docs: the watchdog-lockout and EEPROM-wrap gotchas

A sticky WDRF diverts every reset past the activation window (deliberate, so
an app can reboot instantly, at the cost of a possible lockout); an EEPROM
address past E2END wraps onto low EEPROM (the host bounds it, not the loader).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

CMakeLists.txt

@@ -233,11 +233,11 @@ if(PROJECT_IS_TOP_LEVEL)
 	# The size matrix: every configuration axis that could move the image
 	# size — the serial backend (different code), the USART instance
 	# (different registers), the clock (different constants), and the baud
-	# through the two shapes its bit timing takes — each combination must
+	# through the shapes its bit timing takes — each combination must still
-	# still fit the chip's slot budget. Pins are size-neutral (port and bit
+	# fit the chip's slot budget. Pins are size-neutral (port and bit are
-	# are immediate operands) and the timeout is a constant, so neither adds
+	# immediate operands) and the timeout is a constant, so neither adds an
-	# an axis. The stock build is one point of this matrix and already has
+	# axis. The stock build is one point of this matrix and already has its
-	# its test.
+	# test.
 	function(pureboot_size_variant name)
 		pureboot_add_loader(${name} ${ARGN})
 		add_test(NAME ${name}.size
@@ -245,42 +245,86 @@ if(PROJECT_IS_TOP_LEVEL)
 		                 -DLIMIT=${PUREBOOT_LIMIT} -P ${CMAKE_CURRENT_SOURCE_DIR}/test/check_size.cmake)
 	endfunction()
 
+	# One point of the exhaustive matrix, named from its resolved parameters
+	# so the enumeration cannot collide with itself. Unreachable rates drop
+	# out here rather than aborting the configure.
+	function(pureboot_matrix_point hz baud link)
+		if(link STREQUAL "software")
+			pureboot_baud_feasible(${hz} ${baud} 1 _ok)
+			set(_args SERIAL software)
+		else()
+			pureboot_baud_feasible(${hz} ${baud} 0 _ok)
+			set(_args USART ${link})
+		endif()
+		if(_ok)
+			pureboot_size_variant(pbm_${hz}_${baud}_${link} CLOCK ${hz} BAUD ${baud} ${_args})
+		endif()
+	endfunction()
+
 	# Clock points: the shipped-fuse floor (CKDIV8), the calibrated RC, and
 	# the crystal the stock build assumes (the tiny13's ladder is its own RC
 	# menu — it has no crystal option).
 	if(LIBAVR_MCU MATCHES "^attiny13")
 		set(_matrix_clocks 1200000 4800000 9600000)
+		set(_full_clocks 128000 600000 1200000 4800000 9600000)
 	else()
 		set(_matrix_clocks 1000000 8000000 16000000)
+		set(_full_clocks 128000 1000000 1843200 2000000 3686400 4000000 7372800 8000000
+		                 11059200 12000000 14745600 16000000 18432000 20000000)
+	endif()
+
+	# The exhaustive cross product: every clock a deployment plausibly runs
+	# — the internal oscillators, the shipped CKDIV8 floor, the plain
+	# crystals and the UART crystals — against every rate, against every
+	# backend. Beyond the ladder the list carries the slow rates a
+	# sub-megahertz oscillator is left with, which no ladder rate reaches
+	# (16000 Bd is the only rate the 128 kHz oscillator holds exactly); at
+	# the fast clocks those same rates also select the software UART's
+	# 16-bit _delay_loop_2 bit spin (two words more setup at each of its five
+	# sites), the largest image the space produces and a shape the ladder
+	# default — always the *fastest* rate a clock reaches — never picks.
+	#
+	# Bounded to one chip per size-bearing class: flash addressing (the
+	# word-addressed 1284), hand-over shape (the patched vector on the tinies
+	# and m48s), page size, and USART inventory. Everything else in the image
+	# is chip-independent code, so a further chip buys builds and no
+	# coverage; every chip outside the set carries the compact matrix.
+	get_property(_full_bauds GLOBAL PROPERTY PUREBOOT_BAUD_LADDER)
+	list(APPEND _full_bauds 16000 4800 2400 1200)
+	set(_matrix_spot attiny13a attiny85 atmega48pa atmega8a atmega168pa
+	                 atmega328p atmega164a atmega644a atmega1284p)
+	if(DEFINED ENV{PUREBOOT_FULL_MATRIX} AND LIBAVR_MCU IN_LIST _matrix_spot)
+		foreach(_matrix_hz IN LISTS _full_clocks)
+			foreach(_matrix_baud IN LISTS _full_bauds)
+				pureboot_matrix_point(${_matrix_hz} ${_matrix_baud} software)
+				if(PUREBOOT_HAS_USART)
+					pureboot_matrix_point(${_matrix_hz} ${_matrix_baud} 0)
+				endif()
+				if(PUREBOOT_HAS_USART1)
+					pureboot_matrix_point(${_matrix_hz} ${_matrix_baud} 1)
+				endif()
+			endforeach()
+		endforeach()
+	else()
+		foreach(_matrix_hz IN LISTS _matrix_clocks)
+			math(EXPR _matrix_khz "${_matrix_hz} / 1000")
+			if(PUREBOOT_HAS_USART OR NOT _matrix_hz EQUAL _pb_stock_hz)
+				pureboot_size_variant(pureboot_sw_${_matrix_khz}k CLOCK ${_matrix_hz} SERIAL software)
+			endif()
+			if(PUREBOOT_HAS_USART AND NOT _matrix_hz EQUAL _pb_stock_hz)
+				pureboot_size_variant(pureboot_hw_${_matrix_khz}k CLOCK ${_matrix_hz} SERIAL hardware)
+			endif()
+			if(PUREBOOT_HAS_USART1 AND NOT _matrix_hz EQUAL _pb_stock_hz)
+				pureboot_size_variant(pureboot_usart1_${_matrix_khz}k CLOCK ${_matrix_hz} USART 1)
+			endif()
+		endforeach()
+		list(GET _matrix_clocks -1 _matrix_top_hz)
+		pureboot_size_variant(pureboot_sw_wide CLOCK ${_matrix_top_hz} BAUD 9600 SERIAL software)
 	endif()
-	foreach(_matrix_hz IN LISTS _matrix_clocks)
-		math(EXPR _matrix_khz "${_matrix_hz} / 1000")
-		if(PUREBOOT_HAS_USART OR NOT _matrix_hz EQUAL _pb_stock_hz)
-			pureboot_size_variant(pureboot_sw_${_matrix_khz}k CLOCK ${_matrix_hz} SERIAL software)
-		endif()
-		if(PUREBOOT_HAS_USART AND NOT _matrix_hz EQUAL _pb_stock_hz)
-			pureboot_size_variant(pureboot_hw_${_matrix_khz}k CLOCK ${_matrix_hz} SERIAL hardware)
-		endif()
-		if(PUREBOOT_HAS_USART1 AND NOT _matrix_hz EQUAL _pb_stock_hz)
-			pureboot_size_variant(pureboot_usart1_${_matrix_khz}k CLOCK ${_matrix_hz} USART 1)
-		endif()
-	endforeach()
 	if(PUREBOOT_HAS_USART1)
 		pureboot_size_variant(pureboot_usart1 USART 1)
 	endif()
 
-	# The baud axis, whose one size-bearing shape the ladder never picks: a
-	# software UART spins out each bit with _delay_loop_1 while the count
-	# fits a byte and with the 16-bit _delay_loop_2 beyond it, two words more
-	# setup at every one of its five sites — the largest image the
-	# configuration space produces. The ladder default takes the *fastest*
-	# rate a clock reaches, which always lands in the byte, so the wide form
-	# needs the slowest ladder rate against the fastest clock to appear. The
-	# hardware USART has no such shape: its baud is a divisor constant, and
-	# the ladder's U2X solutions are already its larger form.
-	list(GET _matrix_clocks -1 _matrix_top_hz)
-	pureboot_size_variant(pureboot_sw_wide CLOCK ${_matrix_top_hz} BAUD 9600 SERIAL software)
-
 	# One configured deployment end to end — a real board's shape rather
 	# than the stock assumption: the ATmega328P on its shipped 1 MHz fuses,
 	# the software UART on hand-picked pins (TX = PB1, RX = PB5), the ladder

pureboot/CMakeLists.txt

@@ -146,36 +146,51 @@ set(PUREBOOT_HAS_USART ${_pb_has_usart} PARENT_SCOPE)
 set(PUREBOOT_HAS_USART1 ${_pb_has_usart1} PARENT_SCOPE)
 set(PUREBOOT_SIM_MCU ${_pb_sim_mcu} PARENT_SCOPE)
 
-# The fastest standard rate the clock reaches within 2.5 %, by the same
+# The rates a default may pick, fastest first.
-# best-of-U2X-and-plain divisor search libavr's solve_baud runs, so a default
+set_property(GLOBAL PROPERTY PUREBOOT_BAUD_LADDER 115200 57600 38400 19200 9600)
+
+# Whether <baud> is reachable from <clock> within 2.5 %, by the same
+# best-of-U2X-and-plain divisor search libavr's solve_baud runs, so a build
 # never trips the compile-time error it is checked against. A software build
 # also needs the polled receiver's 100-cycles-a-bit floor: at low clocks the
 # U2X divisor reaches rates the bit-banged sampler cannot.
-function(pureboot_default_baud clock software outvar)
+function(pureboot_baud_feasible clock baud software outvar)
-	foreach(baud 115200 57600 38400 19200 9600)
+	set(${outvar} 0 PARENT_SCOPE)
-		math(EXPR _cycles "${clock} / ${baud}")
+	math(EXPR _cycles "${clock} / ${baud}")
-		if(software AND _cycles LESS 100)
+	if(software AND _cycles LESS 100)
+		return()
+	endif()
+	foreach(divisor 8 16)
+		math(EXPR _step "${divisor} * ${baud}")
+		math(EXPR _n "(${clock} + ${_step} / 2) / ${_step}")
+		if(_n LESS 1 OR _n GREATER 4096)
 			continue()
 		endif()
-		foreach(divisor 8 16)
+		math(EXPR _actual "${clock} / (${divisor} * ${_n})")
-			math(EXPR _step "${divisor} * ${baud}")
+		math(EXPR _delta "${_actual} - ${baud}")
-			math(EXPR _n "(${clock} + ${_step} / 2) / ${_step}")
+		if(_delta LESS 0)
-			if(_n LESS 1 OR _n GREATER 4096)
+			math(EXPR _delta "-(${_delta})")
-				continue()
+		endif()
-			endif()
+		math(EXPR _error_bp "${_delta} * 10000 / ${baud}")
-			math(EXPR _actual "${clock} / (${divisor} * ${_n})")
+		if(_error_bp LESS_EQUAL 250)
-			math(EXPR _delta "${_actual} - ${baud}")
+			set(${outvar} 1 PARENT_SCOPE)
-			if(_delta LESS 0)
+			return()
-				math(EXPR _delta "-(${_delta})")
+		endif()
-			endif()
-			math(EXPR _error_bp "${_delta} * 10000 / ${baud}")
-			if(_error_bp LESS_EQUAL 250)
-				set(${outvar} ${baud} PARENT_SCOPE)
-				return()
-			endif()
-		endforeach()
 	endforeach()
-	message(FATAL_ERROR "pureboot: no standard baud rate fits a ${clock} Hz clock within 2.5 %")
+endfunction()
+
+# The fastest ladder rate the clock reaches.
+function(pureboot_default_baud clock software outvar)
+	get_property(_ladder GLOBAL PROPERTY PUREBOOT_BAUD_LADDER)
+	foreach(baud ${_ladder})
+		pureboot_baud_feasible(${clock} ${baud} ${software} _ok)
+		if(_ok)
+			set(${outvar} ${baud} PARENT_SCOPE)
+			return()
+		endif()
+	endforeach()
+	message(FATAL_ERROR "pureboot: no standard baud rate fits a ${clock} Hz clock within 2.5 % "
+	        "— pass BAUD <rate> to deploy a non-standard one")
 endfunction()
 
 # pureboot_add_loader(<name> [CLOCK <hz>] [BAUD <bd>]

pureboot/README.md

@@ -98,8 +98,15 @@ speak to the build. This exact deployment runs the full protocol suite in CI
 
 Reset enters the loader (BOOTRST on the boot-sectioned megas, the patched
 reset vector elsewhere) — except a watchdog reset, which hands straight to the
-application, since the application owns its watchdog and must clear WDRF
+application with no activation window, since the application owns its watchdog.
-itself.
+This is deliberate: it lets an application reboot itself instantly rather than
+sit through the window. The application must clear WDRF itself (libavr's
+`watchdog::disable()` does). **Gotcha:** WDRF is sticky (cleared only by
+software, not by a later reset), so an application that watchdog-resets and
+never clears it diverts *every* subsequent reset — external ones included —
+past the window too, and the loader becomes reachable only through an external
+programmer until the flag is cleared. A serial recovery path therefore assumes
+the application clears WDRF on its own reset path.
 
 The host then knocks `p` then `b`, each awaited byte under a fresh activation
 window; any other byte is discarded and awaited again, so line noise can delay
@@ -123,19 +130,26 @@ On chips whose flash exceeds 64 KiB (the 1284s — info-block flag bit 1) the
 addresses (the 644s' 64 KiB is exactly the 16-bit byte space). EEPROM
 addresses and all counts are bytes.
 
+The loader trusts the host to keep addresses in range: it does not bound them
+against the info block. **Gotcha:** a `w` (or `r`) that runs past `E2END` wraps
+— EEAR is only as wide as the array, so an address past the end truncates onto
+low EEPROM and the write silently overwrites it. Keeping writes within the
+advertised sizes is the host's job (the shipped tool does); the flash budget
+is better spent on features than on re-checking a bound the host already holds.
+
 | Cmd | Arguments | Reply |
 |---|---|---|
 | `b` | — | the 12-byte info block |
 | `R` | addr16, n8 | n flash bytes (n = 0 means 256) |
-| `W` | addr16, then one page of data | — (completion = next prompt) |
+| `W` | addr16 (any address in the page), then one page of data | — (completion = next prompt) |
 | `r` | addr16, n8 | n EEPROM bytes (n = 0 means 256) |
 | `w` | addr16, n8, then n data bytes | `+` per byte, sent once its write has begun |
 | `F` | — | 4 bytes: low fuse, lock, extended fuse, high fuse |
 | `J` | word address (16-bit) | `+`, then execution continues there |
 | other | — | ignored; the loop re-prompts (send a junk byte, await `+`, to resync) |
 
-`W` streams exactly one page-aligned SPM page (size from the info block) into
+`W` streams exactly one SPM page (size from the info block) into the buffer,
-the buffer, then erases and programs — except pages inside the 512-byte slot
+then erases and programs — except pages inside the 512-byte slot
 the loader is *running* in, which are drained and left alone, so a broken host
 cannot brick the running copy and a staged copy may rewrite the resident.
 
@@ -309,6 +323,13 @@ Per chip preset, `ctest` runs:
   the configuration space produces, and a shape the ladder default (always the
   *fastest* rate a clock reaches) never picks. Pins are immediate operands and
   the timeout is a constant: neither is an axis;
+- `pbm_*.size` — under `--full`, the exhaustive cross product replacing that
+  compact matrix: every plausible oscillator (the internal ones, the CKDIV8
+  floor, the plain and the UART crystals) × every rate reachable from it ×
+  every backend, unreachable combinations dropping out rather than aborting
+  the configure. Bounded to one chip per size-bearing class — flash
+  addressing, hand-over shape, page size, USART inventory — since everything
+  else in the image is chip-independent code;
 - `pureboot.pi` — the position-independence lint: no absolute `jmp`/`call`, the
   info block within the image's first 256 bytes;
 - `pureboot.planner` — the host tool's pure logic: programming orders and their

pureboot/pureboot.cpp

@@ -67,18 +67,29 @@ constexpr std::uint8_t timeout_seconds = PUREBOOT_TIMEOUT;
 
 // The loader's one identity number. The protocol carries none of its own —
 // a version implies it, and the host tool holds that map (README.md).
-constexpr std::uint8_t version = 3;
+constexpr std::uint8_t version = 4;
 
 // The 'b' reply, byte for byte (layout: README.md). Flash-resident because
 // no crt copies a .data image — and flash_table's storage carries the word
 // alignment 'b' needs to halve the address on the large chips.
+// One wire byte per line: this is the reply's layout, not a list.
+// clang-format off
 inline constexpr avr::flash_table<std::array<std::uint8_t, 12>{
-    'P', 'B', version, avr::hw::db.signature[0], avr::hw::db.signature[1], avr::hw::db.signature[2],
+    'P',
-    static_cast<std::uint8_t>(page), // 0 means 256
+    'B',
-    wire_base & 0xff, wire_base >> 8, avr::hw::db.mem.eeprom_size & 0xff, avr::hw::db.mem.eeprom_size >> 8,
+    version,
-    static_cast<std::uint8_t>((boot_section ? 0 : 1) | (word_flash ? 2 : 0)), // patch-vector, word-addressed
+    avr::hw::db.signature[0],
+    avr::hw::db.signature[1],
+    avr::hw::db.signature[2],
+    static_cast<std::uint8_t>(page),                                           // 0 means 256
+    wire_base & 0xff,
+    wire_base >> 8,
+    avr::hw::db.mem.eeprom_size & 0xff,
+    avr::hw::db.mem.eeprom_size >> 8,
+    static_cast<std::uint8_t>((boot_section ? 0 : 1) | (word_flash ? 2 : 0)),  // patch-vector, word-addressed
 }>
     info_data;
+// clang-format on
 
 // The serial link, per the build's PUREBOOT_USART / PUREBOOT_SOFT_SERIAL,
 // defaulting to the chip's USART0 where it has one. The software receiver is
@@ -309,18 +320,19 @@ void store_eeprom(std::uint16_t address, std::uint8_t count)
 // that write clears the condition and the host's read-back rewrites the page.
 void program_flash(std::uint16_t wire_address, std::uint8_t slot_high)
 {
-	// One induction either way: a byte-addressed wire address walks the page
+	// The address names a page, so its in-page bits are dropped and the walk
-	// itself (aligned, so the offset bits wrap to zero), while a word one
+	// starts at the page base — one induction either way: a byte-addressed
-	// becomes a byte cursor once. The slot index is the wire address's high
+	// wire address walks the page itself (the offset bits wrap back to zero),
-	// byte — on byte-addressed chips the byte address's, with the low bit
+	// while a word one becomes a byte cursor once. The slot index is the wire
-	// dropped, since a slot is two of those.
+	// address's high byte — on byte-addressed chips the byte address's, with
+	// the low bit dropped, since a slot is two of those.
 	spm::flash_address_t address;
 	std::uint8_t page_high;
 	if constexpr (word_flash) {
 		// A page is aligned, so it never crosses 64 KiB: RAMPZ is a per-page
 		// constant and the 16-bit Z's low byte is the whole in-page offset.
 		const std::uint8_t rampz = static_cast<std::uint8_t>(wire_address >> 15);
-		const std::uint16_t z0 = static_cast<std::uint16_t>(wire_address << 1);
+		const std::uint16_t z0 = static_cast<std::uint16_t>(wire_address << 1) & ~static_cast<std::uint16_t>(page - 1);
 		std::uint16_t z = z0;
 		do {
 			std::uint8_t low = link::rx();
@@ -331,7 +343,7 @@ void program_flash(std::uint16_t wire_address, std::uint8_t slot_high)
 		address = (static_cast<spm::flash_address_t>(rampz) << 16) | z0;
 		page_high = static_cast<std::uint8_t>(wire_address >> 8);
 	} else {
-		address = static_cast<spm::flash_address_t>(wire_address);
+		address = static_cast<spm::flash_address_t>(wire_address & ~static_cast<std::uint16_t>(page - 1));
 		do {
 			std::uint8_t low = link::rx();
 			std::uint8_t high = link::rx();

pureboot/pureboot.py

@@ -24,13 +24,13 @@ else:
     import termios
 
 PROMPT = b"+"
-VERSION = 2  # this tool's own version — free to drift from a loader's
+VERSION = 3  # this tool's own version — free to drift from a loader's
 # The loader versions this tool speaks. A pureboot version implies its wire
 # protocol, which carries no number of its own, so this window is where that
 # map lives: every version so far speaks the same protocol, and one that
 # changes it becomes the new floor here.
 OLDEST_LOADER = 1
-NEWEST_LOADER = 3
+NEWEST_LOADER = 4
 SLOT = 512  # the loader slot, on every chip
 RETRIES = 3  # rewrites of a page that reads back wrong, before the run stops
 
@@ -364,26 +364,37 @@ class Loader:
         self.info = None
 
     def connect(self, wait):
-        """Knock until the window answers, then read the info block. Also
+        """Knock until the info block comes back. The block is what proves the
-        converges into a live session: the knock bytes are ignored there and
+        loader is listening — a prompt byte alone does not, since one left over
-        the drain absorbs whatever they produced."""
+        from a previous session can still be in the pipeline while the port
-        self.port.flush_input()
+        opening resets the device into a fresh activation window, where a
+        command without its knock is discarded. Each attempt is therefore the
+        whole handshake, retried until it produces the block or the window
+        closes. Also converges into a live session: the knock bytes are ignored
+        there and the drain absorbs whatever they produced."""
         deadline = time.monotonic() + wait
         knocks = 0
         while True:
+            self.port.flush_input()
             self.port.write(b"pb")
             knocks += 1
             if PROMPT in self.port.read_available(0.4):
-                break
+                while self.port.read_available(0.3):
+                    pass
+                self.port.write(b"b")
+                try:
+                    block = self.port.read_exact(12, 2.0)
+                except Error:
+                    block = b""
+                # A version the tool cannot speak is the loader's own answer,
+                # not a failed knock: Info reports it rather than retrying.
+                if block[0:2] == b"PB":
+                    self.info = Info(block)
+                    self._expect_prompt()
+                    verbose(f"loader answered knock {knocks}; info block read")
+                    return self.info
             if time.monotonic() > deadline:
                 raise Error("no answer — reset the device within its activation window")
-        while self.port.read_available(0.3):
-            pass
-        self.port.write(b"b")
-        self.info = Info(self.port.read_exact(12, 2.0))
-        self._expect_prompt()
-        verbose(f"loader answered knock {knocks}; info block read")
-        return self.info
 
     def _expect_prompt(self, timeout=2.0):
         byte = self.port.read_exact(1, timeout)

test/pbtest.py

@@ -105,6 +105,17 @@ def main():
             # was never told about is a loader it would refuse to speak to.
             if live.version != pb.NEWEST_LOADER:
                 fail(f"loader reports pureboot {live.version}, the tool's newest is {pb.NEWEST_LOADER}")
+
+            # A W addressed inside a page rather than at its base must still
+            # consume exactly one page and prompt. The loader's own slot is
+            # the target — it is drained and never programmed — and the
+            # payload is erased-state bytes, so the probe can disturb neither
+            # the image nor the page buffer it leaves behind.
+            wire = wire_base + 1
+            port.write(bytes((ord("W"), wire & 0xFF, wire >> 8)) + b"\xff" * page)
+            if port.read_exact(1, 5.0) != pb.PROMPT:
+                fail("unaligned W did not return to the prompt")
+
             loader.run_application()
             banner = port.read_exact(3, 5.0)
             if banner != b"APP":

test/test_planner.py

@@ -280,6 +280,68 @@ def main():
     if device.writes != pb.RETRIES + 1:
         fail(f"unrepairable page took {device.writes} writes, expected {pb.RETRIES + 1}")
 
+    # The knock handshake against a device that is not listening yet — the
+    # state a port open leaves behind: it resets the chip into a fresh
+    # activation window while the previous session's prompt is still in
+    # flight, so the first knock is lost and a prompt arrives anyway.
+    class FakePort:
+        """A loader in its activation window, plus `lost` leading writes the
+        reset swallows and one stale prompt still on the wire."""
+
+        def __init__(self, info_raw, lost=0, stale=b"", active=False):
+            self.info_raw = info_raw
+            self.lost = lost
+            self.inflight = bytearray(stale)
+            self.rx = bytearray()
+            self.active = active
+            self.last = None
+
+        def flush_input(self):
+            self.rx.clear()
+
+        def write(self, data):
+            if self.lost:
+                self.lost -= 1
+                return
+            for byte in bytes(data):
+                if not self.active:
+                    self.active = self.last == ord("p") and byte == ord("b")
+                    self.last = byte
+                    if self.active:
+                        self.rx += pb.PROMPT
+                elif byte == ord("b"):
+                    self.rx += self.info_raw + pb.PROMPT
+                else:
+                    self.rx += pb.PROMPT
+
+        def read_available(self, wait):
+            self.rx = self.inflight + self.rx  # the stale prompt lands late
+            self.inflight.clear()
+            out, self.rx = bytes(self.rx), bytearray()
+            return out
+
+        def read_exact(self, count, timeout):
+            if len(self.rx) < count:
+                raise pb.Error(f"timeout: got {len(self.rx)} of {count} bytes")
+            out, self.rx = bytes(self.rx[:count]), self.rx[count:]
+            return out
+
+    raw = info_of(pb, 0x7E00, 128, False, 0x8000).raw
+    for what, port in (
+        ("clean window", FakePort(raw)),
+        ("stale prompt over a lost knock", FakePort(raw, lost=1, stale=pb.PROMPT)),
+        ("live session", FakePort(raw, active=True)),
+    ):
+        info = pb.Loader(port).connect(5)
+        if info.raw != raw:
+            fail(f"connect ({what}) returned {info.raw.hex()}")
+
+    # A device that never answers still says so, and a version the tool cannot
+    # speak is reported as such rather than retried into a timeout.
+    expect_error("dead device", lambda: pb.Loader(FakePort(raw, lost=99)).connect(0), "no answer")
+    old = bytes(raw[:2]) + bytes((pb.NEWEST_LOADER + 1,)) + bytes(raw[3:])
+    expect_error("unspeakable version", lambda: pb.Loader(FakePort(old)).connect(5), "needs a newer tool")
+
     print("test_planner: all planner and policy checks pass")
 
 

tools/check.sh

@@ -2,12 +2,14 @@
 # The port's gate: every chip's generated workflow — build, size matrix, and
 # the simulator-driven protocol suites. --full adds the reflect-spot builds
 # (libavr's rule: reflect compiles are bounded to its spot set, never the
-# full matrix). LIBAVR_ROOT must point at the libavr checkout.
+# full matrix) and swaps the compact size matrix for the exhaustive
+# clock × baud × backend cross product. LIBAVR_ROOT must point at the libavr
+# checkout.
 set -e
 cd "$(dirname "$0")/.."
 
 full=0
-[[ "$1" == "--full" ]] && { full=1; shift; }
+[[ "$1" == "--full" ]] && { full=1; shift; export PUREBOOT_FULL_MATRIX=1; }
 
 CHIPS=(attiny13 attiny13a attiny25 attiny45 attiny85
        atmega8 atmega8a atmega16 atmega16a atmega32 atmega32a