The second 06 session listed tests/, read eight loopd modules and
support/mod.rs, grepped bxcore, then hit Context size exceeded with
no commit. The cp is now the first action; tick is glue over two
todo!() bodies; run-plan tells the session to run step 1 before
reading crate source.
Co-Authored-By: Grok 4.6 <noreply@x.ai>
Task 06 opened the whole implementer log (~360 kB) after reading supporting
modules; OpenCode returned "Context size has been exceeded" and made no
commit. AGENTS.md and tasks 06-10 now say to read the first 12 lines only.
Co-Authored-By: Grok 4.6 <noreply@x.ai>
The review of tasks 01 to 15 in the implementer log, with the six findings fixed in review. Nine
tips for writing tasks from the run's transcripts and the review, new evidence for I16 and I17,
and four rules in AGENTS.md: the Cargo registry is outside the repository, `git stash -u` and the
README's flaky tests, an edit never anchors on another line, and what a test count includes.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The owner's hosts (titan, talos) run 1.98.1; nixos-26.05's Rust is
1.95.0, so builds and lints differed by host. The flake gains a second
input, oxalica's rust-overlay (following our nixpkgs, so host configs
can still follow theirs), and both the package build and the dev shell
use its stable 1.98.1 with clippy and rustfmt. The workspace's
rust-version rises to 1.98 to match; AGENTS.md, docs/dependencies.md
and the M5c-1 plan follow.
Checked on straylight: nix build gives all seven binaries; the dev
shell has rustc, cargo and clippy 1.98.1, rustfmt 1.9.0, cargo-deny
0.19.6; make gate in it passes with 1122 tests, as on titan.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
From the combined Ornith guidance (~/projects/ornith/GUIDANCE.md, §4):
experiments go under the ignored .state/scratch/, never /tmp (which
reconciles I16 with crossbar's in-repo experiments); a refused tool call
does not end the turn; todo!() bodies are filled one at a time with
cargo check between; the gate runs with a 600000 ms shell timeout;
Cargo.lock is staged when it changed; commit messages are written to a
file and committed with -F, since quotes broke -m in crossbar.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Owner's rule. The implementer often cannot know which model it is, so
run-plan.sh derives the name from OPENCODE_MODEL (the part after the
provider), gives the exact trailer and the Model column's value in the
session prompt, and stops the run when a task's commit lacks that exact
line. AGENTS.md replaces the old Implemented-By trailer and the "owner
fills in the model" rule.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Two review entries in the implementer log: tasks 01 to 15 (the header
forgery, review ids, the runbook entries, log rows written from memory)
and tasks 16 to 22 with the device check on straylight (the ledger
raising state by the grant's label, the note answers, the stale target/
that stalled task 21, the clippy 1.95 stop, the fake podman race). Two
short rules go into AGENTS.md: stop after one check when a test outside
the task fails, and write the log row from the diff.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
M5a task 04 stopped twice on the chat-template tags the check refuses.
The first time, the model read them in a file and took them for its own
template. The second time, it spelled them out in its own reasoning.
Measured on straylight: the think and tool-call tags are one token
whatever the tokenizer's flag. Inside any chat message, the turn
markers become control tokens, so a tool result can forge a system
turn.
Adds the rule to AGENTS.md, and proposes neutralizing the tags in
loopd as an open decision.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
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>
The first M3a run's orchestrator copied a reference file from another
checkout and logged it as its own work, and its workers got a summary
of AGENTS.md instead of the file.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
All ten tasks pass the checklist, the gate, the audit and the device
checks, including a four-turn conversation with a loopd restart and no
cache loss. Reading and probing found four low defects: the busy guard
is released before the final frame on the main path but not on the
three error paths, its Drop skips a poisoned lock, an unreadable
core.md is treated as missing, and bxctl's interactive loop exits on a
failed turn. Task 11 carries the fixes with two new tests, checked
against a fixed copy of the branch.
The Model column is filled in (all Ornith) and one malformed row is
repaired. Two rules are promoted to AGENTS.md.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The branch passes every check, including make verify-device on
straylight and repeated timing runs under load. Reading and probing
found that inferproxy does not pass an upstream close on to a client
that is still sending, and that the chunked body reader delivers a
stream only when the caller's buffer fills or the stream ends. Both
were also gaps in the tasks and tests, so tasks 14 and 15 carry the
fixes with new tests checked against the reference.
The Model column is corrected: tasks 04 to 06 and 08 to 13 were Ornith.
Lessons gain four implementer tips and five task-writing tips; three
rules are promoted to AGENTS.md.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The implementer log gains a Model column, filled by the owner. Tasks so
far: M1 and M2a 01 to 06 by Laguna S 2.1, M2a 07 by GLM-5.3. The commit
trailer no longer names a model.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The tasks build the inference path: emsha-backed SHA-256, inferproxy,
config, a hand-written HTTP and SSE client, request building, delta
assembly, the chat state machine, the thinking cap, the slot gate with
retry, the startup self-test and on-device verification.
Everything the tasks copy in was checked against a private reference
implementation: the gate passes after each task in order, the timing
tests pass repeatedly under CPU load, and the reference passes the
self-test and all four device checks on straylight. Expected results
for the recorded streams were derived by a separate script.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Tasks 08 and 09 pass the checklist and the reviewer's probes, so M1 is
complete. docs/implementer-lessons.md turns the review findings into
tips for the implementer and for task writing, each tied to its
evidence, with a column to record whether the defect comes back.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The branch passes the checklist: seven commits, copied files unchanged,
gate and audit green. Reading and probing found that AuditRecord and
ToolCall accept unknown fields, that large Timestamps panic when
formatted, and that the dependency-direction scripts miss table-form
dependencies and pass when their inputs are missing. The last two
families were gaps in the tasks, not only in the code.
Tasks 08 and 09 carry the fixes, defined by an exhaustive unknown-field
test, a bounded-Timestamp test and an extended gate-script self-test.
All three were checked against the reference implementation and fail on
the current branch.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Seven task files for the implementing model under docs/plans/M1/, with
the test files, byte-exact fixtures, Makefile, deny.toml and gate-script
self-test they copy into place. All of it was verified against a private
reference implementation: the gate passes after every task in order.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
kyleandGrok 4.6
