agent: builder model: opus max_turns: 80 budget_usd: 20 —
Score: a defect that blocks yaml (#928) step 2b’s parse(input, limits) (y2b-keys-directives-limits.md runs after this brief); found by the architect probing y2b. It changes crates/: the gate of .claude/agents/builder.md applies in full, plus target/fast/nikaia test --both-settings --project tests/compiler (a change to tools/check_*.nika or tools/emit_*.nika), and the package gate below.
Read docs/builder-facts.md. Run the probe on the unfixed binary first and read its lowered file (~/.cache/nikaia/run/<name>-*/target/nikaia/gen/), then compare with the keep(lim) variant’s lowering: the difference is where the checker records an argument taken by an ordinary call’s owned parameter. Decide in the checker (CLAUDE.md, docs/architect.md: a missing or extra & is the checker’s, not the emitter’s); the emitter only writes what the checker decided.
The architect probing yaml’s next brief (y2b step 2, parse(input, limits) handing a Limits to the entry rule, ADR-yaml-1 D8; develop 6064835c, 2026-10-31). Blocks y2b step 2.
An entry rule takes values after its input (ADR-grammar-1 D2, Part II 10; tests/compiler/tests/grammar_an_entry_takes_values_after_its_input.nika passes only literals and locals). A parameter of the calling function handed there is lowered as a lent &Limits, and the entry’s parse_doc(lim: Limits) wants it owned:
pub struct Limits {
pub depth: i64,
}
grammar G {
rule WS = "" -> { }
entry rule doc(lim: Limits) -> i64 = "x" if(lim.depth > 0) eof -> { lim.depth }
}
fn parse(input: String, lim: Limits) -> i64 {
return G::doc(input, lim) catch {
return -1
}
}
fn main() {
println(f"{parse("x", Limits { depth: 3 })}")
println(f"{parse("x", Limits { depth: 0 })}")
}Today: rustc Mismatched types at G::doc(input, lim) (“Consider dereferencing the borrow”); the lowered fn parse(input: &str, lim: &Limits) calls G::parse_doc(lim). Wanted: 3 then -1. The same with a local (let lim = Limits { depth: n } in parse) prints 3 / -1 today, and an ordinary function fn keep(l: Limits) -> Vec[Limits] { return [l] } called as keep(lim) makes parse’s lim owned (fn parse(input: &str, lim: Limits)): only the grammar entry’s value parameters are not seen as a position that takes its argument. Over ref Bytes input the same (parse_bytes(&*input, GOverBytes::parse_doc(lim))).
A defect: the entry is “an ordinary call” (ADR-296 D24, the comment in check_core_method.nika:852), so its value parameters take their arguments as an ordinary call’s do.
keep), or, where the caller cannot give it up, the checker’s existing rules for an ordinary call apply (copy for a Copy type, a refusal with the code an ordinary call gets). No new NK code. An i64 or other copy value is unchanged.tests/compiler/tests/grammar_an_entry_takes_a_parameter_of_its_caller.nika + .stdout: the probe above, plus the same with ref Bytes input (Bytes("x".bytes().collect())); it fails on the unfixed binary.Checker: check_core_grammar_call (crates/nikaia-std/src/tools/check_core_pilot.nika:33), reached from check_core_method.nika:854 (grammar_entry, check_decls.nika:261); how an ordinary call marks an argument taken: an_owned_parameter (check_fields.nika:260), a_lent_parameter (check_fields.nika:223), the_compiler_writes_the_reference (check_references.nika:124). Emitter: emit_core_grammar_entry (emit_core_leaves.nika:467), called from emit_core_calls.nika:622. Lowered twins in crates/nikaia-std/src/tools/lowered/.
The probe prints 3 / -1 over String and over ref Bytes; the new test passes and fails on the unfixed binary (say so under Tests:); grammar_an_entry_takes_values_after_its_input and every grammar_ test green in NIKAIA_CACHE_LIMIT=2G target/fast/nikaia test --both-settings --project tests/compiler > out.txt 2>&1; the package gate below green; committed and pushed with Fixes #1041. Files you may change: the files under Locations with their lowered twins (regenerate them as docs/builder-facts.md says), the predicate they call where the decision lives (name it in Body:), the new test. Name under Changelog: what the change decided.
docs/builder-facts.md first. develop in the main checkout; git status at start: other agents’ uncommitted files are not yours, never touch or stage them.git add <files> only; commit after each step; git push origin develop fast-forward, no rebase (rejected: report Pushed: rejected, go on committing).cargo fmt, cargo clippy --all-targets -- -D warnings, scripts/pre-push-check.sh, and the gate of .claude/agents/builder.md (#852).CHANGELOG.md, badges; no new NK code. New tests in Nikaia only; never the full suite. No foreground sleep, no polling; scripts in files.std or the toolchain lacks stops the work: no code around it unless an ADR or Part I-III refuses it (name it). Else Result: blocked, Found: gap + probe, Needs: owner decision (CLAUDE.md, A missing form stops the work).NIKAIA_CACHE_LIMIT=2G; at most two clones with target/ in the machine; delete your own clone’s target/ and target/release/nikaia-scratch at the end; report GB freed.Pushed: line names the pushed sha. A report without a Pushed: line, or with a placeholder left in (TC, DISK), is not done and cuts the batch (k3a1 2026-10-29: Result: done, nothing committed).NIKAIA_CACHE_LIMIT=2G target/fast/nikaia test --project packages/yaml green, and cargo test --profile fast -p nikaia --test it -- fmt::every_nika_file (it formats every .nika under packages/). For a change only under packages/yaml/ this is the gate the line above asks for; a change under crates/ runs the gate of .claude/agents/builder.md (#852) as well. target/fast/nikaia is built by the session hook; if it is missing, cargo build --profile fast -p nikaia once.Changelog: none, unless the brief changes crates/.Files not to touch: anything outside packages/yaml/ and the brief’s own report, unless the brief names it; never docs/briefs/batch.txt or a brief of another lane.
max_turns: commit and push every finished step, then report Result: partial with what is left under Needs:. Uncommitted work at the end is lost work (y4 ran out at 110)./home/user/Nikaia/docs/briefs/yaml/y17-1041-entry-takes-a-parameter.md.report.md)Fields of docs/architect.md, Briefs and reports: Result: done|noop|partial|blocked (the bare word alone on that line: Result: done, never a summary after it, which cuts the batch, b869a 2026-10-27; Owner: is a question for the owner or none, never a role), Files, Commit, Body (optional, one paragraph for the commit message), Fixes, Pushed, Tests, Gate (green|red), Deviation, Found, Needs, Changelog, Owner, Disk freed, and for a move Rs2nika: (the kept N of M lines of rs2nika --score, then the three costliest hand edits; none for a task that moves no Rust, none (redesign) for a brief with Shape: redesign and no Convert: line). none where nothing, and then the bare word: Deviation: none (a note) cuts the batch (batch.nika compares exactly); a note goes into the commit message. Found: is only for a defect outside your change (it cuts the batch); a process event such as another session resetting or rewriting your files is no Found:, it goes under Needs: (m3a 2026-10-28); a converter draft that came out wrong is no Found:, it is one of the costliest edits under Rs2nika:, which the converter lane reads (e12-4b 2026-10-27); how you solved your own step goes into the commit message. Deviation: is only a step of the brief built otherwise than written or not built (a choice the brief left to you, such as keep what X needs and say so, is no deviation: it goes into the commit message; nor is building two steps in one commit when every step is built, e12-3a 2026-10-27, nor a step another commit on develop already built, shown by your test failing with that commit’s change reverted, b889 2026-10-27: name the commit in Body:, nor a test’s expected .stdout/.stderr taken from what the program really prints where the brief’s sketch of it was short or wrong, b934 2026-10-29: say so in Body:, nor a lowering that follows the ADR governing it where the brief’s expected lowering contradicts that ADR, b933 2026-10-29: name the ADR in Body:, nor a lowering other than the brief’s where rustc cannot take the brief’s, b1029 2026-10-31: say why in Body:, nor re-keying an allow-list entry (KNOWN) whose hash changed for the same program and the same reason, b-fixforward-sweep2 2026-10-28: say so in Body:, nor an existing test’s expected .stdout/.stderr updated because your change rightly changes the message it prints, b1012b 2026-10-31: name the test in Body:); how you verified (e.g. a test not run against the unfixed compiler) goes under Tests:. A noop says why under Tests: (what was probed), not under Deviation:. Final answer, one line: done <sha>, report <path> (or BLOCKED: ... / PUSH REJECTED ...).
Attribution: Co-Authored-By: Claude Opus 5.5 noreply@anthropic.com Claude-Session: https://claude.ai/code/session_01UVxJDveRM5qKZKyCqq6Y24