Commit Graph
3 Commits
Author SHA1 Message Date
gregandClaude Opus 5.5 929cbc31cf fix(builder): keep every game's name and code out of the builder
Validate game templates / validate (push) Successful in 19s
Validate game templates / boot-test (push) Skipped
Validate game templates / publish (push) Skipped
The builder must be game-agnostic, but its prompts named games: AUTHORING.md
(the model's rules) used three games as examples, the research prompt listed
two games' editions, the schema described containerUser by one game's image,
and every draft prompt included two real templates from the repo, so the
model saw, and could copy, other games' commands and options.

- AUTHORING.md, the research prompt and the schema describe the rules without
  naming a game.
- The draft prompt's format example is now one invented server (no real
  command, options, ports or app id), checked by
  TestExampleTemplateFollowsTheRules against validation and the draft checks.
- Comments, help texts, BUILDER.md and test fixtures use invented names and
  values.
- TestBuilderIsGameAgnostic reads every game's name and id from games/ and
  fails if any appears in the builder's code, tests, rules, schemas or docs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 17:58:27 -04:00
gregandClaude Opus 5.5 8b49895d5e feat(builder): launch options must appear in the research sources
Validate game templates / validate (push) Successful in 19s
Validate game templates / boot-test (push) Skipped
Validate game templates / publish (push) Skipped
The Valheim draft in #13 passed -maxplayers, an option Valheim doesn't have.
The server ignores unknown options, so the draft booted and passed every
boot test while its MaxPlayers setting did nothing.

build now reads the pages research based the variant on, in full, and the
drafter rejects any launch option in the startup command that none of them,
nor the image's own scripts, mention. The model gets it back to remove or
spell correctly. Options of shell tools (mkdir -p, [ -n ...]) are skipped.
The check is off when there are no sources (draft run by hand, no reader).

Against #13's 11 real sources it flags -maxplayers and nothing else.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 17:47:33 -04:00
gregandClaude Opus 5.5 c75190d8c4 feat(builder): research, build and a worker for the AI builder
Validate game templates / validate (push) Successful in 19s
Validate game templates / boot-test (push) Skipped
Validate game templates / publish (push) Skipped
- research: searches SearXNG, reads the best pages through the reader, has the
  model list the server's variants, then checks every Docker image and Steam
  app it named for real before an admin sees it.
- build: first boot of the variant's images (skipping ones that need root),
  a draft by the model, then the draft deployed with the node-agent's
  BootTest like CI does; crashes, error lines and saves outside /server go
  back to the model, three boots at most.
- worker: polls the panel's builder queue (outbound only), runs research or
  build in a fresh clone, streams the output as the job log, and opens the
  result as a pull request from the bot account.
- Dockerfile.builder, a workflow publishing gbr-builder:latest, and
  BUILDER.md. Everything about where it runs comes from environment
  variables; deployment files live outside this public repo.

draft now keeps its conversation in a drafter, so build can send boot
failures back to the same model session. The boot-test runner comment no
longer names its VM.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-25 12:51:29 -04:00