agent: builder model: opus max_turns: 70 budget_usd: 12 —
hex_digit (Part II 10.8) is “Undefined rule”Score: S=3 (a wrong refusal of a specified built-in; found by the yaml lane, which wrote around it), O=0.3 M, C=2 M, area bugs. Cheap and certain.
grammar Hex {
rule WS = "" -> { }
entry rule one -> String = "x" h:hex_digit eof -> { f"{h}" }
}
fn main() throws {
println(Hex::one("xa"))
}Today: error: Undefined rule: 'hex_digit'. at 3:35. Expected a. Part II 10.8 (docs/specification/20-nikaia-advance.md, the vocabulary table near line 746) lists hex_digit as one hexadecimal digit, value a scalar. The checker already knows the name (check_grammar.nika:80,118, bounds_matched.nika:39, fold_bound.nika:200); what lacks it is whoever resolves a called rule name when the grammar is built or lowered (find the message with nikaia run scripts/where.nika -- "Undefined" or by the place digit is handled beside it).
hex_digit resolves to a built-in matching 0-9, a-f, A-F, one scalar, as digit does for 0-9; hex_digit+ gives text as digit+ does. Then try every other built-in of the 10.8 table with a value or a plain match (digit, alpha1, any, char, raw_ident, string, multispace0, multispace1, line_ending, empty, eof); any other one refused the same way is the same defect: build it here when it is the same few lines, else name it under Found:.tests/compiler/tests/grammar_the_built_in_rules.nika with .stdout: the probe above, hex_digit+ over "x1fA" (prints 1fA), and one line per built-in step 1 found working or made to work. Run it against the unfixed compiler first; then the tests whose names start with grammar_ and hold digit or builtin.Only the file that resolves the built-ins (its .nika and lowered .rs, and lowered.rs) and the new test are yours; another file needed: stop, report partial with what and why. If the fix needs the specification changed (the list is wrong rather than the engine), stop and report blocked with Needs: owner decision.
The commit that finishes it says Fixes #1002.
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)./home/user/Nikaia/docs/briefs/bugs/b5-1002-hex-digit-built-in.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_01GFeMqxRbtUMiGVyDMxsvEq