agent: builder model: opus max_turns: 70 budget_usd: 14 —
yaml merge, the << merge key on request (#928 step 4, D6)Score: #928 step 4, the step after load (y27-load.md run 2 runs before this brief in the same checkout; its commit is on your develop). This change touches only packages/yaml and needs no version raise and no CHANGELOG.md entry (ADR-yaml-1 D1).
Read docs/builder-facts.md, ADR-yaml-1 D6 with its paragraph of 2026-10-31 on merge (docs/specification/adr/adr-yaml-1.md), and in packages/yaml/src/main.nika the tree types, Error, place_of, load, load_error, key_of.
rg -n "pub fn load|fn key_of" packages/yaml/src/main.nika shows both (y27 built). If not, build nothing: Result: blocked, Found: y27 not built. Rebuild target/fast/nikaia (cargo build --profile fast -p nikaia) when it is older than git log -1 --format=%ci -- crates/.
pub fn merge(node: Node, input: ref Bytes) -> Node sync throws, over a tree from load, every mapping at every depth (sequences, mapping values and keys walked):
<< is taken out. Its value is a mapping, or a sequence of mappings; each such mapping is merged first (its own <<), then its entries are appended after the mapping’s own entries, in order, each only when its key (key_of, as load compares keys) is not yet in the mapping: the mapping’s own keys win, then the first merged mapping over a later one (<<: [*a, *b]: a’s key wins over b’s).<< (scalar, null, a sequence with a non-mapping, an Alias left) is an Error at that value’s position (load_error), message naming what it found (expected a mapping or a list of mappings to merge, found <kind>, wording yours)."<<" key is an ordinary key, untouched. Anchors and tags stay on the nodes; strings stay views (no .clone() of a text where the node’s own .clone() serves).
Commit.packages/yaml/tests/merge.nika + .stdout: <<: *base with an own key overriding one of base’s (order printed: own keys, then base’s remaining); <<: [*a, *b] where a and b share a key (a wins); a nested merge (base itself holds a <<); a merge inside a sequence item; "<<" quoted left as a key; a scalar <<: 1 refused with its line:column; a sequence holding a scalar refused; merge on a tree without << gives it unchanged. Print each mapping as key=value lines through a small helper in the test. Write the test before the first package run, fill .stdout with --bless in that run only after check is clean (docs/builder-facts.md, Traps already met), and check every line by hand.If a form the package needs is missing or refused in the compiler, the lowering or std (no ADR refusing it), stop: Result: blocked, Found: the gap with a probe of a few lines, Needs: architect decision. Do not write around it (a hand-written copy instead of .clone(), an index map because a map of views is refused, x?.clone() to dodge a match that rustc refuses: report them).
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. Do not push: the driver runs the suite on your commit and pushes it (CLAUDE.md, Builders commit, the driver tests and pushes).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: architect 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 is local <sha> of your last commit. 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 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/y31-merge.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