agent: builder model: opus max_turns: 120 budget_usd: 25 —

Brief: P5c, Project::drive and drive_to of project.rs into project_drive.nika (Part #125)

Score: self-hosting lane, plan row P5c of docs/selfhosting-plan.md (prerequisites P5a, P5b, P5d built; #920 built 8eb22790, so process::run streams). S=2, C~3-5 M (comparable: P5d). K3b is blocked on #1077 and #1078 (bug lane b17, b18) and did not land: a host method write_if_changed(path, text) forwards to the Rust one in comptime_run.rs (unchanged); say so in Body:. K3b’s re-run later turns it into the Nikaia call.

Cut: crates/nikaia/src/project.rs:2116-2590 Convert: –profile check-free –prefix project_drive_ Shape: schematic host-calls (R295’s host parameter, as project_members.nika and P5d’s project_check.nika)

Facts: Where things live, Traps already met, Moving Rust into Nikaia, Commands

The driver converts this before you start. Ranges re-grepped at 4520d400 (33ed1119 and its neighbours shifted them by 4); if git log -- crates/nikaia/src/project.rs shows a later change (K3b may touch build_for_cpu’s call), re-grep /// Build the project, or build and run it. and the end of pub fn drive_to and cut again.

Facts

To build

  1. project_drive.nika, the host impl and the forwards in project.rs; lower-std and its fixpoint. Tests: cargo test -p nikaia --test it -- project build run_ library c_library python node explain ledger (anchored grep -E '^test result:|FAILED|panicked'), cargo test -p nikaia --lib project::, and nikaia test tests/compiler on two project_* tests. Commit project: drive and drive_to move into Nikaia (P5c), Part: #125; plan rows P5c (built, what stays Rust) and P5e (record_resolved_dependencies is a host method of P5c now) updated, self-hosting share in the body. Stop about 15 turns before max_turns, commit what is finished and report partial.

Re-run (after #1088, bug lane b20)

Run 1 finished the move on branch wip/p5c-project-drive (cc40334f) and stopped on #1088: a tuple’s String? part at a return match end got no Some. Pre-flight: the probe in #1088 prints 2x on HEAD’s binary, or stop. Then take the branch’s files onto develop (by name, not a merge). Do not hand-wrap lowered/project_drive.rs. Run lower-std, the build and the tests, update plan rows P5c/P5e and the self_hosting.py row, score rs2nika against the branch’s project_drive.nika, and commit. Keep the design run 1 chose: ProjectDriveRefusal::Failed(String), toolchain_can_build_for -> bool with its text in project_drive_no_std_for, the host getters shown_as, allowlist, root_tag, package_name, bind, and Rust dependencies_first removed. Name them in Body:.

Rules (CLAUDE.md; this block is pasted into every brief, also a fix-forward)

Report (at most 15 lines, to exactly /home/user/Nikaia/docs/briefs/p5c-project-drive.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

This site is open source. Improve this page.