agent: builder model: opus max_turns: 100 budget_usd: 20 —
sum() of a typed number sequence lowers without a type (run 2)Score: bug lane, a false acceptance (the checker passes, rustc refuses; S=2) in a one-line form any move that adds numbers writes. K3a part 2 waits on the owner (#1012), so this runs first. Builders have no GitHub: the issue text is copied below. Run 1 (b1007-sum-typed.md.run1.report.md) stopped because no checker fact carries the call’s result type to the emitter; this run adds that fact (the brief now allows the checker files).
sum() over a sequence of a typed number list lowers to a bare .sum(); rustc cannot infer the result type when nothing annotates it (found by b1006). #931 (5162370e) wrote the type on the let only for an open number literal list.
target/fast/nikaia run; all rows but the annotated ones fail)fn total(v: Vec[i64]) -> i64 {
let t: i64 = v.iter().sum()
return t
}
fn main() {
let v: Vec[i64] = [3, 4]
println(v.iter().sum()) // 7
let s = v.iter().sum()
println(s) // 7
println(total(v) + v.iter().sum()) // 14
let w: Vec[f64] = [1.5, 2.0]
let t: f64 = w.iter().sum()
println(t) // what println prints for 3.5
println(w.iter().sum()) // the same
}Today: rustc “type annotations needed” (Sum<i64>, i64: Add<_>).
The emitter reads checker facts by node key (node_key(e) = id_of(e) as i64); there is no fact with a call’s result type: std_receivers (receiver’s ledger type), open_items (open literals only, #931) and collected_into (a set) do not give i64 here. Add one:
crates/nikaia-std/src/tools/check_facts.nika: a new field beside collected_into (line 218), e.g. pub summed: collections::BTreeMap[i64, String] (call node -> Rust number type, "i64", "f64", …), with its doc comment, and its empty value in the constructor beside line 502.crates/nikaia-std/src/tools/check_core_method.nika:568, check_core_method_called: value is the checked result of check_core_call_on. When name == "sum" (and only for the core sequence method, not a program’s own sum) and value is a plain number type (Ty::Named with no args, a number name), insert id_of(expr) as i64 -> name into the new fact.crates/nikaia-std/src/tools/emit_core_calls.nika ~1176-1186, emit_core_method_call_body: beside collect’s ::<Vec<_>>, push ::<T> after sum when self.facts.summed[on_node] holds a type. Check which node on_node is at this point (the call’s or the receiver’s: emit_core_calls.nika:1480 passes node_key(receiver), so the call node may need to be handed in, or the fact keyed by the receiver; decide by reading, say which in Body:).crates/nikaia-std/src/tools/lowered/{check_facts,check_core_method,emit_core_calls}.rs (written by lower-std, never by hand).tests/compiler/tests/a_number_list_literal_summed_is_typed.nika (must still pass).lower-std fixpoint (lower-std, build, lower-std: the second run changes nothing; only files that call sum or the three edited files change). New test tests/compiler/tests/a_typed_list_summed_needs_no_annotation.nika + .stdout holding the probe rows (take the .stdout from the real run; say so in Body: for the f64 lines). Any turbofish rustc accepts is fine (.sum::<i64>()); a ref element stays Sum<&i64> on the Rust side, the turbofish names the result. Fixes #1007.The new test passes through nikaia test (copy it to the scratchpad to nikaia run it alone first), a_number_list_literal_summed_is_typed still passes, the lower-std fixpoint is clean, the gate of .claude/agents/builder.md is green; pushed. Commit subject: check, emit: sum() names its result type (#1007), Fixes #1007. Changelog: one line (a program that rustc refused now runs).
An edit outside the three .nika files above, their lowered files, lowered.rs’s index lines, other lowered files lower-std rewrites because they call sum, and the test; an error in another agent’s file.
Not yours, never stage: crates/rs2nika/convert/nikaia.{contracts,derived,proofs} and every docs/briefs/* file that git status shows modified or untracked except your report.
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/b1007-sum-typed.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_01GFeMqxRbtUMiGVyDMxsvEq