agent: builder model: opus max_turns: 90 budget_usd: 22 —
text(d:P+), a name below a repeat)Score: a defect (rustc errors on programs the checker passed), found by this lane (y14); nothing in packages/yaml needs it, it touches only the grammar checker and emitter. Runs before y2b-keys-directives-limits.md.
Read docs/builder-facts.md. Read bdbe8a7a’s and 03d43063’s commit messages first (git show --stat <sha>): they say how a bound s:text(p) binds its inner names ((a) @ __nikaia_s_from ... (c) @ __nikaia_s_to, nikaia_std::grammar::covered) and how a guard reads them (__nikaia_covered). The unbound form is to go the same way. y14’s debrief: its first fix also let the unbound form through to a guard, and only a probe after the build showed rustc refusing it; so run the five probe rows below on the unfixed binary first, then after each build.
y14 (#1013 step 4, 03d43063, 2026-10-31), building the yaml package (#928). The checker’s bindings_of (crates/nikaia-std/src/tools/check_grammar.nika:158) hands the action every name bound anywhere inside a pattern; the emitter binds a name only where emit_pattern’s grammar_nested rule lets it through (Seq, Group, Bind pass, everything else is nested; emit_pattern.nika:14) and, inside text(..), only for a bound s:text(p) (emit_is_a_binding_text, emit_pattern.nika:373; bdbe8a7a). Where the two disagree the program passes the checker and rustc says Cannot find value d.
Part II 10 (docs/specification/20-nikaia-advance.md:731), the text(p) row: “a name inside p is bound as it is without the text(..) around it”. That holds for an unbound text(..) too: a defect, not a decision.
rule WS = "" -> { } and rule Ch -> i64 = x:any if(x >= '0' && x <= '9') -> { 1 }, called with catch { println("error") return })| # | entry rule | input | today | wanted |
|---|---|---|---|---|
| a | plain -> String = text(d:Ch+) ";" -> { f"{d.len()}" } |
"12;" |
rustc: d not found |
prints 2 |
| b | plain -> String = s:text(text(d:Ch+) "-") ";" -> { f"{s} {d.len()}" } |
"12-;" |
rustc: d not found |
prints 12- 2 |
| c | plain -> String = text(d:Ch+) if(d.len() > 1) ";" -> { "ok" } |
"12;" |
NK1117 at the guard’s d (y14 kept it inside on purpose because the emitter did not bind it) |
prints ok |
| d | plain -> String = (d:Ch ",")* ";" -> { f"{d}" } |
"1,2,;" |
rustc: d not found |
NK1117 at the action’s d (a name below a repeat is not the action’s: Part II 10’s p* row yields a list of what p yields, nothing binds inside) |
| e | bound s:text(d:Ch+) if(d.len() > 1) ";" -> { s } (the y14 test) |
"12;" / "1;" |
12 / error |
unchanged |
text(p) at the alternative’s level (rows a, b, c): written as the bound form with a hidden label (__nikaia_text_N, the lowering’s own names start with __nikaia_), so emit_text_bindings, emit_text_edge, emit_texts_a_guard_reads (emit_pattern.nika:386) and the action’s prelude (emit_grammar.nika:103) treat it as they treat s:text(p). The checker’s grammar_values (check_grammar.nika:320, helper grammar_a_text_call:43) then hands those names on to a later guard for the unbound form as well (row c). Over Bytes the covered text keeps its UTF-8 check (covered_bytes), as the bound form.bindings_of hands the action only the names the emitter binds (below a repeat, a counted repeat, a choice, or a built-in’s argument other than text(..) at the alternative’s level: not bound), so row d is NK1117 at the use, with its span. The code exists; no new NK code. Untouched: what a fold(p, init, step)’s step reads of p (its own scope, emit_fold), and a bound repeat xs:(d:Ch ",")* (the label is the action’s, d is not). Every tests/compiler/tests/grammar_* test stays green; one that reads a name below a repeat in its action and passes today is a counter-example: stop and report it.tests/compiler/tests/: grammar_an_unbound_text_binds_its_inner_names.nika (rows a, b, c; .stdout), grammar_a_name_below_a_repeat_is_not_the_actions.nika (row d; .stderr). Part II 10’s text(p) row: say it holds bound or not; the x:p row: a name below a repeat or a choice is not in the action’s scope.check_grammar.nika: bindings_of:158, grammar_values:320, grammar_a_text_call:43. emit_pattern.nika: emit_pattern:10 (grammar_nested), emit_is_a_binding_text:373, emit_texts_a_guard_reads:386, emit_text_nested:442, emit_text_edge:452. emit_grammar.nika: emit_text_bindings:103. Lowered twins in crates/nikaia-std/src/tools/lowered/. y14’s test tests/compiler/tests/grammar_a_guard_reads_a_name_bound_inside_text.nika and bdbe8a7a’s grammar_text_binds_its_inner_parts.nika must stay green.
Not needed by yaml (it reads no such name); built in the yaml lane because it touches only the grammar checker and emitter.
Rows a-e print what the table wants; both new tests pass and fail on the unfixed binary (say so under Tests:); NIKAIA_CACHE_LIMIT=2G target/fast/nikaia test --both-settings --project tests/compiler > out.txt 2>&1 green with every grammar_ test in it; the package gate below green; committed and pushed with Fixes #1039, both steps in one commit or two. Files you may change: the files under Locations with their lowered twins (crates/nikaia-std/src/tools/lowered/*.rs, regenerate them as docs/builder-facts.md says), crates/nikaia-std/src/grammar.rs if the covered-text helper needs it, the Part II 10 rows, the two new tests with their expected output. Name under Changelog: what the change decided. Stop and report if an existing test reads a name the new rule refuses.
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/y16-1039-unbound-text-names.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