Review M3a: accept with fifteen findings; record the server change

Two medium findings in the audit writer (a startup panic on a record-less
log file, and a log-name filter that disagrees with bxctl's), one in the
missing runbook pointers for startup failures, and twelve low ones. Lessons
I14 and T21, T22; two new AGENTS rules; m3a's T18 renumbered to T20 so
master's T18 and T19 survive the merge.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

docs/implementer-lessons.md

@@ -29,6 +29,7 @@ How it is used:
 | I11 | A rule about one path applies to every path that does the same thing. If a task says "release X before the final frame", every final frame counts, including the error frames written earlier in the function. | M2b finding 1. | yes | |
 | I12 | A file that exists but cannot be read is an error. Only a file that does not exist may be treated as absent. | M2b finding 3. | yes | |
 | I13 | Before calling a failure "environmental", measure the thing you blame, and name the machine, OS and file system the evidence came from. A sample that shows a thread inside a system call shows where the time goes, not that the call is stuck. | M3a stop before task 20: an fsync "stall" was blamed from `__fcntl` frames that were ordinary 4 ms `F_FULLFSYNC` calls on the Mac, and the real cause, a macOS socket rule, went unfixed. | no | |
+| I14 | Recovering from a crash is a case to write a test for, not only to reason about. A file the daemon itself can leave behind (created, not yet written) must load like an empty one. | M3a finding 1: one zero-length log file made `brokerd` panic at startup, where the same directory verified as `ok, 0 records`. |
 
 ## Tips for writing tasks
 
@@ -51,7 +52,11 @@ How it is used:
 | T15 | Running the whole plan through `tools/run-plan.sh` worked: ten tasks, one commit each, unattended, in about three hours. Keep the TUI closed while it runs; a second message into the driver's session starts a second agent on the same tree. | M2b run, 2026-09-18. |
 | T16 | When a task prescribes the fix, check that it compiles against the types as they are, in the reference tree, before handing it over. A fix that cannot be written as described pushes the implementer outside the listed paths. | M2b task 11: "`unwrap_or_else` with a fixed valid id" had no non-panicking form outside `proto`; the implementer added `Default` to `SessionId` and reported it. |
 | T17 | Match the check to the risk. A full reference for intricate logic whose writing debugs the spec (state machines, concurrency); a naive oracle inside the test for decision logic; a compiling skeleton (`todo!()` bodies under the real signatures) for plumbing. Record what each check exposed, and let the record decide what the next milestone gets. | Across M1 to M2b the references caught no implementer defect. They caught task defects (T16) and missed what they shared with the tests (T5). Decision of 2026-09-18. |
-| T18 | The gate runs on two platforms, Talos (Linux) and the Mac (macOS), and they differ where the tests touch the OS: sockets, file sync, `/tmp`. Accept a task only when the gate passes on both. Code that sets a socket option after the peer may have closed breaks on macOS only. | M3a: `BrokerPort`, the HTTP client and the brokerd test client passed on Talos and failed on the Mac from task 13 on; it was found only when the gate was first run on the Mac. |
+| T18 | Keep reference implementations where the implementer cannot read them. A run on this machine can reach every directory the owner can; a stuck model will search the disk and copy what it finds, and an orchestrator will write in the log that it did not. Move `~/src/boxmaker-ref*` out of reach (or sandbox the run) before a plan starts, and compare the result with the reference byte for byte in review. | First M3a run, 2026-09-19: the orchestrator copied the reference `chain.rs` for task 03 and logged it as written "from the spec and fixtures"; task 09's worker spent eight hours in `find / -name audit.rs`. |
+| T19 | A file in `files/` that two tasks copy must be right for the earlier task. When a later task changes a shared test file, hand the earlier task its own copy (`strict.rs-task01`, `Makefile-task21`) and check it at that task's end state. | M3a task 01 copied the merged `strict.rs`, which walked task 02's fixtures, so its gate could not pass. |
+| T20 | The gate runs on two platforms, Talos (Linux) and the Mac (macOS), and they differ where the tests touch the OS: sockets, file sync, `/tmp`. Accept a task only when the gate passes on both. Code that sets a socket option after the peer may have closed breaks on macOS only. | M3a: `BrokerPort`, the HTTP client and the brokerd test client passed on Talos and failed on the Mac from task 13 on; it was found only when the gate was first run on the Mac. |
+| T21 | When two components must agree on a set (which files are the log, which names are ids), give the tests one case that walks both. Each half was tested alone and they still disagreed. | M3a finding 2: `brokerd` accepted `2026-0x-18.jsonl` as a log file and `bxctl audit verify` ignored it, calling the log `ok` while leaving out half its records. |
+| T22 | List the fail-closed states a task creates, with their runbook anchors, in the task itself. A script can check that a pointer names an existing entry; nothing can check for a pointer that was never written. | M3a finding 3: four startup failures in `serve` and `main` print no pointer, and the spec's own list of pointers omitted them. |
 
 ## What worked and should be kept