refactor patches and bump to 1.17.2

zephcore/adapters/radio/LR1110Radio.cpp

@@ -78,6 +78,21 @@ bool LR1110Radio::hwIsReceiving()
 	return lr11xx_is_receiving(_dev);
 }
 
+void LR1110Radio::hwResetAgc()
+{
+	lr11xx_reset_agc(_dev);
+}
+
+void LR1110Radio::hwRecalibrate()
+{
+	lr11xx_recalibrate(_dev);
+}
+
+int16_t LR1110Radio::hwGetChipTempC()
+{
+	return lr11xx_get_chip_temp_c(_dev);
+}
+
 void LR1110Radio::hwSetRxBoost(bool enable)
 {
 	lr11xx_set_rx_boost(_dev, enable);

zephcore/adapters/radio/LR1110Radio.h

@@ -34,6 +34,9 @@ protected:
 	int16_t hwGetCurrentRSSI() override;
 	bool hwIsReceiving() override;
 	void hwSetRxBoost(bool enable) override;
+	void hwResetAgc() override;
+	void hwRecalibrate() override;
+	int16_t hwGetChipTempC() override;
 	uint32_t hwWakeupTimeUs() override;
 	int hwCadProbe(int8_t level) override;
 	void hwCadSetPeakOffset(int8_t offset) override;

zephcore/adapters/radio/LR2021Radio.cpp

@@ -167,6 +167,23 @@ uint8_t LR2021Radio::hwCadPeakMax()
 	return lr20xx_cad_peak_max();
 }
 
+void LR2021Radio::hwResetAgc()
+{
+	lr20xx_reset_agc(_dev);
+}
+
+void LR2021Radio::hwRecalibrate()
+{
+	/* Front-end calibration included: this is the temperature-drift path, and
+	 * image/FE cal is the part a temperature swing actually invalidates. */
+	lr20xx_recalibrate(_dev);
+}
+
+int16_t LR2021Radio::hwGetChipTempC()
+{
+	return lr20xx_get_chip_temp_c(_dev);
+}
+
 uint32_t LR2021Radio::hwWakeupTimeUs()
 {
 	/* Per-device, because the TCXO term dominates and is board-specific:

zephcore/adapters/radio/LR2021Radio.h

@@ -52,6 +52,9 @@ protected:
 	uint8_t hwCadPeakMin() override;
 	uint8_t hwCadPeakMax() override;
 	uint32_t hwWakeupTimeUs() override;
+	void hwResetAgc() override;
+	void hwRecalibrate() override;
+	int16_t hwGetChipTempC() override;
 };
 
 } /* namespace mesh */

zephcore/adapters/radio/LoRaRadioBase.cpp

@@ -60,6 +60,8 @@ LoRaRadioBase::LoRaRadioBase(const struct device *lora_dev, MainBoard &board,
 	  _rx_duty_cycle_enabled(IS_ENABLED(CONFIG_ZEPHCORE_LORA_RX_DUTY_CYCLE)),
 	  _rx_boost_enabled(true),
 	  _dc_last_rx_us(0), _dc_last_sleep_us(0),
+	  _agc_rx_count_shadow(0), _agc_last_activity_ms(0),
+	  _agc_last_cal_temp_c(INT16_MIN),
 	  _config_cached(false),
 	  _has_radio_override(false),
 	  _override_freq(0), _override_bw(0),
@@ -1125,6 +1127,102 @@ bool LoRaRadioBase::isReceiving()
 	return isChannelActive();
 }
 
+/* ── Receiver hygiene ─────────────────────────────────────────────────
+ *
+ * Two independent faults, two independent triggers, neither on the packet path.
+ *
+ * 1. STUCK AGC.  Semtech's remedy is a warm sleep plus recalibration; it is not
+ *    in the datasheets, so it is not up for removal on datasheet reasoning.
+ *    What IS a design choice is when to fire it, and the honest answer is that
+ *    a periodic reset gets it backwards: a timer fires most often on a busy
+ *    channel, which is exactly where a received packet has just PROVED the AGC
+ *    is working, and it fires no more often on a silent one, where a
+ *    desensitised receiver is invisible and nothing else will reveal it.
+ *
+ *    So trigger on silence instead.  If nothing has been heard for
+ *    AGC_IDLE_RESET_MS the receiver is either genuinely idle — in which case
+ *    the reset costs nothing, there is no traffic to miss — or it is deaf, in
+ *    which case this is the only thing that will recover it.  Self-targeting in
+ *    both directions: a busy node essentially never resets, and the resets a
+ *    quiet node does perform are free.  Arduino MeshCore's periodic
+ *    `agc_reset_interval` addressed the same fault and shipped defaulted to 0
+ *    (off), which is a fair summary of how well a plain timer serves it.
+ *
+ *    Deliberately NOT reset here: the noise floor.  The previous periodic
+ *    implementation (removed in fe6e585) zeroed it on every fire, forcing a
+ *    fresh seed and a full EMA warmup each time — that, not the AGC work, is
+ *    what made it a net loss.  Arduino zeroes it too; we do not.
+ *
+ * 2. CALIBRATION DRIFT.  Image/front-end and PLL/AAF calibration are valid for
+ *    a temperature range, not forever: "Image calibration is necessary if there
+ *    is a frequency change > 10MHz, or a temperature change > 10 C", and the
+ *    LR2021 additionally advises redoing PLL and AAF beyond +/-20 C.  A node
+ *    that boots on a hot afternoon and runs into a cold night crosses both.
+ *    Nothing does this automatically: the LR2021's temperature-compensation
+ *    block (DS 6.12) only corrects crystal drift from TX self-heating, and it
+ *    refuses to run at all when a TCXO is fitted.
+ *
+ *    AGC_RECAL_TEMP_DELTA_C is deliberately tighter than either datasheet
+ *    figure — cheap insurance, and the reading is a junction temperature that
+ *    lags ambient. */
+#define AGC_IDLE_RESET_MS        60000U
+#define AGC_RECAL_TEMP_DELTA_C   5
+
+void LoRaRadioBase::agcMaintenance()
+{
+	/* Never mid-transmit: both operations sleep the chip. */
+	if (atomic_get(&_tx_active)) {
+		return;
+	}
+
+	uint32_t now = (uint32_t)k_uptime_get_32();
+
+	/* Any demodulation activity counts as proof of life, errored frames
+	 * included — a CRC failure still means RF reached the demodulator, which
+	 * is precisely what a stuck AGC would prevent.  Counting only good
+	 * packets would fire resets on a node that is merely out of range. */
+	uint32_t rx_total = (uint32_t)atomic_get(&_packets_recv) +
+			    (uint32_t)atomic_get(&_packets_recv_errors);
+
+	if (rx_total != _agc_rx_count_shadow || _agc_last_activity_ms == 0) {
+		_agc_rx_count_shadow = rx_total;
+		_agc_last_activity_ms = now ? now : 1;
+	} else if ((now - _agc_last_activity_ms) >= AGC_IDLE_RESET_MS) {
+		LOG_INF("agc: %u ms without RX activity — resetting AGC",
+			(unsigned)(now - _agc_last_activity_ms));
+		hwResetAgc();
+		/* hwResetAgc() leaves the chip out of RX by contract, so this is
+		 * a genuine re-entry and re-arms the duty cycle if one is set. */
+		startReceive();
+		_agc_last_activity_ms = now ? now : 1;
+	}
+
+	/* Temperature drift.  Sampled every pass because the read is one cheap
+	 * command; the expensive recalibration is gated on the delta. */
+	int16_t temp_c = hwGetChipTempC();
+
+	if (temp_c == INT16_MIN) {
+		return;   /* backend cannot measure — drift handling disabled */
+	}
+	if (_agc_last_cal_temp_c == INT16_MIN) {
+		_agc_last_cal_temp_c = temp_c;   /* first reading is the baseline */
+		return;
+	}
+
+	int delta = (int)temp_c - (int)_agc_last_cal_temp_c;
+
+	if (delta < 0) {
+		delta = -delta;
+	}
+	if (delta >= AGC_RECAL_TEMP_DELTA_C) {
+		LOG_INF("agc: chip temp moved %d C (%d -> %d) — recalibrating",
+			delta, (int)_agc_last_cal_temp_c, (int)temp_c);
+		hwRecalibrate();
+		startReceive();
+		_agc_last_cal_temp_c = temp_c;
+	}
+}
+
 void LoRaRadioBase::recoverRxState()
 {
 	/* Called by the Dispatcher on CAD timeout when isReceiving() has been

zephcore/adapters/radio/LoRaRadioBase.h

@@ -121,6 +121,9 @@ public:
 	void setCadParams(bool auto_enabled, int8_t offset,
 			  uint16_t probe_interval_s, uint8_t busycap_pct) override;
 	void cadMaintenance() override;
+	/** Deaf-aware AGC unstick + temperature-drift recalibration.
+	 *  Called from Dispatcher::maintenanceLoop(); never on the packet path. */
+	void agcMaintenance() override;
 	uint32_t msUntilNextMaintenance() override;
 	int8_t getCadOffset() const override { return _cad_offset; }
 
@@ -175,6 +178,26 @@ protected:
 	virtual uint8_t hwCadPeakMin() { return 0; }
 	virtual uint8_t hwCadPeakMax() { return 0; }
 
+	/* ── Receiver hygiene — see LoRaRadioBase::agcMaintenance() ────── */
+
+	/** Unstick a jammed AGC: warm sleep to drop the analog front end, then
+	 *  recalibrate on the way back up.  Semtech's stated remedy; the
+	 *  datasheets do not describe it, so do not "simplify" it away on
+	 *  datasheet grounds alone.  Must leave the driver out of RX so the
+	 *  caller's startReceive() performs a real re-entry rather than hitting
+	 *  an idempotent fast path.  Default: unsupported, no-op. */
+	virtual void hwResetAgc() {}
+
+	/** Redo the frequency-dependent calibrations (image / front end, and
+	 *  PLL+AAF where the part separates them) at the current operating
+	 *  frequency.  Called on temperature drift, never on the packet path.
+	 *  Same RX-state contract as hwResetAgc(). Default: unsupported. */
+	virtual void hwRecalibrate() {}
+
+	/** Chip junction temperature in whole degrees C, or INT16_MIN when the
+	 *  backend cannot measure it (which disables drift recalibration). */
+	virtual int16_t hwGetChipTempC() { return INT16_MIN; }
+
 	/** Radio deaf time per duty-cycle wake transition (context restore +
 	 *  PLL lock + TCXO startup where fitted), in microseconds.  Counts
 	 *  against the duty-cycle preamble-catch budget: per SX126x DS rev 2.2
@@ -298,8 +321,16 @@ protected:
 	 * changes once at INF instead of on every RX restart.  0/0 = never
 	 * computed; UINT32_MAX rx = continuous-RX fallback active. */
 	uint32_t _dc_last_rx_us;
+
 	uint32_t _dc_last_sleep_us;
 
+	/* agcMaintenance() bookkeeping.  RX activity is inferred by sampling the
+	 * existing packet counters rather than timestamping in the RX callback,
+	 * so nothing is added to the ISR path. */
+	uint32_t _agc_rx_count_shadow;
+	uint32_t _agc_last_activity_ms;
+	int16_t  _agc_last_cal_temp_c;
+
 	/* Config cache — skip redundant hwConfigure() */
 	struct lora_modem_config _last_cfg;
 	bool _config_cached;

zephcore/adapters/radio/SX126xRadio.cpp

@@ -75,6 +75,27 @@ bool SX126xRadio::hwIsReceiving()
 	return sx126x_is_receiving(_dev);
 }
 
+void SX126xRadio::hwResetAgc()
+{
+	/* Leaves the chip in STANDBY and the driver state at IDLE, so the
+	 * caller's startReceive() performs a real re-entry. */
+	sx126x_reset_agc(_dev);
+}
+
+void SX126xRadio::hwRecalibrate()
+{
+	/* Calibrate(ALL) on this part already includes image rejection and
+	 * sx126x_reset_agc() re-issues CalibrateImage for the operating
+	 * frequency, so the drift path needs nothing extra. */
+	sx126x_reset_agc(_dev);
+}
+
+/* No hwGetChipTempC(): the SX126x exposes no junction-temperature readout —
+ * no command in the datasheet, and RadioLib has no getTemperature() for it
+ * either.  Drift recalibration is therefore inactive on this family, which
+ * costs little: unlike the LR parts, its datasheet gives no temperature
+ * threshold for image calibration in the first place. */
+
 void SX126xRadio::hwSetRxBoost(bool enable)
 {
 	sx126x_set_rx_boost(_dev, enable);

zephcore/adapters/radio/SX126xRadio.h

@@ -29,6 +29,8 @@ protected:
 	int16_t hwGetCurrentRSSI() override;
 	bool hwIsReceiving() override;
 	void hwSetRxBoost(bool enable) override;
+	void hwResetAgc() override;
+	void hwRecalibrate() override;
 	bool hwIsChipBusy() override;
 	uint32_t hwWakeupTimeUs() override;
 	int hwCadProbe(int8_t level) override;