agent: builder model: opus max_turns: 120 budget_usd: 32 —
Read first: ADR-361 D4, D5, D9 and D12 (new), Part III 14.2 (docs/specification/30-nikaia-tooling.md line 454), then the spike spike/prover-loop-ranges (09a7d79f): git show 09a7d79f -- crates/nikaia-std/src/tools/prover_loops.nika (+219 lines, a prototype) and its probes git show 09a7d79f:spike-probes/<name>.nika (a_const, b2_typed, c2_typed, c_acc_for, d_throw, e2_post, e_caller). Read them with git show; never check the branch out in the shared tree.
j gives the linear candidate counter > start + j*k || lo_j <= x <= hi_j, checked by D4’s three queries like any other. Proves json’s hex4 shape (n <= 0xFFFF after four turns of n = n*16 + v).throw in a loop body is a way out like a return (before, such a loop was not stated at all).let (typed, or a cast) that nothing reads binds a fresh name, so the conditions on it constrain it.let mut cp = call() never read, prover_walk.nika:499’s early return; facts of a let inside a branch lost at the join) and the untyped let d = ds[k] read (probe b vs b2). A probe that needs those stays out of this brief’s tests.prover_loops.nika diff onto develop in your head, not in the tree: list what of it is prototype (fixed limits, names) and what stays. Run probes a_const and b2_typed against develop’s compiler (check --asserts): both open today, say so under Tests:.let (small, separable): with tests prove_a_throw_in_a_loop_is_an_exit.nika (from d_throw) and one for the fresh name.for over a literal range and a while counter against a literal limit; nothing proposed beyond 16 or for a trip count the prover does not read; --asserts names what carried the proof (D7). Tests from a_const, b2_typed, c2_typed, e2_post, e_caller, and one with 17 turns that stays open (warning under unproved-claims = "warn", as unproved_claims tests do).throw an exit). Changelog: one sentence; the version raise is the supervisor’s.lower-std after each tools/*.nika change; the gate of .claude/agents/builder.md (#852), plus cargo test --profile fast -p nikaia --test it -- prove unproved_claims. The last commit says Fixes #639 and Part of #1003.
Files this brief may touch (beyond packages/yaml/): crates/nikaia-std/src/tools/prover_*.nika and their lowered files, tests/compiler/tests/prove_*, Part III 14.2 of docs/specification/30-nikaia-tooling.md; not packages/json/ (y4c’s).
sync (#1014): declare new or changed prover functions sync (y5 lost 8 turns to stale prover_passes.rs).--asserts lists only the checker’s claims; NK1300 for a precondition is raised at the callee’s assert (check_claims.nika).cargo test --lib prove runs 0 tests; the prover’s tests are tests/compiler and it -- prove unproved_claims.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/y7a-639-loop-ranges.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 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:); 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