M4.2: the toolchain step
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 2m36s
CI / e2e (pull_request) Successful in 11m13s

The preflight becomes the toolchain step (D3, as #135 describes it): a
bounded run of the item's driver model, in a transcript of its own,
that makes the build VM and the project's files agree.

- Started by the harness when the VM isn't set up for the project
  (M4.1's checks): it sets the VM up from the repository and edits
  nothing there (no write_file; anything a command changed is reported,
  left for the work).
- Requested by the driver with toolchain_step(reason) once work is
  agreed: it installs, then brings pins, setup docs and CI
  configuration in step; its edits land in the current milestone. The
  driver gets the step's report as the tool's result, not its turns.
- D1 made structural: until the go-ahead the fast path refuses what it
  knows changes something (and anything dangerous), with a pointer to
  the restatement; unknown commands still go to the classifier, so a
  bug can be reproduced before it's restated.
- A `toolchain` actor and view; the walk asks for steps now and then.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-08 17:37:21 +00:00
1 parent 97ea451629
commit d9f2ebd5aa
10 files changed
+283 -62

No files matched your search

+2 -2
View File
@@ -90,8 +90,8 @@ tuning:
driver:
max_turns: 40 # model calls per driver run before it stops as capped
failure_limit: 2 # consecutive failed commands before escalating (L9)
preflight: # getting a project's toolchain ready (D3)
max_turns: 20 # model calls the preflight run may make
preflight: # the toolchain step (D3)
max_turns: 20 # model calls one toolchain step may make
command_timeout_s: 900 # one command in it: installs take a while
expert:
consult_budget: 3 # ask_expert calls per milestone (L9)