone or s.pass_on_timeout): + raise ValueError(f"{g.id}.{s.id}: wait step needs until/until_milestone/pass_on_timeout") + if s.tool_action not in (None, "reset"): + raise ValueError(f"{g.id}.{s.id}: unknown tool_action {s.tool_action!r}") + for t in s.targets(): + kind, _, ref = t.partition(":") + if kind == "end" and ref not in g.ends: + raise ValueError(f"{g.id}.{s.id}: unknown end {ref!r}") + elif kind == "guide" and ref not in guides: + raise ValueError(f"{g.id}.{s.id}: unknown guide {ref!r}") + elif not ref and t not in g.steps: + raise ValueError(f"{g.id}.{s.id}: unknown step {t!r}") + for e in g.ends.values(): + if e.severity not in END_SEVERITY: + raise ValueError(f"{g.id}.end.{e.id}: unknown severity {e.severity!r}") + + +def recommended(guides: dict[str, Guide], engine: DiagnosticsEngine) -> list[Guide]: + """Guides matching the current root findings (in root order), then the LED.""" + report = engine.report() + keys: list[str] = [] + for rc in report.roots: + keys.append(rc.finding.rule_id) + keys += [c.rule_id for c in rc.consequences] + if report.led not in ("UNKNOWN",): + keys.append(f"led:{report.led}") + out: list[Guide] = [g for g in guides.values() if "always" in g.recommend] + for k in keys: + for g in guides.values(): + if k in g.recommend and g not in out: + out.append(g) + return out + + +@dataclass +class View: + """What the UI should show right now.""" + guide: Guide | None = None + step: Step | None = None + text: str = "" + options: list[tuple[str, str]] = field(default_factory=list) # (key, label) + waiting: bool = False + remaining_s: float = 0.0 + note: str = "" + end: End | None = None + can_back: bool = False + + +class GuideRunner: + def __init__(self, engine: DiagnosticsEngine, guides: dict[str, Guide] | None = None, + on_action: Callable[[str], bool] | None = None, + on_log: Callable[[str], None] | None = None, + clock: Callable[[], float] = time.monotonic): + self.engine = engine + self.guides = guides if guides is not None else load_guides() + self._on_action = on_action or (lambda _a: False) + self._on_log = on_log or (lambda _t: None) + self._clock = clock + self.cancel() + + # ------------------------------------------------------------ control + def cancel(self) -> None: + self.guide: Guide | None = None + self.step: Step | None = None + self.end: End | None = None + self.note = "" + self._stack: list[tuple[str, str]] = [] # (guide id, step id) for Back + self._wait_started = 0.0 + self._wait_boot = 0 + self._wait_milestones: set[str] = set() + + def start(self, guide_id: str) -> None: + self.cancel() + self._enter_guide(guide_id) + + def answer(self, key: str) -> None: + """Pick an option: LED colour name for led steps, option index otherwise.""" + s = self.step + if s is None: + return + if s.type == "led": + label = LED_ANSWER_LABELS.get(key, key) + self._record(s, label) + self._check_led(key) + target = s.route.get(key) + elif s.type == "question": + opt = s.options[int(key)] + self._record(s, opt.label) + target = opt.next + else: + return + if target: + self._push() + self._go(target) + + def proceed(self) -> None: + """Continue on info steps; 'skip waiting' on wait steps.""" + s = self.step + if s is None: + return + if s.type == "info" and s.next: + self._push() + self._go(s.next) + elif s.type == "wait": + self._record(s, "technician skipped the wait") + self._finish_wait("timeout") + + def back(self) -> None: + # Never step back into a wait: re-entering it could restart the box. + while self._stack: + gid, sid = self._stack.pop() + if self.guides[gid].steps[sid].type != "wait": + self.guide, self.end, self.note = self.guides[gid], None, "" + self._enter_step(sid) + return + + # --------------------------------------------------------------- feed + def feed(self, line: LogLine) -> None: + s = self.step + if s is None or s.type != "wait": + return + if s.fail_on and s.fail_on.search(line.text): + self._record(s, f"log: {line.text}") + self._finish_wait("fail") + elif s.until and s.until.search(line.text): + self._record(s, f"log: {line.text}") + self._finish_wait("ok") + elif s.until_milestone and self._milestone_new(s.until_milestone): + self._record(s, f"milestone reached: {s.until_milestone}") + self._finish_wait("ok") + + def tick(self) -> None: + s = self.step + if s is not None and s.type == "wait" and self._clock() - self._wait_started >= s.timeout_s: + self._finish_wait("ok" if s.pass_on_timeout else "timeout") + + # --------------------------------------------------------------- view + def view(self) -> View: + v = View(guide=self.guide, step=self.step, end=self.end, note=self.note, can_back=bool(self._stack)) + s = self.step + if s is None: + return v + v.text = self._render(s.text) + if s.type == "led": + v.options = [(k, LED_ANSWER_LABELS[k]) for k in LED_ANSWERS if k in s.route] + elif s.type == "question": + v.options = [(str(i), o.label) for i, o in enumerate(s.options)] + elif s.type == "wait": + v.waiting = True + v.remaining_s = max(0.0, s.timeout_s - (self._clock() - self._wait_started)) + return v + + # ---------------------------------------------------------- internals + def _push(self) -> None: + if self.guide and self.step: + self._stack.append((self.guide.id, self.step.id)) + + def _enter_guide(self, guide_id: str) -> None: + self.guide = self.guides[guide_id] + self._on_log(f"technician: started guide '{self.guide.title}'") + self._enter_step(self.guide.start) + + def _go(self, target: str) -> None: + kind, _, ref = target.partition(":") + if kind == "end" and ref: + self._conclude(self.guide.ends[ref]) + elif kind == "guide" and ref: + self._enter_guide(ref) + else: + self._enter_step(target) + + def _enter_step(self, step_id: str) -> None: + s = self.guide.steps[step_id] + self.step, self.note = s, "" + if s.skip_if_finding and self._finding_active(s.skip_if_finding): + self._auto(s, f"skipped - log already shows {s.skip_if_finding}", s.skip_to) + return + if s.skip_unless_feature and not self._feature(s.skip_unless_feature): + self._auto(s, f"skipped - firmware has no {s.skip_unless_feature}", s.skip_to) + return + if s.type == "route": + target = self._route(s) + self._auto(s, f"routed by log findings -> {target}", target) + return + if s.type == "wait": + self._wait_started = self._clock() + self._wait_boot = self.engine.boot.index + self._wait_milestones = set(self.engine.milestones) + if s.tool_action and not self._on_action(s.tool_action): + self.note = "Could not restart the box from the tool - connect to it first, or switch it off and on." + # A milestone that is already reached satisfies the wait at once + # unless the step first restarts the box. + if s.until_milestone and not s.tool_action and s.until_milestone in self.engine.milestones: + self._record(s, f"already reached: {s.until_milestone}") + self._finish_wait("ok") + + def _auto(self, s: Step, why: str, target: str | None) -> None: + self._on_log(f"technician guide: {s.id}: {why}") + if target: + self._go(target) + + def _finish_wait(self, outcome: str) -> None: + s = self.step + target = {"ok": s.on_ok, "fail": s.on_fail or s.on_timeout, "timeout": s.on_timeout or s.on_fail}[outcome] + if target is None: + return + self._push() + self._go(target) + + def _milestone_new(self, mid: str) -> bool: + if mid not in self.engine.milestones: + return False + return self.engine.boot.index != self._wait_boot or mid not in self._wait_milestones + + def _route(self, s: Step) -> str: + report = self.engine.report() + for rc in report.roots: + for f in (rc.finding, *rc.consequences): + if f.rule_id in s.routes: + return s.routes[f.rule_id] + return s.default or "end:" + next(iter(self.guide.ends)) + + def _check_led(self, seen: str) -> None: + expected = self.engine.led + if expected in ("UNKNOWN", "OFF") or seen == "CYCLING" or seen == expected: + return + exp_label, see_label = LED[expected][0], LED_ANSWER_LABELS[seen] + self.engine.add_confirmed( + "tech.led_mismatch", Severity.WARNING, + f"LED shows {see_label}, but the log implies {exp_label}", + f"The firmware state in the log corresponds to {exp_label}, while the technician sees {see_label}. " + "Either the LED just changed (check again in a few seconds), the LED/its wiring is faulty, " + "or the box runs different firmware. Trust the log findings.", + ("Look at the LED again for 10 seconds.", "If it stays different: note it for repair (LED board).")) + + def _conclude(self, end: End) -> None: + self.step, self.end = None, end + self._on_log(f"technician guide result: {end.title}") + sev = END_SEVERITY[end.severity] + self.engine.note_technician(f"{self.guide.title}: {end.title}") + if sev is not None: + self.engine.add_confirmed(f"tech.{self.guide.id}.{end.id}", sev, end.title, end.text, end.actions) + + def _record(self, s: Step, answer: str) -> None: + q = self._render(s.text) + self.engine.note_technician(f"{q} -> {answer}") + self._on_log(f"technician: {q[:80]} -> {answer}") + + def _finding_active(self, rule_id: str) -> bool: + return any(f.rule_id == rule_id and f.active for f in self.engine.findings.values()) + + def _feature(self, name: str) -> bool: + fw = self.engine.firmware + if name == "sd_wifi": + return fw.supports_sd_wifi is not False + if name == "setup_portal": + if fw.known is not None: + return fw.known.setup_portal + if "setup_portal" in fw.evidence: + return True + return "legacy_v1" not in fw.evidence # unknown firmware: ask + return False + + def _render(self, text: str) -> str: + report = self.engine.report() + sensors = sorted({f.title.removesuffix(" failed to start") for f in self.engine.findings.values() + if f.rule_id == "sensor.init_failed" and f.active}) + ctx = { + "expected_led": LED[report.led][0], + "failing_sensors": ", ".join(sensors) or "see the Diagnosis tab", + "top_finding": report.roots[0].finding.title if report.roots else "none", + } + return text.format_map(_Fmt(ctx)) + + +class _Fmt(dict): + def __missing__(self, key: str) -> str: + return "{" + key + "}" diff --git a/kota_tech/diag/guides.toml b/kota_tech/diag/guides.toml new file mode 100644 index 0000000..2983cc7 --- /dev/null +++ b/kota_tech/diag/guides.toml @@ -0,0 +1,715 @@ +# Guided troubleshooting: decision trees that combine technician answers +# with live log evidence (diag.guides.GuideRunner executes them). +# +# Guide: id, title, summary, recommend (rule ids / "led:" / "always"), +# start (first step id), [[guide.step]], [[guide.end]] +# Step types: +# led technician picks the LED colour; `route` maps colour -> target. +# Colours: GREEN PURPLE RED BLUE YELLOW ORANGE WHITE OFF CYCLING +# The answer is compared with the colour the firmware log implies. +# question `options` = [{label, next}] +# info instruction + Continue (`next`) +# wait optional `tool_action` ("reset"), then watch the log: +# `until` (regex) / `until_milestone`, `fail_on` (regex), +# `timeout_s`; go to on_ok / on_fail / on_timeout. +# `pass_on_timeout = true`: reaching the timeout without fail_on +# counts as ok (used for "watch for N seconds"). +# route automatic: first current root finding whose rule id is in +# `routes` decides; otherwise `default`. +# Targets: "", "end:", "guide:". +# Optional on any step: skip_if_finding / skip_unless_feature (+ skip_to). +# Text placeholders: {expected_led} {failing_sensors} {top_finding} +# End severity: ok | info | warning | error | critical + +# ================================================================= quick +[[guide]] +id = "quick" +title = "Quick check - start here" +summary = "Tell the tool what the LED shows; it picks the right checks." +recommend = ["always"] +start = "led" + +[[guide.step]] +id = "led" +type = "led" +text = "Look at the RGB status LED on the box (no need to open it). Which colour is it?" +route = { GREEN = "heartbeat", PURPLE = "guide:network", RED = "guide:sensors", BLUE = "guide:rtc_i2c", WHITE = "guide:white", YELLOW = "guide:update", ORANGE = "guide:update", OFF = "guide:power", CYCLING = "guide:reboot_loop" } + +[[guide.step]] +id = "heartbeat" +type = "question" +text = "Is the small LED next to the RGB LED blinking about once per second?" +options = [ + { label = "Yes, blinking", next = "green_route" }, + { label = "No - steady on or off", next = "end:hung" }, +] + +[[guide.step]] +id = "green_route" +type = "route" +routes = { "rtc.clock_not_running" = "guide:clock", "mic.silent" = "guide:mic", "mic.disabled" = "guide:mic", "matter.not_commissioned" = "guide:network", "net.dns_fail" = "guide:network" } +default = "end:healthy" + +[[guide.end]] +id = "healthy" +severity = "ok" +title = "Box looks healthy" +text = "Green LED, firmware running and no problems in the log." +actions = ["If the customer still reports missing data, keep the tool connected for 5 minutes and check that 'Data uploaded to InfluxDB' gets ticked."] + +[[guide.end]] +id = "hung" +severity = "error" +title = "Firmware is not running normally" +text = "The heartbeat LED should blink once per second whenever the firmware runs. A steady heartbeat LED means the firmware has frozen." +actions = [ + "Switch the box off and on with the power switch.", + "If it happens again: save the session log and re-flash the official firmware (Flash tab, coming in v0.4).", +] + +# =============================================================== network +[[guide]] +id = "network" +title = "Purple LED / no Internet" +summary = "Pairing in Matter, site Wi-Fi and Internet checks, with live confirmation." +recommend = ["led:PURPLE", "matter.not_commissioned", "net.dns_fail", "influx.buffer_fail", "ota.registration_failed"] +start = "paired" + +[[guide.step]] +id = "paired" +type = "question" +skip_if_finding = "matter.not_commissioned" +skip_to = "pair_intro" +text = "Was this box already added to the customer's Matter app (Apple Home, Google Home, ...) at this site?" +options = [ + { label = "Yes, it was paired before", next = "internet" }, + { label = "No / not sure", next = "pair_intro" }, +] + +[[guide.step]] +id = "internet" +type = "question" +text = "Does the site Wi-Fi have working Internet? Check with a phone connected to the same Wi-Fi (open any website)." +options = [ + { label = "Yes, Internet works", next = "changed" }, + { label = "No Internet on the site Wi-Fi", next = "end:site_offline" }, +] + +[[guide.step]] +id = "changed" +type = "question" +text = "Was the Wi-Fi name or password changed, or the router replaced, since the box was installed?" +options = [ + { label = "Yes / possibly", next = "end:repair_needed" }, + { label = "No", next = "end:offline_unknown" }, +] + +[[guide.step]] +id = "pair_intro" +type = "info" +text = "The box is not on any Wi-Fi yet: it must be paired in Matter. You need: a phone with Bluetooth on, the customer's Matter app, the 2.4 GHz Wi-Fi password, and the QR sticker of this box. Keep the tool connected - it follows the pairing live." +next = "pair_start" + +[[guide.step]] +id = "pair_start" +type = "wait" +text = "In the Matter app choose 'Add device' and scan the QR code on the sticker (or type the 11-digit code printed under it). Keep the phone within 1 m of the box." +until = 'MAIN: Commissioning session started' +timeout_s = 300 +on_ok = "pair_wifi" +on_timeout = "not_found" + +[[guide.step]] +id = "not_found" +type = "question" +text = "The box has not seen the phone connect yet. What does the app show?" +options = [ + { label = "Still searching / let me try again", next = "pair_start" }, + { label = "'Device not found' or similar", next = "end:ble_not_found" }, +] + +[[guide.step]] +id = "pair_wifi" +type = "wait" +text = "The phone is connected to the box. Follow the app: choose the 2.4 GHz Wi-Fi network and enter its password." +until = 'MAIN: Commissioning complete|MAIN: Fabric is committed' +fail_on = 'Commissioning failed, fail safe timer expired' +timeout_s = 300 +on_ok = "pair_time" +on_fail = "end:pair_failed" +on_timeout = "end:pair_failed" + +[[guide.step]] +id = "pair_time" +type = "wait" +text = "Paired! The box is joining the Wi-Fi and getting the time from the Internet..." +until_milestone = "time_synced" +timeout_s = 120 +on_ok = "pair_upload" +on_timeout = "end:joined_no_internet" + +[[guide.step]] +id = "pair_upload" +type = "wait" +text = "Online. Waiting for the first measurements to reach the database (up to 4 minutes)..." +until = 'INFLUX: HTTP request performed, status code: 2\d\d' +fail_on = 'INFLUX: Failed to perform HTTP request: (401|403|404)' +timeout_s = 240 +on_ok = "end:online" +on_fail = "end:influx_rejected" +on_timeout = "end:no_upload" + +[[guide.end]] +id = "online" +severity = "ok" +title = "Box is paired and uploading data" +text = "Pairing, Internet time and the first upload all worked." +actions = [ + "The box may now download a firmware update (yellow, then orange LED, a few minutes). Do not switch it off.", + "It should end green.", +] + +[[guide.end]] +id = "site_offline" +severity = "warning" +title = "Site network has no Internet" +text = "The box cannot work until the site Wi-Fi reaches the Internet. This is not a box fault." +actions = ["Ask the customer to fix the Internet connection, then power-cycle the box."] + +[[guide.end]] +id = "repair_needed" +severity = "warning" +title = "Box must be paired again" +text = "The box still remembers the old Wi-Fi. It needs a factory reset and new pairing." +actions = [ + "Hold the Matter button for 5 seconds (LED turns white) - this erases the old pairing.", + "Remove the box from the customer's Matter app, then run this guide again and choose 'No / not sure'.", +] + +[[guide.end]] +id = "offline_unknown" +severity = "error" +title = "Box is paired but cannot reach the Internet - cause unclear" +text = "The network works for other devices, but not for this box." +actions = [ + "Check the router does not block new devices (guest isolation, MAC filter). Box MAC is shown in the port list.", + "Move the box closer to the router to rule out weak signal.", + "If nothing helps: factory reset (hold the Matter button 5 s) and pair again.", +] + +[[guide.end]] +id = "ble_not_found" +severity = "error" +title = "Phone cannot find the box over Bluetooth" +text = "The box only accepts pairing for a limited time after start-up." +actions = [ + "Switch the box off and on to reopen the pairing window, then try again within 10 minutes.", + "Check Bluetooth and location permission are on for the Matter app.", + "If the box was paired to another app before: hold the Matter button 5 s (factory reset) first.", +] + +[[guide.end]] +id = "pair_failed" +severity = "error" +title = "Pairing did not finish" +text = "The phone connected but the box did not join the Wi-Fi." +actions = [ + "Use a 2.4 GHz network (many routers have a separate 2.4 GHz name).", + "Re-enter the Wi-Fi password carefully.", + "Switch the box off and on, then pair again.", +] + +[[guide.end]] +id = "joined_no_internet" +severity = "error" +title = "Box joined the Wi-Fi but has no Internet" +text = "Pairing worked, but the box cannot reach time or data servers." +actions = [ + "Check the network allows outgoing connections (HTTPS, NTP) for new devices.", + "Try a phone hotspot to rule out the site network.", +] + +[[guide.end]] +id = "influx_rejected" +severity = "critical" +title = "Database rejected the box (token / bucket)" +text = "The box is online but InfluxDB refused the upload. The SD card settings are wrong." +actions = ["Re-provision the SD card with the current ENV.TXT (SD card is inside the case)."] + +[[guide.end]] +id = "no_upload" +severity = "warning" +title = "Online, but no upload seen yet" +text = "Uploads happen every minute; the first one can be delayed while the air sensor warms up." +actions = ["Keep the tool connected a few more minutes and watch the Diagnosis tab."] + +# ================================================================= RTC / I2C +[[guide]] +id = "rtc_i2c" +title = "Blue LED - clock / I2C cable" +summary = "Re-seat the I2C cable and verify the start-up live." +recommend = ["led:BLUE", "rtc.init_failed", "i2c.errors"] +start = "explain" + +[[guide.step]] +id = "explain" +type = "info" +text = "Blue means the clock chip did not answer. It is the first chip on the shared I2C cable between the boards, so a loose cable is the most common cause. This check needs the case opened." +next = "reseat" + +[[guide.step]] +id = "reseat" +type = "info" +text = "Switch the power OFF. Open the case. Unplug and firmly re-plug the I2C cable between the boards at both ends. Close the case and switch the power ON. Then press Continue." +next = "verify" + +[[guide.step]] +id = "verify" +type = "wait" +text = "Watching the start-up (up to 60 s)..." +until_milestone = "sensors_ready" +fail_on = 'MAIN: Failed to initialize RTC' +timeout_s = 60 +on_ok = "end:i2c_fixed" +on_fail = "damaged" +on_timeout = "damaged" + +[[guide.step]] +id = "damaged" +type = "question" +text = "The clock still does not answer. Is the I2C cable or its connector visibly damaged (pinched, broken wire, bent pin)?" +options = [ + { label = "Yes, damaged", next = "end:replace_cable" }, + { label = "No, looks fine", next = "end:rtc_module" }, +] + +[[guide.end]] +id = "i2c_fixed" +severity = "ok" +title = "Fixed - all sensors start again" +text = "After re-seating the cable the clock and all sensors started." +actions = ["Make sure the cable is routed without strain before closing the case."] + +[[guide.end]] +id = "replace_cable" +severity = "error" +title = "Replace the I2C cable" +text = "A damaged I2C cable stops the clock and all sensors." +actions = ["Replace the cable, then run this check again."] + +[[guide.end]] +id = "rtc_module" +severity = "error" +title = "Clock (RTC) module is probably faulty" +text = "The cable is fine but the clock chip does not answer." +actions = ["Replace the RTC module, or send the box for repair with the session log."] + +# ==================================================================== white +[[guide]] +id = "white" +title = "White LED - SD card / reset / setup mode" +summary = "Tell apart the three white states and check the SD card." +recommend = ["led:WHITE", "sd.card_fail", "sd.mount_fail", "sd.env_open_fail", "influx.env_missing", "influx.init_fail"] +start = "button" + +[[guide.step]] +id = "button" +type = "question" +text = "Did anyone hold the Matter button (outside the case) for about 5 seconds just before the LED turned white?" +options = [ + { label = "Yes", next = "end:factory_reset" }, + { label = "No / don't know", next = "portal" }, +] + +[[guide.step]] +id = "portal" +type = "question" +skip_unless_feature = "setup_portal" +skip_to = "sd_reseat" +text = "On a phone, look at the Wi-Fi list: is there a network called 'KotaSensorBox-....'?" +options = [ + { label = "Yes", next = "end:setup_mode" }, + { label = "No", next = "sd_reseat" }, +] + +[[guide.step]] +id = "sd_reseat" +type = "info" +text = "The SD card is probably not readable. This needs the case opened: switch the power OFF, open the case, push the SD card in until it clicks (or remove and re-insert it). Close the case, switch the power ON, then press Continue." +next = "sd_verify" + +[[guide.step]] +id = "sd_verify" +type = "wait" +text = "Watching the SD card start-up (up to 60 s)..." +until = 'Read INFLUX_URL from \.env file' +fail_on = 'Failed to initialize the card|Failed to mount filesystem|Failed to read INFLUX_(URL|TOKEN)|Failed to open \.env file' +timeout_s = 60 +on_ok = "end:sd_fixed" +on_fail = "end:sd_reprovision" +on_timeout = "end:sd_reprovision" + +[[guide.end]] +id = "factory_reset" +severity = "info" +title = "White = factory reset in progress" +text = "The box erased its Matter pairing and restarts." +actions = ["Pair it again in the Matter app (Purple LED guide)."] + +[[guide.end]] +id = "setup_mode" +severity = "info" +title = "White = Wi-Fi setup mode" +text = "The box is waiting for Wi-Fi settings on its own network." +actions = [ + "Connect a phone to KotaSensorBox-.... and open http://sensorbox.local/ to enter the Wi-Fi,", + "or short-press the Matter button (< 2 s) to leave setup mode.", +] + +[[guide.end]] +id = "sd_fixed" +severity = "ok" +title = "Fixed - SD card is read again" +text = "The box found the SD card and read ENV.TXT." +actions = ["Close the case and watch the Diagnosis tab for a minute."] + +[[guide.end]] +id = "sd_reprovision" +severity = "critical" +title = "SD card is unreadable or has wrong settings" +text = "Even after re-seating, the card or its ENV.TXT cannot be used." +actions = [ + "Re-provision the card with the tool (SD tab, coming in v0.5) or use a new card.", + "The Diagnosis tab shows which step failed (card, file system or ENV.TXT keys).", +] + +# ================================================================== sensors +[[guide]] +id = "sensors" +title = "Red LED - sensor or hardware fault" +summary = "Find the failing sensor and verify after re-seating its cable." +recommend = ["led:RED", "sensor.init_failed", "sensor.selfcheck_failed", "sys.out_of_resources", "ota.selfcheck_failed"] +start = "which" + +[[guide.step]] +id = "which" +type = "route" +routes = { "sensor.init_failed" = "reseat", "rtc.init_failed" = "guide:rtc_i2c", "ota.selfcheck_failed" = "end:selfcheck", "sensor.selfcheck_failed" = "end:selfcheck", "sys.out_of_resources" = "end:oom" } +default = "capture" + +[[guide.step]] +id = "capture" +type = "wait" +text = "The log does not show the cause yet. The tool restarts the box and records its start-up (45 s)..." +tool_action = "reset" +timeout_s = 45 +pass_on_timeout = true +on_ok = "which_again" + +[[guide.step]] +id = "which_again" +type = "route" +routes = { "sensor.init_failed" = "reseat", "rtc.init_failed" = "guide:rtc_i2c", "sys.out_of_resources" = "end:oom" } +default = "end:red_unclear" + +[[guide.step]] +id = "reseat" +type = "info" +text = "Failing: {failing_sensors}. This needs the case opened: switch the power OFF, open the case and re-seat the cable of that sensor. Close the case, switch the power ON, then press Continue." +next = "verify" + +[[guide.step]] +id = "verify" +type = "wait" +text = "Watching the sensor start-up (up to 60 s)..." +until_milestone = "sensors_ready" +fail_on = 'MAIN: Failed to initialize' +timeout_s = 60 +on_ok = "end:sensor_fixed" +on_fail = "end:sensor_replace" +on_timeout = "end:sensor_replace" + +[[guide.end]] +id = "sensor_fixed" +severity = "ok" +title = "Fixed - all sensors start again" +text = "After re-seating, every sensor started." +actions = ["Close the case and watch the Diagnosis tab for a minute."] + +[[guide.end]] +id = "sensor_replace" +severity = "error" +title = "Sensor still fails - replace it" +text = "The sensor does not start even with a re-seated cable." +actions = ["Replace the named sensor (or its cable) and run this check again."] + +[[guide.end]] +id = "selfcheck" +severity = "error" +title = "A firmware update was rejected by its self-check" +text = "The box rolled back to its previous firmware because a sensor failed the test." +actions = ["Check the sensor named in the Diagnosis tab (inside the case), then power-cycle."] + +[[guide.end]] +id = "oom" +severity = "error" +title = "Firmware ran out of memory" +text = "Not a hardware fault; the firmware restarts itself." +actions = ["Power-cycle. If it repeats, send the session log to the firmware team."] + +[[guide.end]] +id = "red_unclear" +severity = "warning" +title = "Red LED without a clear cause in the log" +text = "The start-up did not show a failing sensor." +actions = ["Save the session log and send it to the firmware team."] + +# ============================================================= reboot loop +[[guide]] +id = "reboot_loop" +title = "LED keeps changing / box restarts" +summary = "Record several start-ups and find the error just before each restart." +recommend = ["led:CYCLING", "reboot.loop", "sys.crash", "reboot.unexpected", "reboot.brownout", "reboot.watchdog"] +start = "record" + +[[guide.step]] +id = "record" +type = "wait" +text = "The tool restarts the box and records 45 seconds of start-up..." +tool_action = "reset" +timeout_s = 45 +pass_on_timeout = true +on_ok = "cause" + +[[guide.step]] +id = "cause" +type = "route" +routes = { "rtc.init_failed" = "guide:rtc_i2c", "sd.card_fail" = "guide:white", "sd.mount_fail" = "guide:white", "sd.env_open_fail" = "guide:white", "influx.env_missing" = "guide:white", "influx.init_fail" = "guide:white", "sensor.init_failed" = "guide:sensors", "reboot.brownout" = "end:power_supply", "matter.not_commissioned" = "guide:network", "net.dns_fail" = "guide:network", "influx.buffer_fail" = "guide:network" } +default = "end:loop_unclear" + +[[guide.end]] +id = "power_supply" +severity = "error" +title = "Power supply is too weak or unstable" +text = "The chip reset itself because the voltage dropped." +actions = ["Check the power supply, cable and connectors; try another supply."] + +[[guide.end]] +id = "loop_unclear" +severity = "warning" +title = "No clear restart cause in 45 s" +text = "The box did not show a known start-up error during the recording." +actions = ["Keep the tool connected for 5 minutes, then save the session log for the firmware team."] + +# ================================================================== update +[[guide]] +id = "update" +title = "Yellow / orange LED - firmware update" +summary = "Wait for the update and its self-check to finish." +recommend = ["led:YELLOW", "led:ORANGE", "ota.updating", "ota.selfcheck"] +start = "wait" + +[[guide.step]] +id = "wait" +type = "wait" +text = "A firmware update or its self-check is running. Do NOT switch the box off. Waiting up to 10 minutes..." +until = 'Passing selfcheck|OTA update successful' +fail_on = 'OTA update failed|Failing selfcheck' +timeout_s = 600 +on_ok = "end:update_ok" +on_fail = "end:update_failed" +on_timeout = "end:update_slow" + +[[guide.end]] +id = "update_ok" +severity = "ok" +title = "Update finished" +text = "The new firmware was installed or accepted." +actions = ["Wait for the green LED."] + +[[guide.end]] +id = "update_failed" +severity = "error" +title = "Update failed" +text = "The box keeps its current firmware and retries later." +actions = ["Check the Wi-Fi is stable. The Diagnosis tab shows why it failed."] + +[[guide.end]] +id = "update_slow" +severity = "warning" +title = "Update is taking very long" +text = "No end of the update was seen in 10 minutes." +actions = ["Check the Wi-Fi signal; leave the box powered and check again later."] + +# =================================================================== power +[[guide]] +id = "power" +title = "LED off" +summary = "Power switch, heartbeat LED and USB connection." +recommend = ["led:OFF"] +start = "switch" + +[[guide.step]] +id = "switch" +type = "question" +text = "Is the power switch on the outside of the case set to ON?" +options = [ + { label = "It was OFF - I switched it on", next = "boot" }, + { label = "It is ON", next = "heartbeat" }, +] + +[[guide.step]] +id = "boot" +type = "wait" +text = "Waiting for the box to start (up to 30 s)..." +until_milestone = "app_started" +timeout_s = 30 +on_ok = "end:was_off" +on_timeout = "heartbeat" + +[[guide.step]] +id = "heartbeat" +type = "question" +text = "Is the small LED next to the RGB LED blinking?" +options = [ + { label = "Yes, blinking", next = "end:rgb_led_fault" }, + { label = "No", next = "end:no_power" }, +] + +[[guide.end]] +id = "was_off" +severity = "ok" +title = "Box was switched off" +text = "It starts normally after switching on." +actions = ["Run the Quick check again once the LED shows a colour."] + +[[guide.end]] +id = "rgb_led_fault" +severity = "warning" +title = "Firmware runs, but the RGB LED stays dark" +text = "The heartbeat LED shows the firmware is running; the RGB LED or its wiring is faulty." +actions = ["Use the Diagnosis tab instead of the LED; replace the LED board when convenient."] + +[[guide.end]] +id = "no_power" +severity = "error" +title = "Box does not start" +text = "Neither LED is lit: no power or the firmware does not start." +actions = [ + "Check the power supply and cable.", + "If the USB port shows up in this tool, re-flash the official firmware (Flash tab, coming in v0.4).", +] + +# =================================================================== clock +[[guide]] +id = "clock" +title = "Clock not set" +summary = "Why readings are on hold and when the coin cell matters." +recommend = ["rtc.clock_not_running", "rtc.lost_after_sync"] +start = "internet" + +[[guide.step]] +id = "internet" +type = "question" +text = "The box clock is not set, so readings are on hold. Will the box have Internet at its installation site?" +options = [ + { label = "Yes", next = "end:clock_auto" }, + { label = "No / not yet", next = "end:clock_offline" }, +] + +[[guide.end]] +id = "clock_auto" +severity = "info" +title = "Clock will be set automatically" +text = "On its first Internet connection the box sets its clock and starts recording." +actions = ["If the clock is lost again after every power-off, replace the RTC coin cell (inside the case)."] + +[[guide.end]] +id = "clock_offline" +severity = "error" +title = "Box will not record data without Internet" +text = "Without the Internet the clock cannot be set, and the firmware holds all readings until it is." +actions = [ + "Give the box Internet access (pair it in Matter).", + "Replace the RTC coin cell (inside the case) so the time survives power-offs.", +] + +# ===================================================================== mic +[[guide]] +id = "mic" +title = "Microphone check" +summary = "Switched-off or silent microphone." +recommend = ["mic.disabled", "mic.silent", "mic.read_fail"] +start = "which" + +[[guide.step]] +id = "which" +type = "route" +routes = { "mic.disabled" = "switch", "mic.silent" = "clap", "mic.read_fail" = "end:mic_faulty" } +default = "clap" + +[[guide.step]] +id = "switch" +type = "question" +text = "The firmware reads the microphone as switched off. Does this box have a microphone ON/OFF switch or jumper (inside the case)?" +options = [ + { label = "Yes - I set it to ON", next = "switch_verify" }, + { label = "No such switch / not sure", next = "end:mic_enable_line" }, + { label = "It is meant to be off", next = "end:mic_off_ok" }, +] + +[[guide.step]] +id = "switch_verify" +type = "wait" +text = "The tool restarts the box and waits for a microphone reading (up to 60 s)..." +tool_action = "reset" +until = 'MICROPHONE: Read \d+ bytes' +fail_on = 'Microphone is in shutdown state' +timeout_s = 60 +on_ok = "end:mic_on" +on_fail = "end:mic_enable_line" +on_timeout = "end:mic_enable_line" + +[[guide.step]] +id = "clap" +type = "wait" +text = "Clap your hands or speak loudly right next to the box for about 20 seconds..." +until = 'dB peak: (?!-inf)' +timeout_s = 45 +on_ok = "end:mic_ok" +on_timeout = "end:mic_faulty" + +[[guide.end]] +id = "mic_on" +severity = "ok" +title = "Microphone is on and recording" +text = "The firmware now reads audio samples." +actions = [] + +[[guide.end]] +id = "mic_off_ok" +severity = "info" +title = "Microphone intentionally off" +text = "No noise data is recorded for this box; everything else works." +actions = [] + +[[guide.end]] +id = "mic_enable_line" +severity = "warning" +title = "Microphone enable line stays 'off'" +text = "The firmware keeps reading the microphone as switched off (GPIO3)." +actions = ["Check the microphone board and its cable/connector (inside the case); send the box MAC to the firmware team to confirm the hardware variant."] + +[[guide.end]] +id = "mic_ok" +severity = "ok" +title = "Microphone works" +text = "It picked up sound - the earlier silence was just a very quiet room." +actions = [] + +[[guide.end]] +id = "mic_faulty" +severity = "error" +title = "Microphone records nothing" +text = "Even loud noise next to the box gives no signal." +actions = ["Check the microphone board/cable (inside the case); replace the microphone if needed."] diff --git a/kota_tech/diag/rules.toml b/kota_tech/diag/rules.toml index 861709b..f8b6b5a 100644 --- a/kota_tech/diag/rules.toml +++ b/kota_tech/diag/rules.toml @@ -1,565 +1,572 @@ -# Log signatures for the KOTA sensorbox firmware. -# -# Derived from the firmware source (log strings, Status::set_status calls) and -# checked against real captures (tests/fixtures). Patterns match the cleaned -# line text, not the tag: the deployed v1.0 build logs some messages under -# different tags than the source (e.g. SD mount under INFLUX_BUFFER). -# -# Fields: -# id unique, "." -# pattern Python regex (search). Named groups can be used in `title`. -# severity critical | error | warning | info | ignore -# ignore = never shown (benign ESP_LOGE lines, LED-only rules) -# title short technician-facing headline -# meaning what it means, in plain words -# actions what to do, in order (prefer no-unscrewing actions first) -# explained_by list of rule ids; while one of them is active this finding -# is shown as a consequence of it instead of a root cause -# milestone boot milestone reached when the line is seen -# clears finding ids resolved when this line is seen -# led status LED colour this line sets (firmware Status::set_status) -# led_from only change the LED if it currently has this colour -# (Status::set_status_conditional) -# split_by named group; one finding per distinct value (e.g. per sensor) -# min_count finding becomes active only after this many occurrences -# min_uptime_ms ignore occurrences earlier than this uptime - -# ---------------------------------------------------------------- milestones - -[[rule]] -id = "boot.app_started" -pattern = 'app_init: Project name:\s+kota-sensorboard' -severity = "ignore" -milestone = "app_started" -led = "GREEN" # Status::init() -> STATUS_OK - -[[rule]] -id = "boot.sd_mounted" -pattern = 'SD card mounted successfully' -severity = "ignore" -milestone = "sd_mounted" - -[[rule]] -id = "boot.env_loaded" -pattern = 'Read INFLUX_URL from \.env file' -severity = "ignore" -milestone = "env_loaded" - -[[rule]] -id = "boot.matter_started" -pattern = 'ESP-Matter started successfully' -severity = "ignore" -milestone = "matter_started" - -[[rule]] -id = "boot.local_wifi_mode" -pattern = 'SSID/PASSWORD found in \.env' -severity = "ignore" -milestone = "local_wifi_mode" - -[[rule]] -id = "boot.sensors_ready" -# DeviceStatus::init installs the temperature sensor; it is the last init -# step, and any earlier init failure aborts before reaching it. -pattern = 'temperature_sensor: Range \[' -severity = "ignore" -milestone = "sensors_ready" - -[[rule]] -id = "net.wifi_connected" -pattern = 'sta ip: \d|got ip:|WIFI_SERVICE: Got IP address|IPv4 address changed|Interface IP Address changed' -severity = "ignore" -milestone = "wifi_connected" -clears = ["matter.not_commissioned", "wifi.disconnected"] - -[[rule]] -id = "net.time_synced" -pattern = 'SNTP: Time synchronized' -severity = "ignore" -milestone = "time_synced" -clears = ["rtc.clock_not_running", "net.dns_fail"] - -[[rule]] -id = "influx.upload_ok" -pattern = 'INFLUX: HTTP request performed, status code: 2\d\d' -severity = "ignore" -milestone = "data_uploaded" -clears = ["influx.buffer_fail", "net.dns_fail", "net.tls_fail"] - -[[rule]] -id = "influx.write_ok" -pattern = 'Successfully wrote to Influx' -severity = "ignore" -milestone = "data_uploaded" -led = "GREEN" -led_from = "PURPLE" - -[[rule]] -id = "ota.registered" -pattern = 'Device registered successfully|OTA token loaded from NVS' -severity = "ignore" -milestone = "ota_registered" -clears = ["ota.registration_failed"] - -[[rule]] -id = "ota.checked" -pattern = 'OTA_CLIENT: No update available' -severity = "ignore" -milestone = "ota_checked" -clears = ["ota.check_failed"] -led = "GREEN" -led_from = "PURPLE" - -# ----------------------------------------------------------- benign E lines - -[[rule]] -id = "benign.mac" -pattern = 'ID: Device MAC address' -severity = "ignore" - -[[rule]] -id = "benign.attr_cb" -pattern = 'MAIN: Attribute update callback' -severity = "ignore" - -[[rule]] -id = "benign.zcl" -pattern = 'chip\[ZCL\]: WRITE ERR|data_model: Cluster cannot be NULL' -severity = "ignore" - -[[rule]] -id = "benign.connect_chain" -# Transport-level echo of a failure that a more specific rule reports. -pattern = 'esp-tls: Failed to open new connection|transport_base: Failed to open a new connection|HTTP_CLIENT: Connection failed, sock < 0|INFLUX: Failed to perform HTTP request: 0,|INFLUX_BUFFER: Failed to write chunk to Influx|OTA_CLIENT: Error ESP_ERR_HTTP_CONNECT at' -severity = "ignore" - -# ------------------------------------------------------------------ network - -[[rule]] -id = "matter.not_commissioned" -pattern = 'CHIPoBLE advertising started|MAIN: Commissioning window opened' -severity = "warning" -title = "Box is not connected to Wi-Fi (not commissioned in Matter)" -meaning = "The box is waiting to be added to a Matter network over Bluetooth. Until then it has no Wi-Fi, so it cannot upload data or receive firmware updates." -actions = [ - "Add the box in the customer's Matter app (Apple Home, Google Home, ...) by scanning the QR sticker, or enter the manual code printed under it.", - "Use a 2.4 GHz Wi-Fi network; keep the phone close to the box during pairing.", - "If pairing keeps failing: hold the Matter button 5 s (factory reset) and try again.", -] -milestone = "ble_advertising" - -[[rule]] -id = "matter.commissioning_failed" -pattern = 'Commissioning failed, fail safe timer expired' -severity = "error" -title = "Matter pairing attempt failed" -meaning = "A phone started adding the box to Matter but did not finish in time." -actions = [ - "Retry pairing from the Matter app with the phone next to the box.", - "Check the Wi-Fi is 2.4 GHz and the password entered in the app is correct.", -] - -[[rule]] -id = "net.dns_fail" -pattern = '''couldn't get hostname for :(?P[\w.-]+)''' -severity = "error" -title = "No Internet: server names cannot be resolved" -meaning = "The box could not look up a server name. Either it has no Wi-Fi connection, or the network has no working Internet/DNS." -actions = [ - "Check the site Wi-Fi has Internet (open a website on a phone connected to the same network).", - "If the box was never paired: commission it in Matter first.", - "Check the router does not block new devices (guest isolation, MAC filtering).", -] -explained_by = ["matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] - -[[rule]] -id = "net.tls_fail" -pattern = 'mbedtls_ssl_handshake returned|Failed to verify peer certificate|esp-tls-mbedtls: .*[Hh]andshake' -severity = "error" -title = "Secure connection to the server failed" -meaning = "The box reached the server but the encrypted (HTTPS) connection failed. Common causes: wrong clock on the box, or a network that intercepts HTTPS (corporate proxy/firewall)." -actions = [ - "Try another network (e.g. phone hotspot) to rule out a firewall.", - "Check the clock finding below: HTTPS needs the correct date.", -] -explained_by = ["rtc.clock_not_running"] - -[[rule]] -id = "wifi.disconnected" -pattern = 'WiFi disconnected, retrying in' -severity = "error" -min_count = 3 -title = "Box cannot connect to the configured Wi-Fi" -meaning = "The Wi-Fi name/password from the SD card does not work: wrong password, network out of range, or not 2.4 GHz." -actions = [ - "Check SSID and PASSWORD in ENV.TXT (re-provision the SD card with the tool).", - "Make sure the network is 2.4 GHz and in range.", -] - -[[rule]] -id = "wifi.setup_portal" -pattern = 'WiFi provisioning portal ready: connect to "(?P[^"]+)"' -severity = "warning" -title = "Box is in Wi-Fi setup mode (network {ssid})" -meaning = "The box is hosting its own Wi-Fi network for configuration instead of connecting to the site Wi-Fi." -actions = [ - "Connect a phone to {ssid} and open http://sensorbox.local/ to enter the Wi-Fi details,", - "or short-press the Matter button (< 2 s) to leave setup mode.", -] -led = "WHITE" - -# ------------------------------------------------------------------- InfluxDB - -[[rule]] -id = "influx.buffer_fail" -pattern = 'Failed to write chunk with \d+ retries to Influx|MAIN: Failed to flush Influx buffer' -severity = "error" -title = "Measurements cannot be uploaded to InfluxDB" -meaning = "Uploads keep failing, so readings are stored on the SD card and sent later. The LED turns purple and the box restarts itself after about 2.5 minutes in this state." -actions = [ - "Fix the network problem first (see the finding this is grouped under).", - "Buffered data is uploaded automatically once the connection works.", -] -explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] - -[[rule]] -id = "influx.purple" -pattern = 'Failed to write chunk with \d+ retries to Influx|Failed to flush buffer before writing|Failed to append new entry to buffer' -severity = "ignore" -led = "PURPLE" - -[[rule]] -id = "influx.auth" -pattern = 'INFLUX: Failed to perform HTTP request: (?P401|403)' -severity = "critical" -title = "InfluxDB rejected the token (HTTP {code})" -meaning = "The box reaches the database but the INFLUX_TOKEN on the SD card is wrong or revoked." -actions = [ - "Re-provision the SD card with the current ENV.TXT (SD card is inside the case).", - "If all boxes show this: the shared token was rotated - update ENV.TXT for everyone.", -] - -[[rule]] -id = "influx.not_found" -pattern = 'INFLUX: Failed to perform HTTP request: (?P404)' -severity = "critical" -title = "InfluxDB bucket or organisation not found (HTTP 404)" -meaning = "INFLUX_URL on the SD card points to a bucket/org that does not exist." -actions = ["Re-provision the SD card with the correct ENV.TXT."] - -[[rule]] -id = "influx.server_error" -pattern = 'INFLUX: Failed to perform HTTP request: (?P5\d\d)' -severity = "warning" -title = "InfluxDB server error (HTTP {code})" -meaning = "The database server has a problem. The box is fine; data is buffered on the SD card." -actions = ["Nothing to fix on the box. Report to the backend team if it persists."] - -[[rule]] -id = "influx.bad_request" -pattern = 'INFLUX: Bad request, check line protocol format' -severity = "warning" -title = "InfluxDB refused some measurements (HTTP 400)" -meaning = "A measurement was malformed and dropped (firmware issue, not a hardware fault)." -actions = ["Save the session log and send it to the firmware team."] - -[[rule]] -id = "influx.env_missing" -split_by = "key" -pattern = 'Failed to read (?PINFLUX_URL|INFLUX_TOKEN) from \.env file' -severity = "critical" -title = "ENV.TXT on the SD card is missing {key}" -meaning = "The box cannot start without the InfluxDB settings; it shows white and restarts." -actions = ["Re-provision the SD card with the tool (SD card is inside the case)."] - -[[rule]] -id = "influx.init_fail" -pattern = 'MAIN: Failed to initialize Influx buffer' -severity = "critical" -title = "Data upload could not be initialised" -meaning = "Start-up stopped because the InfluxDB settings could not be read from the SD card. The box restarts." -actions = ["Re-provision the SD card with the tool (SD card is inside the case)."] -explained_by = ["influx.env_missing", "sd.mount_fail", "sd.card_fail", "sd.env_open_fail"] -led = "WHITE" - -# ----------------------------------------------------------------- SD card - -[[rule]] -id = "sd.card_fail" -pattern = 'Failed to initialize the card \((?P[^)]+)\)' -severity = "critical" -title = "SD card not detected ({err})" -meaning = "The SD card does not respond: missing, not seated, or damaged. The box shows white and restarts." -actions = [ - "Open the case and re-seat the SD card.", - "Try a freshly provisioned card.", -] -led = "WHITE" - -[[rule]] -id = "sd.mount_fail" -pattern = 'Failed to mount filesystem' -severity = "critical" -title = "SD card is not formatted correctly" -meaning = "The card responds but has no readable FAT32 file system." -actions = ["Re-provision the card with the tool (FAT32, MBR) - SD card is inside the case."] -led = "WHITE" - -[[rule]] -id = "sd.env_open_fail" -pattern = 'Failed to open \.env file for reading' -severity = "critical" -title = "ENV.TXT not found on the SD card" -meaning = "The card is readable but the configuration file is missing." -actions = ["Re-provision the card with the tool (SD card is inside the case)."] - -[[rule]] -id = "sd.write_fail" -pattern = 'Failed to (create buffer file|open buffer file for appending)' -severity = "error" -title = "Cannot write to the SD card" -meaning = "Offline data cannot be stored: the card is full, write-protected or failing." -actions = ["Replace / re-provision the SD card (inside the case)."] - -# --------------------------------------------------------------- RTC / I2C - -[[rule]] -id = "rtc.init_failed" -pattern = 'MAIN: Failed to initialize RTC: (?P\S+)' -severity = "critical" -title = "Clock chip (RTC) or I2C bus not responding ({err})" -meaning = "The RTC is the first chip the firmware talks to over I2C, so this also appears when the I2C cable between the boards is loose or broken. LED blue, the box restarts." -actions = [ - "Open the case and check the I2C cable/connector between the boards.", - "If the cable is fine: the RTC module is faulty.", -] -led = "BLUE" - -[[rule]] -id = "rtc.clock_not_running" -pattern = 'RTC is uninitialized, using current time as timestamp' -severity = "warning" -min_count = 5 -title = "Clock is not set - sensor readings are on hold" -meaning = "The clock chip answers but its clock is not running (it reads 1 Jan 2000; typical after its coin cell was removed or is empty), and there is no Internet time yet. Readings are held until the time is set, so no data is recorded." -actions = [ - "Give the box Internet access: the clock is set automatically on the first connection.", - "If this comes back after every power-off: replace the RTC coin cell (inside the case).", -] - -[[rule]] -id = "i2c.errors" -pattern = 'I2C (read|write) failed: (?P\S+)|Failed to add I2C device' -severity = "error" -min_count = 2 -title = "I2C bus communication errors" -meaning = "Sensors are not answering reliably on the I2C bus: loose connector, damaged cable, or a failing sensor." -actions = ["Open the case and check the I2C cable/connectors between the boards."] - -# ------------------------------------------------------------------ sensors - -[[rule]] -id = "sensor.init_failed" -split_by = "sensor" -pattern = 'MAIN: Failed to initialize (?PBME688|SEN66|AS7341|Microphone|Flicker sensor|DeviceStatus): (?P.+)' -severity = "critical" -title = "{sensor} failed to start" -meaning = "Start-up stopped at the {sensor} sensor ({err}). LED red, the box restarts." -actions = [ - "Open the case and check the {sensor} connector/cable.", - "If several sensors fail in turn: check the shared I2C cable.", -] -led = "RED" - -[[rule]] -id = "sensor.selfcheck_failed" -split_by = "sensor" -pattern = '(?PBME688|SEN66|AS7341|Microphone|Flicker sensor) self check failed' -severity = "error" -title = "{sensor} failed the post-update self-check" -meaning = "After a firmware update the {sensor} did not work; the box rolls back to the previous firmware." -actions = ["Check the {sensor} connector (inside the case), then power-cycle."] - -[[rule]] -id = "sen66.not_ready" -pattern = 'SEN66: (Failed while awaiting sensor ready|Self-check failed: Sensor not ready|Failed to read measurement)' -severity = "error" -title = "Air-quality sensor (SEN66) not delivering data" -meaning = "The SEN66 answers but never reports a measurement." -actions = ["Check the SEN66 cable (inside the case); the sensor may be faulty."] - -[[rule]] -id = "bme688.read_fail" -pattern = 'Failed to get (BME688 )?data from BME688|No new data available from BME688' -severity = "warning" -min_count = 3 -title = "Temperature/humidity sensor (BME688) read errors" -meaning = "The BME688 repeatedly fails to return a reading." -actions = ["Check the BME688 connection (inside the case)."] - -[[rule]] -id = "as7341.read_fail" -pattern = 'Failed to read (spectral|basic counts) data' -severity = "warning" -min_count = 2 -title = "Light sensor (AS7341) read errors" -meaning = "The AS7341 repeatedly fails to return a reading." -actions = ["Check the AS7341 connection (inside the case)."] - -[[rule]] -id = "mic.silent" -pattern = 'MICROPHONE: .*dB peak: -inf' -severity = "warning" -min_count = 2 -title = "Microphone records pure silence" -meaning = "Every audio sample is zero. A real room is never perfectly silent, so the microphone or its wiring is likely faulty." -actions = [ - "Make some noise near the box and watch whether this finding keeps growing.", - "If it does: check the microphone board/cable (inside the case).", -] - -[[rule]] -id = "mic.read_fail" -pattern = 'Failed to read samples' -severity = "error" -title = "Microphone read error" -meaning = "The audio interface returned an error." -actions = ["Check the microphone board/cable (inside the case)."] - -[[rule]] -id = "gather.stalled" -pattern = 'tasks still running, waiting' -severity = "warning" -min_uptime_ms = 180000 -min_count = 5 -title = "Sensor readings are stuck" -meaning = "A sensor has not finished its reading for minutes (the first 2 minutes of warm-up are normal)." -actions = ["See the grouped cause, or note which sensor stopped logging and check its cable."] -explained_by = ["rtc.clock_not_running", "sen66.not_ready"] - -# ---------------------------------------------------------- OTA / firmware - -[[rule]] -id = "ota.registration_failed" -pattern = 'Device registration failed' -severity = "warning" -title = "Box is not registered for firmware updates" -meaning = "The box could not reach the update server (bin.kota-app.com) to register, so it will not receive new firmware." -actions = ["Fix the network problem; registration is retried automatically every few seconds."] -explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] - -[[rule]] -id = "ota.check_failed" -pattern = 'Failed to check for updates|OTA Update check failed with status code: (?P\d+)' -severity = "error" -title = "Firmware update check failed" -meaning = "The update server could not be reached or refused the request. LED purple." -actions = ["Fix the network problem; the check is retried every 15 minutes."] -explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected"] -led = "PURPLE" - -[[rule]] -id = "ota.unauthorized" -pattern = 'Unauthorized, clearing saved token' -severity = "warning" -title = "Update server did not accept the box - it will re-register" -meaning = "The saved update token was rejected; the box registers again automatically." -actions = ["Nothing to do unless it repeats. Then report the box MAC to the backend team."] - -[[rule]] -id = "ota.updating" -pattern = 'New update available, starting OTA update' -severity = "info" -title = "Firmware update is downloading - do not switch off" -meaning = "The box found new firmware and is installing it (LED yellow). It restarts when done." -actions = ["Wait. Do not switch the power off."] -milestone = "ota_update_started" -led = "YELLOW" - -[[rule]] -id = "ota.update_failed" -pattern = 'OTA update failed: (?P\S+)' -severity = "error" -title = "Firmware update failed ({err})" -meaning = "The download or installation was interrupted; the box keeps its current firmware and retries later." -actions = ["Check the network is stable; the update is retried automatically."] - -[[rule]] -id = "ota.update_ok" -pattern = 'OTA update successful, rebooting' -severity = "info" -title = "Firmware update installed - restarting" -meaning = "New firmware was installed. After the restart it runs a self-check (LED orange, ~2.5 min)." -actions = ["Wait for green."] -milestone = "ota_update_done" - -[[rule]] -id = "ota.selfcheck" -pattern = 'Device is in selfcheck mode' -severity = "info" -title = "Post-update self-check running (~2.5 min)" -meaning = "The new firmware is testing all sensors before it is accepted (LED orange)." -actions = ["Wait. Do not switch off."] -led = "ORANGE" - -[[rule]] -id = "ota.selfcheck_failed" -pattern = 'Failing selfcheck: (?P.+)' -severity = "error" -title = "Update self-check failed: {reason}" -meaning = "The new firmware rejected itself; the box rolls back to the previous version." -actions = ["Check the named sensor (inside the case), then power-cycle."] -led = "RED" - -[[rule]] -id = "ota.selfcheck_passed" -pattern = 'Passing selfcheck' -severity = "ignore" -milestone = "ota_update_accepted" -led = "GREEN" - -[[rule]] -id = "ota.reset_during_update" -pattern = 'Device was reset during update' -severity = "warning" -title = "Box was switched off during a firmware update" -meaning = "An update was interrupted; the box reports it and retries." -actions = ["Leave the box powered while the LED is yellow or orange."] - -# --------------------------------------------------------------- system - -[[rule]] -id = "sys.out_of_resources" -pattern = 'Failed to create (task for sensor|gather task|main gather task)' -severity = "error" -title = "Firmware ran out of memory" -meaning = "The firmware could not start an internal task (LED red); it restarts itself after 30 s." -actions = ["Power-cycle. If it repeats, save the session log for the firmware team."] -led = "RED" - -[[rule]] -id = "sys.factory_reset" -pattern = 'Factory reset button pressed|Factory resetting device' -severity = "warning" -title = "Factory reset triggered with the Matter button" -meaning = "The box forgets its Matter network and must be paired again with the QR sticker." -actions = ["Re-commission the box in the Matter app."] -led = "WHITE" - -[[rule]] -id = "mic.disabled" -pattern = 'MICROPHONE: Microphone is in shutdown state' -severity = "info" -title = "Microphone is switched off - no noise measurements" -meaning = "The firmware reads the microphone enable line (GPIO3) as 'off', which it treats as disabled on purpose. Noise levels are not recorded." -actions = ["If this box should measure noise: check the microphone enable switch/jumper and its wiring (inside the case)."] - -[[rule]] -id = "gather.empty_reading" -pattern = 'SENSOR_GATHERER: Failed to get line protocol from sensor' -severity = "warning" -min_count = 2 -title = "A sensor returned no data" -meaning = "One of the sensors skipped its reading; the preceding log lines name the sensor." -actions = ["Check the log lines just before this message for the sensor name."] -explained_by = ["mic.disabled", "mic.read_fail", "bme688.read_fail", "as7341.read_fail", "rtc.clock_not_running"] +# Log signatures for the KOTA sensorbox firmware. +# +# Derived from the firmware source (log strings, Status::set_status calls) and +# checked against real captures (tests/fixtures). Patterns match the cleaned +# line text, not the tag: the deployed v1.0 build logs some messages under +# different tags than the source (e.g. SD mount under INFLUX_BUFFER). +# +# Fields: +# id unique, "." +# pattern Python regex (search). Named groups can be used in `title`. +# severity critical | error | warning | info | ignore +# ignore = never shown (benign ESP_LOGE lines, LED-only rules) +# title short technician-facing headline +# meaning what it means, in plain words +# actions what to do, in order (prefer no-unscrewing actions first) +# explained_by list of rule ids; while one of them is active this finding +# is shown as a consequence of it instead of a root cause +# milestone boot milestone reached when the line is seen +# clears finding ids resolved when this line is seen +# led status LED colour this line sets (firmware Status::set_status) +# led_from only change the LED if it currently has this colour +# (Status::set_status_conditional) +# split_by named group; one finding per distinct value (e.g. per sensor) +# min_count finding becomes active only after this many occurrences +# min_uptime_ms ignore occurrences earlier than this uptime + +# ---------------------------------------------------------------- milestones + +[[rule]] +id = "boot.app_started" +pattern = 'app_init: Project name:\s+kota-sensorboard' +severity = "ignore" +milestone = "app_started" +led = "GREEN" # Status::init() -> STATUS_OK + +[[rule]] +id = "boot.sd_mounted" +pattern = 'SD card mounted successfully' +severity = "ignore" +milestone = "sd_mounted" + +[[rule]] +id = "boot.env_loaded" +pattern = 'Read INFLUX_URL from \.env file' +severity = "ignore" +milestone = "env_loaded" + +[[rule]] +id = "boot.matter_started" +pattern = 'ESP-Matter started successfully' +severity = "ignore" +milestone = "matter_started" + +[[rule]] +id = "boot.local_wifi_mode" +pattern = 'SSID/PASSWORD found in \.env' +severity = "ignore" +milestone = "local_wifi_mode" + +[[rule]] +id = "boot.sensors_ready" +# DeviceStatus::init installs the temperature sensor; it is the last init +# step, and any earlier init failure aborts before reaching it. +pattern = 'temperature_sensor: Range \[' +severity = "ignore" +milestone = "sensors_ready" + +[[rule]] +id = "net.wifi_connected" +pattern = 'sta ip: \d|got ip:|WIFI_SERVICE: Got IP address|IPv4 address changed|Interface IP Address changed' +severity = "ignore" +milestone = "wifi_connected" +clears = ["matter.not_commissioned", "wifi.disconnected"] + +[[rule]] +id = "matter.commissioned" +pattern = 'MAIN: Commissioning complete|MAIN: Fabric is committed' +severity = "ignore" +milestone = "matter_commissioned" +clears = ["matter.not_commissioned", "matter.commissioning_failed"] + +[[rule]] +id = "net.time_synced" +pattern = 'SNTP: Time synchronized' +severity = "ignore" +milestone = "time_synced" +clears = ["rtc.clock_not_running", "net.dns_fail"] + +[[rule]] +id = "influx.upload_ok" +pattern = 'INFLUX: HTTP request performed, status code: 2\d\d' +severity = "ignore" +milestone = "data_uploaded" +clears = ["influx.buffer_fail", "net.dns_fail", "net.tls_fail"] + +[[rule]] +id = "influx.write_ok" +pattern = 'Successfully wrote to Influx' +severity = "ignore" +milestone = "data_uploaded" +led = "GREEN" +led_from = "PURPLE" + +[[rule]] +id = "ota.registered" +pattern = 'Device registered successfully|OTA token loaded from NVS' +severity = "ignore" +milestone = "ota_registered" +clears = ["ota.registration_failed"] + +[[rule]] +id = "ota.checked" +pattern = 'OTA_CLIENT: No update available' +severity = "ignore" +milestone = "ota_checked" +clears = ["ota.check_failed"] +led = "GREEN" +led_from = "PURPLE" + +# ----------------------------------------------------------- benign E lines + +[[rule]] +id = "benign.mac" +pattern = 'ID: Device MAC address' +severity = "ignore" + +[[rule]] +id = "benign.attr_cb" +pattern = 'MAIN: Attribute update callback' +severity = "ignore" + +[[rule]] +id = "benign.zcl" +pattern = 'chip\[ZCL\]: WRITE ERR|data_model: Cluster cannot be NULL' +severity = "ignore" + +[[rule]] +id = "benign.connect_chain" +# Transport-level echo of a failure that a more specific rule reports. +pattern = 'esp-tls: Failed to open new connection|transport_base: Failed to open a new connection|HTTP_CLIENT: Connection failed, sock < 0|INFLUX: Failed to perform HTTP request: 0,|INFLUX_BUFFER: Failed to write chunk to Influx|OTA_CLIENT: Error ESP_ERR_HTTP_CONNECT at' +severity = "ignore" + +# ------------------------------------------------------------------ network + +[[rule]] +id = "matter.not_commissioned" +pattern = 'CHIPoBLE advertising started|MAIN: Commissioning window opened' +severity = "warning" +title = "Box is not connected to Wi-Fi (not commissioned in Matter)" +meaning = "The box is waiting to be added to a Matter network over Bluetooth. Until then it has no Wi-Fi, so it cannot upload data or receive firmware updates." +actions = [ + "Add the box in the customer's Matter app (Apple Home, Google Home, ...) by scanning the QR sticker, or enter the manual code printed under it.", + "Use a 2.4 GHz Wi-Fi network; keep the phone close to the box during pairing.", + "If pairing keeps failing: hold the Matter button 5 s (factory reset) and try again.", +] +milestone = "ble_advertising" + +[[rule]] +id = "matter.commissioning_failed" +pattern = 'Commissioning failed, fail safe timer expired' +severity = "error" +title = "Matter pairing attempt failed" +meaning = "A phone started adding the box to Matter but did not finish in time." +actions = [ + "Retry pairing from the Matter app with the phone next to the box.", + "Check the Wi-Fi is 2.4 GHz and the password entered in the app is correct.", +] + +[[rule]] +id = "net.dns_fail" +pattern = '''couldn't get hostname for :(?P[\w.-]+)''' +severity = "error" +title = "No Internet: server names cannot be resolved" +meaning = "The box could not look up a server name. Either it has no Wi-Fi connection, or the network has no working Internet/DNS." +actions = [ + "Check the site Wi-Fi has Internet (open a website on a phone connected to the same network).", + "If the box was never paired: commission it in Matter first.", + "Check the router does not block new devices (guest isolation, MAC filtering).", +] +explained_by = ["matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] + +[[rule]] +id = "net.tls_fail" +pattern = 'mbedtls_ssl_handshake returned|Failed to verify peer certificate|esp-tls-mbedtls: .*[Hh]andshake' +severity = "error" +title = "Secure connection to the server failed" +meaning = "The box reached the server but the encrypted (HTTPS) connection failed. Common causes: wrong clock on the box, or a network that intercepts HTTPS (corporate proxy/firewall)." +actions = [ + "Try another network (e.g. phone hotspot) to rule out a firewall.", + "Check the clock finding below: HTTPS needs the correct date.", +] +explained_by = ["rtc.clock_not_running"] + +[[rule]] +id = "wifi.disconnected" +pattern = 'WiFi disconnected, retrying in' +severity = "error" +min_count = 3 +title = "Box cannot connect to the configured Wi-Fi" +meaning = "The Wi-Fi name/password from the SD card does not work: wrong password, network out of range, or not 2.4 GHz." +actions = [ + "Check SSID and PASSWORD in ENV.TXT (re-provision the SD card with the tool).", + "Make sure the network is 2.4 GHz and in range.", +] + +[[rule]] +id = "wifi.setup_portal" +pattern = 'WiFi provisioning portal ready: connect to "(?P[^"]+)"' +severity = "warning" +title = "Box is in Wi-Fi setup mode (network {ssid})" +meaning = "The box is hosting its own Wi-Fi network for configuration instead of connecting to the site Wi-Fi." +actions = [ + "Connect a phone to {ssid} and open http://sensorbox.local/ to enter the Wi-Fi details,", + "or short-press the Matter button (< 2 s) to leave setup mode.", +] +led = "WHITE" + +# ------------------------------------------------------------------- InfluxDB + +[[rule]] +id = "influx.buffer_fail" +pattern = 'Failed to write chunk with \d+ retries to Influx|MAIN: Failed to flush Influx buffer' +severity = "error" +title = "Measurements cannot be uploaded to InfluxDB" +meaning = "Uploads keep failing, so readings are stored on the SD card and sent later. The LED turns purple and the box restarts itself after about 2.5 minutes in this state." +actions = [ + "Fix the network problem first (see the finding this is grouped under).", + "Buffered data is uploaded automatically once the connection works.", +] +explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] + +[[rule]] +id = "influx.purple" +pattern = 'Failed to write chunk with \d+ retries to Influx|Failed to flush buffer before writing|Failed to append new entry to buffer' +severity = "ignore" +led = "PURPLE" + +[[rule]] +id = "influx.auth" +pattern = 'INFLUX: Failed to perform HTTP request: (?P401|403)' +severity = "critical" +title = "InfluxDB rejected the token (HTTP {code})" +meaning = "The box reaches the database but the INFLUX_TOKEN on the SD card is wrong or revoked." +actions = [ + "Re-provision the SD card with the current ENV.TXT (SD card is inside the case).", + "If all boxes show this: the shared token was rotated - update ENV.TXT for everyone.", +] + +[[rule]] +id = "influx.not_found" +pattern = 'INFLUX: Failed to perform HTTP request: (?P404)' +severity = "critical" +title = "InfluxDB bucket or organisation not found (HTTP 404)" +meaning = "INFLUX_URL on the SD card points to a bucket/org that does not exist." +actions = ["Re-provision the SD card with the correct ENV.TXT."] + +[[rule]] +id = "influx.server_error" +pattern = 'INFLUX: Failed to perform HTTP request: (?P5\d\d)' +severity = "warning" +title = "InfluxDB server error (HTTP {code})" +meaning = "The database server has a problem. The box is fine; data is buffered on the SD card." +actions = ["Nothing to fix on the box. Report to the backend team if it persists."] + +[[rule]] +id = "influx.bad_request" +pattern = 'INFLUX: Bad request, check line protocol format' +severity = "warning" +title = "InfluxDB refused some measurements (HTTP 400)" +meaning = "A measurement was malformed and dropped (firmware issue, not a hardware fault)." +actions = ["Save the session log and send it to the firmware team."] + +[[rule]] +id = "influx.env_missing" +split_by = "key" +pattern = 'Failed to read (?PINFLUX_URL|INFLUX_TOKEN) from \.env file' +severity = "critical" +title = "ENV.TXT on the SD card is missing {key}" +meaning = "The box cannot start without the InfluxDB settings; it shows white and restarts." +actions = ["Re-provision the SD card with the tool (SD card is inside the case)."] + +[[rule]] +id = "influx.init_fail" +pattern = 'MAIN: Failed to initialize Influx buffer' +severity = "critical" +title = "Data upload could not be initialised" +meaning = "Start-up stopped because the InfluxDB settings could not be read from the SD card. The box restarts." +actions = ["Re-provision the SD card with the tool (SD card is inside the case)."] +explained_by = ["influx.env_missing", "sd.mount_fail", "sd.card_fail", "sd.env_open_fail"] +led = "WHITE" + +# ----------------------------------------------------------------- SD card + +[[rule]] +id = "sd.card_fail" +pattern = 'Failed to initialize the card \((?P[^)]+)\)' +severity = "critical" +title = "SD card not detected ({err})" +meaning = "The SD card does not respond: missing, not seated, or damaged. The box shows white and restarts." +actions = [ + "Open the case and re-seat the SD card.", + "Try a freshly provisioned card.", +] +led = "WHITE" + +[[rule]] +id = "sd.mount_fail" +pattern = 'Failed to mount filesystem' +severity = "critical" +title = "SD card is not formatted correctly" +meaning = "The card responds but has no readable FAT32 file system." +actions = ["Re-provision the card with the tool (FAT32, MBR) - SD card is inside the case."] +led = "WHITE" + +[[rule]] +id = "sd.env_open_fail" +pattern = 'Failed to open \.env file for reading' +severity = "critical" +title = "ENV.TXT not found on the SD card" +meaning = "The card is readable but the configuration file is missing." +actions = ["Re-provision the card with the tool (SD card is inside the case)."] + +[[rule]] +id = "sd.write_fail" +pattern = 'Failed to (create buffer file|open buffer file for appending)' +severity = "error" +title = "Cannot write to the SD card" +meaning = "Offline data cannot be stored: the card is full, write-protected or failing." +actions = ["Replace / re-provision the SD card (inside the case)."] + +# --------------------------------------------------------------- RTC / I2C + +[[rule]] +id = "rtc.init_failed" +pattern = 'MAIN: Failed to initialize RTC: (?P\S+)' +severity = "critical" +title = "Clock chip (RTC) or I2C bus not responding ({err})" +meaning = "The RTC is the first chip the firmware talks to over I2C, so this also appears when the I2C cable between the boards is loose or broken. LED blue, the box restarts." +actions = [ + "Open the case and check the I2C cable/connector between the boards.", + "If the cable is fine: the RTC module is faulty.", +] +led = "BLUE" + +[[rule]] +id = "rtc.clock_not_running" +pattern = 'RTC is uninitialized, using current time as timestamp' +severity = "warning" +min_count = 5 +title = "Clock is not set - sensor readings are on hold" +meaning = "The clock chip answers but its clock is not running (it reads 1 Jan 2000; typical after its coin cell was removed or is empty), and there is no Internet time yet. Readings are held until the time is set, so no data is recorded." +actions = [ + "Give the box Internet access: the clock is set automatically on the first connection.", + "If this comes back after every power-off: replace the RTC coin cell (inside the case).", +] + +[[rule]] +id = "i2c.errors" +pattern = 'I2C (read|write) failed: (?P\S+)|Failed to add I2C device' +severity = "error" +min_count = 2 +title = "I2C bus communication errors" +meaning = "Sensors are not answering reliably on the I2C bus: loose connector, damaged cable, or a failing sensor." +actions = ["Open the case and check the I2C cable/connectors between the boards."] + +# ------------------------------------------------------------------ sensors + +[[rule]] +id = "sensor.init_failed" +split_by = "sensor" +pattern = 'MAIN: Failed to initialize (?PBME688|SEN66|AS7341|Microphone|Flicker sensor|DeviceStatus): (?P.+)' +severity = "critical" +title = "{sensor} failed to start" +meaning = "Start-up stopped at the {sensor} sensor ({err}). LED red, the box restarts." +actions = [ + "Open the case and check the {sensor} connector/cable.", + "If several sensors fail in turn: check the shared I2C cable.", +] +led = "RED" + +[[rule]] +id = "sensor.selfcheck_failed" +split_by = "sensor" +pattern = '(?PBME688|SEN66|AS7341|Microphone|Flicker sensor) self check failed' +severity = "error" +title = "{sensor} failed the post-update self-check" +meaning = "After a firmware update the {sensor} did not work; the box rolls back to the previous firmware." +actions = ["Check the {sensor} connector (inside the case), then power-cycle."] + +[[rule]] +id = "sen66.not_ready" +pattern = 'SEN66: (Failed while awaiting sensor ready|Self-check failed: Sensor not ready|Failed to read measurement)' +severity = "error" +title = "Air-quality sensor (SEN66) not delivering data" +meaning = "The SEN66 answers but never reports a measurement." +actions = ["Check the SEN66 cable (inside the case); the sensor may be faulty."] + +[[rule]] +id = "bme688.read_fail" +pattern = 'Failed to get (BME688 )?data from BME688|No new data available from BME688' +severity = "warning" +min_count = 3 +title = "Temperature/humidity sensor (BME688) read errors" +meaning = "The BME688 repeatedly fails to return a reading." +actions = ["Check the BME688 connection (inside the case)."] + +[[rule]] +id = "as7341.read_fail" +pattern = 'Failed to read (spectral|basic counts) data' +severity = "warning" +min_count = 2 +title = "Light sensor (AS7341) read errors" +meaning = "The AS7341 repeatedly fails to return a reading." +actions = ["Check the AS7341 connection (inside the case)."] + +[[rule]] +id = "mic.silent" +pattern = 'MICROPHONE: .*dB peak: -inf' +severity = "warning" +min_count = 2 +title = "Microphone records pure silence" +meaning = "Every audio sample is zero. A real room is never perfectly silent, so the microphone or its wiring is likely faulty." +actions = [ + "Make some noise near the box and watch whether this finding keeps growing.", + "If it does: check the microphone board/cable (inside the case).", +] + +[[rule]] +id = "mic.read_fail" +pattern = 'Failed to read samples' +severity = "error" +title = "Microphone read error" +meaning = "The audio interface returned an error." +actions = ["Check the microphone board/cable (inside the case)."] + +[[rule]] +id = "gather.stalled" +pattern = 'tasks still running, waiting' +severity = "warning" +min_uptime_ms = 180000 +min_count = 5 +title = "Sensor readings are stuck" +meaning = "A sensor has not finished its reading for minutes (the first 2 minutes of warm-up are normal)." +actions = ["See the grouped cause, or note which sensor stopped logging and check its cable."] +explained_by = ["rtc.clock_not_running", "sen66.not_ready"] + +# ---------------------------------------------------------- OTA / firmware + +[[rule]] +id = "ota.registration_failed" +pattern = 'Device registration failed' +severity = "warning" +title = "Box is not registered for firmware updates" +meaning = "The box could not reach the update server (bin.kota-app.com) to register, so it will not receive new firmware." +actions = ["Fix the network problem; registration is retried automatically every few seconds."] +explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected", "wifi.setup_portal"] + +[[rule]] +id = "ota.check_failed" +pattern = 'Failed to check for updates|OTA Update check failed with status code: (?P\d+)' +severity = "error" +title = "Firmware update check failed" +meaning = "The update server could not be reached or refused the request. LED purple." +actions = ["Fix the network problem; the check is retried every 15 minutes."] +explained_by = ["net.dns_fail", "net.tls_fail", "matter.not_commissioned", "wifi.disconnected"] +led = "PURPLE" + +[[rule]] +id = "ota.unauthorized" +pattern = 'Unauthorized, clearing saved token' +severity = "warning" +title = "Update server did not accept the box - it will re-register" +meaning = "The saved update token was rejected; the box registers again automatically." +actions = ["Nothing to do unless it repeats. Then report the box MAC to the backend team."] + +[[rule]] +id = "ota.updating" +pattern = 'New update available, starting OTA update' +severity = "info" +title = "Firmware update is downloading - do not switch off" +meaning = "The box found new firmware and is installing it (LED yellow). It restarts when done." +actions = ["Wait. Do not switch the power off."] +milestone = "ota_update_started" +led = "YELLOW" + +[[rule]] +id = "ota.update_failed" +pattern = 'OTA update failed: (?P\S+)' +severity = "error" +title = "Firmware update failed ({err})" +meaning = "The download or installation was interrupted; the box keeps its current firmware and retries later." +actions = ["Check the network is stable; the update is retried automatically."] + +[[rule]] +id = "ota.update_ok" +pattern = 'OTA update successful, rebooting' +severity = "info" +title = "Firmware update installed - restarting" +meaning = "New firmware was installed. After the restart it runs a self-check (LED orange, ~2.5 min)." +actions = ["Wait for green."] +milestone = "ota_update_done" + +[[rule]] +id = "ota.selfcheck" +pattern = 'Device is in selfcheck mode' +severity = "info" +title = "Post-update self-check running (~2.5 min)" +meaning = "The new firmware is testing all sensors before it is accepted (LED orange)." +actions = ["Wait. Do not switch off."] +led = "ORANGE" + +[[rule]] +id = "ota.selfcheck_failed" +pattern = 'Failing selfcheck: (?P.+)' +severity = "error" +title = "Update self-check failed: {reason}" +meaning = "The new firmware rejected itself; the box rolls back to the previous version." +actions = ["Check the named sensor (inside the case), then power-cycle."] +led = "RED" + +[[rule]] +id = "ota.selfcheck_passed" +pattern = 'Passing selfcheck' +severity = "ignore" +milestone = "ota_update_accepted" +led = "GREEN" + +[[rule]] +id = "ota.reset_during_update" +pattern = 'Device was reset during update' +severity = "warning" +title = "Box was switched off during a firmware update" +meaning = "An update was interrupted; the box reports it and retries." +actions = ["Leave the box powered while the LED is yellow or orange."] + +# --------------------------------------------------------------- system + +[[rule]] +id = "sys.out_of_resources" +pattern = 'Failed to create (task for sensor|gather task|main gather task)' +severity = "error" +title = "Firmware ran out of memory" +meaning = "The firmware could not start an internal task (LED red); it restarts itself after 30 s." +actions = ["Power-cycle. If it repeats, save the session log for the firmware team."] +led = "RED" + +[[rule]] +id = "sys.factory_reset" +pattern = 'Factory reset button pressed|Factory resetting device' +severity = "warning" +title = "Factory reset triggered with the Matter button" +meaning = "The box forgets its Matter network and must be paired again with the QR sticker." +actions = ["Re-commission the box in the Matter app."] +led = "WHITE" + +[[rule]] +id = "mic.disabled" +pattern = 'MICROPHONE: Microphone is in shutdown state' +severity = "info" +title = "Microphone is switched off - no noise measurements" +meaning = "The firmware reads the microphone enable line (GPIO3) as 'off', which it treats as disabled on purpose. Noise levels are not recorded." +actions = ["If this box should measure noise: check the microphone enable switch/jumper and its wiring (inside the case)."] + +[[rule]] +id = "gather.empty_reading" +pattern = 'SENSOR_GATHERER: Failed to get line protocol from sensor' +severity = "warning" +min_count = 2 +title = "A sensor returned no data" +meaning = "One of the sensors skipped its reading; the preceding log lines name the sensor." +actions = ["Check the log lines just before this message for the sensor name."] +explained_by = ["mic.disabled", "mic.read_fail", "bme688.read_fail", "as7341.read_fail", "rtc.clock_not_running"] diff --git a/kota_tech/ui/cheatsheet.py b/kota_tech/ui/cheatsheet.py index a713587..c8cc492 100644 --- a/kota_tech/ui/cheatsheet.py +++ b/kota_tech/ui/cheatsheet.py @@ -55,7 +55,8 @@ STEPS = [ "Open the Serial monitor tab, choose the sensorbox port, press " "Connect.", "Press Reset & capture to record a full boot log from the first line.", - "Note the RGB LED colour and compare with the table below.", + "Read the Diagnosis panel on the right, then open Guided troubleshooting " + "and start Quick check: the tool asks what you see and checks the log live.", ] diff --git a/kota_tech/ui/guide_panel.py b/kota_tech/ui/guide_panel.py new file mode 100644 index 0000000..193f30a --- /dev/null +++ b/kota_tech/ui/guide_panel.py @@ -0,0 +1,216 @@ +"""Guided troubleshooting panel: renders a diag.guides.GuideRunner.""" + +from __future__ import annotations + +from PySide6.QtCore import QSize, Qt +from PySide6.QtGui import QBrush, QColor, QIcon, QLinearGradient, QPainter, QPixmap +from PySide6.QtWidgets import ( + QFrame, + QHBoxLayout, + QLabel, + QListWidget, + QListWidgetItem, + QProgressBar, + QPushButton, + QVBoxLayout, + QWidget, +) + +from ..diag.engine import LED, DiagnosticsEngine +from ..diag.guides import GuideRunner, recommended + +END_STYLE = { # end severity -> (border, background) + "ok": ("#2e9e44", "#e3f4e7"), + "info": ("#2e6da4", "#e3edf7"), + "warning": ("#c77c02", "#fdf0d6"), + "error": ("#d9534f", "#f9e0df"), + "critical": ("#b03a2e", "#f6d5d1"), +} + + +def _swatch(key: str, size: int = 22) -> QIcon: + """Round LED-colour icon; CYCLING is drawn as a blue-dark-red gradient.""" + pm = QPixmap(size, size) + pm.fill(QColor(0, 0, 0, 0)) + p = QPainter(pm) + p.setRenderHint(QPainter.RenderHint.Antialiasing) + if key == "CYCLING": + g = QLinearGradient(0, 0, size, 0) + for stop, c in ((0.0, "#2f6fd6"), (0.5, "#444444"), (1.0, "#d64541")): + g.setColorAt(stop, QColor(c)) + p.setBrush(QBrush(g)) + else: + p.setBrush(QColor(LED.get(key, ("", "#888888"))[1])) + p.setPen(QColor("#777777")) + p.drawEllipse(1, 1, size - 2, size - 2) + p.end() + return QIcon(pm) + + +def _esc(s: str) -> str: + return s.replace("&", "&").replace("<", "<").replace(">", ">") + + +class GuidePanel(QWidget): + def __init__(self, runner: GuideRunner, engine: DiagnosticsEngine, parent: QWidget | None = None): + super().__init__(parent) + self.runner, self.engine = runner, engine + self._shown_key: tuple | None = None + + # --- picker (no guide running) + self.picker = QWidget() + pl = QVBoxLayout(self.picker) + pl.setContentsMargins(0, 0, 0, 0) + pl.addWidget(QLabel("Recommended checks for this box (based on the log):")) + self.guide_list = QListWidget() + self.guide_list.itemDoubleClicked.connect(lambda it: self._start(it.data(Qt.ItemDataRole.UserRole))) + pl.addWidget(self.guide_list, 1) + self.start_btn = QPushButton("Start selected check") + self.start_btn.clicked.connect(self._start_selected) + pl.addWidget(self.start_btn) + + # --- running guide + self.card = QFrame() + self.card.setFrameShape(QFrame.Shape.StyledPanel) + cl = QVBoxLayout(self.card) + self.guide_title = QLabel() + self.guide_title.setStyleSheet("color:#666") + self.step_text = QLabel(wordWrap=True) + f = self.step_text.font() + f.setPointSize(f.pointSize() + 2) + self.step_text.setFont(f) + self.step_text.setTextFormat(Qt.TextFormat.RichText) + self.options = QVBoxLayout() + self.wait_bar = QProgressBar() + self.wait_bar.setTextVisible(False) + self.wait_label = QLabel() + self.note = QLabel(wordWrap=True) + self.note.setStyleSheet("color:#b03a2e") + self.continue_btn = QPushButton("Continue") + self.continue_btn.clicked.connect(self._proceed) + self.skip_btn = QPushButton("Skip waiting / it did not work") + self.skip_btn.clicked.connect(self._proceed) + self.end_box = QLabel(wordWrap=True) + self.end_box.setTextFormat(Qt.TextFormat.RichText) + self.end_box.setMargin(10) + for w in (self.guide_title, self.step_text): + cl.addWidget(w) + cl.addLayout(self.options) + for w in (self.wait_label, self.wait_bar, self.note, self.continue_btn, self.skip_btn, self.end_box): + cl.addWidget(w) + cl.addStretch(1) + nav = QHBoxLayout() + self.back_btn = QPushButton("← Back") + self.back_btn.clicked.connect(self._back) + self.done_btn = QPushButton("Back to checks list") + self.done_btn.clicked.connect(self._cancel) + nav.addWidget(self.back_btn) + nav.addStretch(1) + nav.addWidget(self.done_btn) + cl.addLayout(nav) + + lay = QVBoxLayout(self) + lay.setContentsMargins(4, 0, 0, 0) + lay.addWidget(self.picker, 1) + lay.addWidget(self.card, 1) + self.refresh() + + # ------------------------------------------------------------ actions + def _start_selected(self) -> None: + it = self.guide_list.currentItem() or self.guide_list.item(0) + if it: + self._start(it.data(Qt.ItemDataRole.UserRole)) + + def _start(self, guide_id: str) -> None: + self.runner.start(guide_id) + self.refresh() + + def _answer(self, key: str) -> None: + self.runner.answer(key) + self.refresh() + + def _proceed(self) -> None: + self.runner.proceed() + self.refresh() + + def _back(self) -> None: + self.runner.back() + self.refresh() + + def _cancel(self) -> None: + self.runner.cancel() + self.refresh() + + # ------------------------------------------------------------- render + def refresh(self) -> None: + """Called after every interaction and periodically (timeouts, countdown).""" + self.runner.tick() + v = self.runner.view() + running = v.guide is not None + self.picker.setVisible(not running) + self.card.setVisible(running) + if not running: + self._fill_picker() + self._shown_key = None + return + key = (v.guide.id, v.step.id if v.step else None, v.end.id if v.end else None) + if key != self._shown_key: + self._shown_key = key + self._render_step(v) + if v.waiting: + total = v.step.timeout_s + self.wait_bar.setMaximum(int(total)) + self.wait_bar.setValue(int(total - v.remaining_s)) + m, s = divmod(int(v.remaining_s), 60) + self.wait_label.setText(f"Watching the live log... {m}:{s:02d} left") + self.note.setText(v.note) + self.note.setVisible(bool(v.note)) + self.back_btn.setEnabled(v.can_back) + + def _fill_picker(self) -> None: + wanted = [(g.id, g.title, g.summary) for g in recommended(self.runner.guides, self.engine)] + current = [(self.guide_list.item(i).data(Qt.ItemDataRole.UserRole)) for i in range(self.guide_list.count())] + if [w[0] for w in wanted] == current: + return + self.guide_list.clear() + for gid, title, summary in wanted: + it = QListWidgetItem(f"{title}\n {summary}") + it.setData(Qt.ItemDataRole.UserRole, gid) + self.guide_list.addItem(it) + self.guide_list.setCurrentRow(0) + + def _render_step(self, v) -> None: + self.guide_title.setText(v.guide.title) + while self.options.count(): + w = self.options.takeAt(0).widget() + if w: + # Detach now; deleteLater alone leaves it visible until the + # event loop processes the deferred delete. + w.hide() + w.setParent(None) + w.deleteLater() + is_end = v.end is not None + self.step_text.setVisible(not is_end) + self.step_text.setText(_esc(v.text)) + for opt_key, label in v.options: + b = QPushButton(label) + b.setMinimumHeight(34) + if v.step and v.step.type == "led": + b.setIcon(_swatch(opt_key)) + b.setIconSize(QSize(22, 22)) + b.setStyleSheet("QPushButton { text-align:left; padding-left:10px; }") + b.clicked.connect(lambda _=False, k=opt_key: self._answer(k)) + self.options.addWidget(b) + step_type = v.step.type if v.step else None + self.continue_btn.setVisible(step_type == "info") + self.skip_btn.setVisible(step_type == "wait") + self.wait_bar.setVisible(step_type == "wait") + self.wait_label.setVisible(step_type == "wait") + self.end_box.setVisible(is_end) + if is_end: + e = v.end + border, bg = END_STYLE.get(e.severity, END_STYLE["info"]) + acts = "".join(f"
  • {_esc(a)}
    • " for a in e.actions) + self.end_box.setStyleSheet(f"QLabel {{ border:2px solid {border}; background:{bg}; border-radius:6px; }}") + self.end_box.setText(f"

    {_esc(e.title)}

    {_esc(e.text)}

    " + + (f"
      {acts}
    " if acts else "")) diff --git a/kota_tech/ui/main_window.py b/kota_tech/ui/main_window.py index 7b160a2..2107ad2 100644 --- a/kota_tech/ui/main_window.py +++ b/kota_tech/ui/main_window.py @@ -22,13 +22,15 @@ from PySide6.QtWidgets import ( from .. import __version__ from ..core.logfile import read_log_file -from ..core.logline import LineKind, LogLine +from ..core.logline import LineKind, LogLine, host_event from ..core.session import SessionLog from ..diag.engine import DiagnosticsEngine +from ..diag.guides import GuideRunner from ..serialio.manager import SerialManager, State from ..serialio.ports import PortInfo, list_serial_ports from .cheatsheet import cheatsheet_html from .diag_panel import DiagnosticsPanel +from .guide_panel import GuidePanel MAX_LINES = 20000 LEVEL_FILTERS = {"All lines": None, "Warnings + errors": {"W", "E"}, "Errors only": {"E"}} @@ -63,6 +65,7 @@ class SerialTab(QWidget): self._counts = {"E": 0, "W": 0, "boots": 0} self._engine = DiagnosticsEngine() self._diag_dirty = True + self._runner = GuideRunner(self._engine, on_action=self._guide_action, on_log=self._guide_log) # --- controls self.port_combo = QComboBox(minimumWidth=320) @@ -102,9 +105,13 @@ class SerialTab(QWidget): self.view.setStyleSheet("QPlainTextEdit { background:#1e1e1e; color:#d4d4d4; }") self.diag = DiagnosticsPanel() + self.guide = GuidePanel(self._runner, self._engine) + self.side_tabs = QTabWidget() + self.side_tabs.addTab(self.diag, "Diagnosis") + self.side_tabs.addTab(self.guide, "Guided troubleshooting") split = QSplitter(Qt.Orientation.Horizontal) split.addWidget(self.view) - split.addWidget(self.diag) + split.addWidget(self.side_tabs) split.setStretchFactor(0, 3) split.setStretchFactor(1, 2) split.setSizes([700, 480]) @@ -175,6 +182,7 @@ class SerialTab(QWidget): return self._counts = {"E": 0, "W": 0, "boots": 0} self._engine.reset() + self._runner.cancel() self._diag_dirty = True self._session.start(port.mac or port.device) self._manager.connect(port) @@ -206,6 +214,7 @@ class SerialTab(QWidget): def _on_line(self, line: LogLine) -> None: self._session.write(line) self._engine.feed(line) + self._runner.feed(line) self._diag_dirty = True if line.kind == LineKind.BOOT: self._counts["boots"] += 1 @@ -240,6 +249,21 @@ class SerialTab(QWidget): if self._diag_dirty: self._diag_dirty = False self.diag.show_report(self._engine.report()) + self.guide.refresh() # countdowns and timeouts need a steady tick + + # ---- guided troubleshooting hooks ------------------------------------ + def _guide_action(self, action: str) -> bool: + if action == "reset" and self._manager.state == State.CONNECTED: + self._manager.reset_board() + return True + return False + + def _guide_log(self, text: str) -> None: + # Technician answers go into the session log and the log view. + line = host_event(text) + self._session.write(line) + self._append(line) + self._diag_dirty = True def _copy_report(self) -> None: QGuiApplication.clipboard().setText(self._engine.report().to_text()) @@ -252,6 +276,7 @@ class SerialTab(QWidget): lines = read_log_file(Path(path)) self.view.clear() self._engine.reset() + self._runner.cancel() self._counts = {"E": 0, "W": 0, "boots": 0} for line in lines: self._engine.feed(line) diff --git a/pyproject.toml b/pyproject.toml index d006ac0..3fe9dc4 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "kota-technician-tool" -version = "0.2.0" +version = "0.3.0" description = "KOTA sensorbox technician diagnostic tool (demo)" requires-python = ">=3.11,<3.14" dependencies = [ diff --git a/run_macos.command b/run_macos.command index 8afb622..b00e4f0 100755 --- a/run_macos.command +++ b/run_macos.command @@ -3,7 +3,7 @@ cd "$(dirname "$0")" || exit 1 # Keep the virtual environment out of the (Google Drive) tool folder. -export UV_PROJECT_ENVIRONMENT="$HOME/Library/Caches/KotaTechnicianTool/venv-0.2" +export UV_PROJECT_ENVIRONMENT="$HOME/Library/Caches/KotaTechnicianTool/venv-0.3" export PATH="$HOME/.local/bin:$PATH" if ! command -v uv >/dev/null 2>&1; then diff --git a/run_windows.bat b/run_windows.bat index 32d50ee..2466668 100644 --- a/run_windows.bat +++ b/run_windows.bat @@ -3,7 +3,7 @@ setlocal cd /d "%~dp0" rem Keep the virtual environment out of the (Google Drive) tool folder. -set "UV_PROJECT_ENVIRONMENT=%LOCALAPPDATA%\KotaTechnicianTool\venv-0.2" +set "UV_PROJECT_ENVIRONMENT=%LOCALAPPDATA%\KotaTechnicianTool\venv-0.3" set "PATH=%USERPROFILE%\.local\bin;%PATH%" where uv >nul 2>nul diff --git a/tests/test_guides.py b/tests/test_guides.py new file mode 100644 index 0000000..3515285 --- /dev/null +++ b/tests/test_guides.py @@ -0,0 +1,231 @@ +"""Guided troubleshooting: runner + engine with simulated technician +answers, simulated board output and a fake clock.""" + +from pathlib import Path + +import pytest + +from kota_tech.core.logfile import read_log_file +from kota_tech.core.logline import parse_line +from kota_tech.diag.engine import DiagnosticsEngine, Severity +from kota_tech.diag.guides import LED_ANSWERS, GuideRunner, load_guides, recommended + +FIX = Path(__file__).parent / "fixtures" +BOOT = ["ESP-ROM:esp32s3-20210327", "rst:0x1 (POWERON),boot:0x8 (SPI_FAST_FLASH_BOOT)", + "I (1299) app_init: Project name: kota-sensorboard", + "I (1317) app_init: ELF file SHA256: 45fa9d5b9..."] + + +class Clock: + def __init__(self): + self.t = 1000.0 + + def __call__(self): + return self.t + + +@pytest.fixture +def rig(): + engine, clock, actions, log = DiagnosticsEngine(), Clock(), [], [] + runner = GuideRunner(engine, on_action=lambda a: actions.append(a) or True, + on_log=log.append, clock=clock) + + def board(*lines): + for ln in lines: + parsed = parse_line(ln) + engine.feed(parsed) + runner.feed(parsed) + + return engine, runner, clock, actions, board, log + + +def _bench(engine): + for ln in read_log_file(FIX / "live_boot_A4CB8FC946F8_fw1.0.txt"): + engine.feed(ln) + + +def test_all_guides_load_and_validate(): + guides = load_guides() + assert "quick" in guides and len(guides) >= 8 + led = guides["quick"].steps["led"] + assert set(led.route) == set(LED_ANSWERS) # every colour has a route + + +def test_recommendations_follow_findings(rig): + engine, *_ = rig + _bench(engine) + ids = [g.id for g in recommended(load_guides(), engine)] + assert ids[0] == "quick" + assert ids.index("network") < ids.index("clock") # root order preserved + assert "mic" in ids + + +def test_purple_uncommissioned_box_skips_to_pairing_and_follows_it_live(rig): + engine, runner, clock, _, board, log = rig + _bench(engine) # log: not commissioned, LED purple + runner.start("quick") + runner.answer("PURPLE") + # "Was it paired before?" is skipped: the log already shows it is not. + assert runner.step.id == "pair_intro" + runner.proceed() + assert runner.view().waiting and runner.step.id == "pair_start" + board("I (90000) MAIN: Commissioning session started") + assert runner.step.id == "pair_wifi" + board("I (95000) MAIN: Commissioning complete") + assert runner.step.id == "pair_time" + board("I (99000) SNTP: Time synchronized: Sat Sep 26 16:00:00 2026") + assert runner.step.id == "pair_upload" + board("I (120000) INFLUX: HTTP request performed, status code: 204") + assert runner.end.id == "online" and runner.end.severity == "ok" + assert any("Paired" in t or "paired" in t for t in engine.technician) + assert "matter.not_commissioned" not in {rc.finding.rule_id for rc in engine.report().roots} + assert any(l.startswith("technician:") for l in log) + + +def test_pairing_timeout_asks_what_the_app_shows(rig): + engine, runner, clock, _, board, _ = rig + _bench(engine) + runner.start("network") + runner.proceed() # pair_intro -> pair_start + clock.t += 301 + runner.tick() + assert runner.step.id == "not_found" + runner.answer("1") + assert runner.end.id == "ble_not_found" + f = engine.findings["tech.network.ble_not_found"] + assert f.severity == Severity.ERROR and f.active + + +def test_led_mismatch_is_recorded(rig): + engine, runner, *_ = rig + _bench(engine) # log implies PURPLE + runner.start("quick") + runner.answer("GREEN") + f = engine.findings["tech.led_mismatch"] + assert "Green" in f.title and "Purple" in f.title + assert runner.step.id == "heartbeat" + + +def test_led_match_records_nothing(rig): + engine, runner, *_ = rig + _bench(engine) + runner.start("quick") + runner.answer("PURPLE") + assert "tech.led_mismatch" not in engine.findings + + +def test_blue_reseat_fixed_after_power_cycle(rig): + engine, runner, clock, _, board, _ = rig + board(*BOOT, "E (3511) MAIN: Failed to initialize RTC: ESP_ERR_TIMEOUT") + runner.start("quick") + runner.answer("BLUE") + runner.proceed() + runner.proceed() # -> verify (technician power-cycles) + assert runner.step.id == "verify" + board(*BOOT, "I (14800) temperature_sensor: Range [20°C ~ 100°C], error < 2°C") + assert runner.end.id == "i2c_fixed" + + +def test_blue_still_failing_then_module(rig): + engine, runner, clock, _, board, _ = rig + board(*BOOT, "E (3511) MAIN: Failed to initialize RTC: ESP_ERR_TIMEOUT") + runner.start("rtc_i2c") + runner.proceed() + runner.proceed() + board(*BOOT, "E (3511) MAIN: Failed to initialize RTC: ESP_ERR_TIMEOUT") + assert runner.step.id == "damaged" + runner.answer("1") + assert runner.end.id == "rtc_module" + + +def test_white_skips_portal_question_on_v1_firmware(rig): + engine, runner, clock, _, board, _ = rig + board(*BOOT) # known v1.0: no setup portal + runner.start("white") + runner.answer("1") # nobody held the button + assert runner.step.id == "sd_reseat" + + +def test_white_asks_portal_question_on_unknown_firmware(rig): + engine, runner, clock, _, board, _ = rig + board("ESP-ROM:esp32s3-20210327", "I (1317) app_init: ELF file SHA256: 0123456789...") + runner.start("white") + runner.answer("1") + assert runner.step.id == "portal" + + +def test_red_routes_to_failing_sensor_and_names_it(rig): + engine, runner, clock, _, board, _ = rig + board(*BOOT, "E (14000) MAIN: Failed to initialize SEN66: ESP_ERR_TIMEOUT") + runner.start("sensors") + assert runner.step.id == "reseat" + assert "SEN66" in runner.view().text + runner.proceed() + board(*BOOT, "E (14000) MAIN: Failed to initialize SEN66: ESP_ERR_TIMEOUT") + assert runner.end.id == "sensor_replace" + + +def test_reboot_loop_resets_board_then_routes_by_cause(rig): + engine, runner, clock, actions, board, _ = rig + runner.start("reboot_loop") + assert actions == ["reset"] + board(*BOOT, "E (1519) SD_CARD: Failed to initialize the card (ESP_ERR_TIMEOUT). x") + clock.t += 46 + runner.tick() + assert runner.guide.id == "white" + + +def test_reset_action_failure_is_shown(rig): + engine = DiagnosticsEngine() + runner = GuideRunner(engine, on_action=lambda a: False, clock=Clock()) + runner.start("reboot_loop") + assert "connect" in runner.view().note.lower() + + +def test_mic_disabled_switch_on_verified(rig): + engine, runner, clock, actions, board, _ = rig + _bench(engine) + runner.start("mic") + assert runner.step.id == "switch" + runner.answer("0") # set it to ON + assert actions == ["reset"] + board(*BOOT, "I (20000) MICROPHONE: Read 300000 bytes in 4936 ms") + assert runner.end.id == "mic_on" + + +def test_mic_clap_test_detects_dead_mic(rig): + engine, runner, clock, _, board, _ = rig + board(*BOOT, *["I (20036) MICROPHONE: Sum SQ: 0.000000, RMS pressure: 0.000000, " + "Normalized: 0.000000, dB peak: -inf"] * 2) + runner.start("mic") + assert runner.step.id == "clap" + board("I (30036) MICROPHONE: Sum SQ: 0.000000, RMS pressure: 0.000000, Normalized: 0.000000, dB peak: -inf") + clock.t += 46 + runner.tick() + assert runner.end.id == "mic_faulty" + + +def test_mic_clap_test_passes_on_sound(rig): + engine, runner, clock, _, board, _ = rig + runner.start("mic") + board("I (30036) MICROPHONE: Sum SQ: 12.5, RMS pressure: 0.02, Normalized: 0.1, dB peak: 71.3") + assert runner.end.id == "mic_ok" + + +def test_back_never_reenters_a_wait(rig): + engine, runner, clock, actions, board, _ = rig + runner.start("sensors") # route -> capture (wait, resets board) + assert runner.step.id == "capture" and actions == ["reset"] + clock.t += 46 + runner.tick() # -> which_again -> end:red_unclear + runner.back() + assert actions == ["reset"] # no second reset + + +def test_skip_wait_and_report_contains_technician_checks(rig): + engine, runner, clock, _, board, _ = rig + runner.start("update") + runner.proceed() # technician skips the wait + assert runner.end.id == "update_slow" + text = engine.report().to_text() + assert "Technician checks:" in text and "Update is taking very long" in text