clawmates

768 Commits 6 Branches 0 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
Omar SobhandClaude Opus 5	e4bddeb1ba	feat(ui): three-screen mission wizard that asks only what the type needs Five fixed steps for every mission type, and getting a research document out of it meant naming a team, choosing a runtime, and writing per-phase completion conditions under a paragraph explaining what a model checker can and cannot prove. Two of those steps asked for things the mission does not use, and one of them blocked outright. 1 What do you want to do? 2 Title, a description with a Polish button, repo ONLY if the type needs one 3 Review -> Launch, plus one collapsed Advanced section Two hard defects fixed on the way: - The microVM runtime could not be selected AT ALL. Step 4 gated Next on `targetNodeId`, which microVM deliberately never sets because placement picks the node per phase. Everything shipped today, the local-GPU backend included, was unreachable from the UI. - Step 3 required a team while every workflow TOML already names one in `default_team_template` — which this file ignored. The answer was always available and the question was always asked. It is now resolved by key, with a category fallback, and shown under Advanced so an operator can see WHICH default rather than having to supply one. A failed `/api/team-templates` request and a genuinely empty list rendered the identical red banner, which sends the reader looking for missing template files when the request had 401'd. They now say different things. `phases[]` is no longer sent unless someone set a completion condition. `recipeToPreset` strips each phase's `config`, so posting the stripped list overrode the recipe's real settings — tools, commit policy, loop mode — with nothing. Omitting it lets `phases_for_create` use the recipe, which is both simpler and more correct. Launch keeps its own gate, since Advanced can still produce an unlaunchable combination — but it names what is missing instead of greying out in silence. Artifacts get a Download link. Deliberately a plain link to the streaming route rather than a Blob built from what "Read" already fetched: that content is capped at 2 MiB and UTF-8-decoded, so reusing it would silently produce a truncated or undownloadable file for exactly the artifacts worth downloading. Co-Authored-By: Claude Opus 5 <[email protected]>	2026-08-09 18:50:13 -07:00
Omar Sobh	3616bc4733	feat(missions): an operator button to merge a mission's branch into main `MergePolicy::Never` — the default for anything touching code — has always meant "do not merge on your own", deferring to a human. There was no way for that human to say yes: `auto_merge` was reachable only from the paper-harvest path, no workflow template declares `merge_policy`, and every mission ended at a branch. `POST /api/missions/{id}/merge` is that yes, with a button on the artifacts tab. The additive-only gate does NOT apply here, deliberately: an operator reading a code change is exactly the judgement the policy was holding out for. What is not waived: - the branch comes from the artifact delivery RECORDED, not rebuilt from the mission id, and must have `pushed: true`. A phase that never pushed shows no button instead of one that cannot work. - an empty branch is refused. A button reporting success for merging nothing is worse than no button. - a conflict refuses, aborts, and leaves the repo clean rather than forcing. It works in a FRESH CLONE under `_merge/<mission>`, never the mission checkout: that directory is reaped on a timer after a mission ends, so a merge using it would succeed right after a run and fail inexplicably an hour later. The clone is made by the server process, so nothing runs as root and ordinary cleanup works — unlike the copies in `root_copy`. `merge_and_push` is split out so the operator path and the automatic path run the SAME git commands; only the gates differ. A test asserts both call it, that the operator path does not re-apply the additive gate it exists to bypass, and that it still refuses an empty branch. Harness 43/43 across all five recipes before this change, with `_gate`, `_bench` and `_verify` all at zero. 246 lib tests, 20 binaries, 89 frontend tests, clean build.	2026-08-07 18:53:38 -07:00
Omar Sobh	821cbb8622	feat(missions): hold every producing phase to delivering, and read markdown instead of PDFs Two changes the portal review asked for. 1. `benchmark` and `security_hardening` had no delivery guarantee. `empty_delivery_is_a_failure` tested `kind == "coding"`, on the reasoning that "research phases legitimately write nothing to the tree" — which the research directive three modules over contradicts, since it tells the agent to save findings under /mission/repo/research/. The cost: a `benchmark` mission is ONE benchmark phase, and with that phase exempt nothing in the platform could fail it. Same for `security_hardening`, whose first two phases are security_scan and research. Now keyed on PRODUCING_KINDS = coding, research, benchmark, security_scan. `review` stays exempt — a reviewing phase that changes nothing has done its job, the same distinction `vm_stop_gate::per_node` makes. The test that encoded the old rule is rewritten rather than deleted, with the reasoning that replaced it. All 8 harness fixtures are coding phases, so harness behaviour is unchanged. 2. PDFs are dropped; markdown is the deliverable. Rendering a PDF meant asking an LLM to convert markdown to HTML — a paid API call per document, on the critical path of "let me read my research", which failed on depleted Gemini credits and left every artifact unreadable. Styling at render time is free, offline, instant and cannot 429. - `mission_outputs` no longer requests a render. - New `GET /api/missions/{id}/artifacts/{artifact_id}/content`. The frontend had no way to READ an artifact at all: it listed paths and offered a PDF preview that never rendered (and whose `rendered_pdf_path` had no route serving it). Two containment rules, both enforced: the artifact must belong to a mission in the caller's workspace, and the CANONICALISED path must stay under `_outputs` — canonicalise first, because checking the string before resolving `..` is the classic hole. - `MarkdownBlock` now uses react-markdown + remark-gfm + rehype-slug. It was a deliberate zero-dep renderer for "the subset the refiner emits", and that subset stopped matching reality: agent briefs are largely GFM pipe tables, which it showed as literal pipes. MissionOutputReader and RefineDiffModal use the same component and gain tables for free. - Heading ids come from rehype-slug and `outlineOf` slugs with the same GithubSlugger, so the outline rail's anchors still resolve. A test pins that invariant, including duplicate headings. Styles live in globals.css under `.md-view`: the markup is generated so there are no class hooks, and this project has no styled-jsx registry — the app-router requirement is documented in next/dist/docs/01-app/02-guides/css-in-js.md, which frontend/AGENTS.md exists to make me read. The artifacts tab moved to `MissionArtifacts.tsx`. MissionCanvas was 1341 lines against a 1250 limit BEFORE this change — already failing lint; it is now 1248. 238 backend lib tests, 20 backend test binaries, 89 frontend tests, clean tsc, clean eslint on every file touched, production build succeeds.	2026-08-07 12:19:06 -07:00

Author

SHA1

Message

Date

Omar SobhandClaude Opus 5

e4bddeb1ba

feat(ui): three-screen mission wizard that asks only what the type needs

Five fixed steps for every mission type, and getting a research document out of
it meant naming a team, choosing a runtime, and writing per-phase completion
conditions under a paragraph explaining what a model checker can and cannot
prove. Two of those steps asked for things the mission does not use, and one of
them blocked outright.

  1  What do you want to do?
  2  Title, a description with a Polish button, repo ONLY if the type needs one
  3  Review -> Launch, plus one collapsed Advanced section

Two hard defects fixed on the way:

- The microVM runtime could not be selected AT ALL. Step 4 gated Next on
  `targetNodeId`, which microVM deliberately never sets because placement picks
  the node per phase. Everything shipped today, the local-GPU backend included,
  was unreachable from the UI.
- Step 3 required a team while every workflow TOML already names one in
  `default_team_template` — which this file ignored. The answer was always
  available and the question was always asked. It is now resolved by key, with a
  category fallback, and shown under Advanced so an operator can see WHICH
  default rather than having to supply one.

A failed `/api/team-templates` request and a genuinely empty list rendered the
identical red banner, which sends the reader looking for missing template files
when the request had 401'd. They now say different things.

`phases[]` is no longer sent unless someone set a completion condition.
`recipeToPreset` strips each phase's `config`, so posting the stripped list
overrode the recipe's real settings — tools, commit policy, loop mode — with
nothing. Omitting it lets `phases_for_create` use the recipe, which is both
simpler and more correct.

Launch keeps its own gate, since Advanced can still produce an unlaunchable
combination — but it names what is missing instead of greying out in silence.

Artifacts get a Download link. Deliberately a plain link to the streaming route
rather than a Blob built from what "Read" already fetched: that content is
capped at 2 MiB and UTF-8-decoded, so reusing it would silently produce a
truncated or undownloadable file for exactly the artifacts worth downloading.

Co-Authored-By: Claude Opus 5 <[email protected]>

2026-08-09 18:50:13 -07:00

Omar Sobh

3616bc4733

feat(missions): an operator button to merge a mission's branch into main

`MergePolicy::Never` — the default for anything touching code — has always meant
"do not merge on your own", deferring to a human. There was no way for that human
to say yes: `auto_merge` was reachable only from the paper-harvest path, no
workflow template declares `merge_policy`, and every mission ended at a branch.

`POST /api/missions/{id}/merge` is that yes, with a button on the artifacts tab.
The additive-only gate does NOT apply here, deliberately: an operator reading a
code change is exactly the judgement the policy was holding out for.

What is not waived:

  - the branch comes from the artifact delivery RECORDED, not rebuilt from the
    mission id, and must have `pushed: true`. A phase that never pushed shows no
    button instead of one that cannot work.
  - an empty branch is refused. A button reporting success for merging nothing
    is worse than no button.
  - a conflict refuses, aborts, and leaves the repo clean rather than forcing.

It works in a FRESH CLONE under `_merge/<mission>`, never the mission checkout:
that directory is reaped on a timer after a mission ends, so a merge using it
would succeed right after a run and fail inexplicably an hour later. The clone is
made by the server process, so nothing runs as root and ordinary cleanup works —
unlike the copies in `root_copy`.

`merge_and_push` is split out so the operator path and the automatic path run the
SAME git commands; only the gates differ. A test asserts both call it, that the
operator path does not re-apply the additive gate it exists to bypass, and that
it still refuses an empty branch.

Harness 43/43 across all five recipes before this change, with `_gate`, `_bench`
and `_verify` all at zero.

246 lib tests, 20 binaries, 89 frontend tests, clean build.

2026-08-07 18:53:38 -07:00

Omar Sobh

821cbb8622

feat(missions): hold every producing phase to delivering, and read markdown instead of PDFs

Two changes the portal review asked for.

1. `benchmark` and `security_hardening` had no delivery guarantee.

`empty_delivery_is_a_failure` tested `kind == "coding"`, on the reasoning that
"research phases legitimately write nothing to the tree" — which the research
directive three modules over contradicts, since it tells the agent to save
findings under /mission/repo/research/. The cost: a `benchmark` mission is ONE
benchmark phase, and with that phase exempt nothing in the platform could fail
it. Same for `security_hardening`, whose first two phases are security_scan and
research.

Now keyed on PRODUCING_KINDS = coding, research, benchmark, security_scan.
`review` stays exempt — a reviewing phase that changes nothing has done its job,
the same distinction `vm_stop_gate::per_node` makes. The test that encoded the
old rule is rewritten rather than deleted, with the reasoning that replaced it.
All 8 harness fixtures are coding phases, so harness behaviour is unchanged.

2. PDFs are dropped; markdown is the deliverable.

Rendering a PDF meant asking an LLM to convert markdown to HTML — a paid API
call per document, on the critical path of "let me read my research", which
failed on depleted Gemini credits and left every artifact unreadable. Styling at
render time is free, offline, instant and cannot 429.

- `mission_outputs` no longer requests a render.
- New `GET /api/missions/{id}/artifacts/{artifact_id}/content`. The frontend had
  no way to READ an artifact at all: it listed paths and offered a PDF preview
  that never rendered (and whose `rendered_pdf_path` had no route serving it).
  Two containment rules, both enforced: the artifact must belong to a mission in
  the caller's workspace, and the CANONICALISED path must stay under `_outputs`
  — canonicalise first, because checking the string before resolving `..` is the
  classic hole.
- `MarkdownBlock` now uses react-markdown + remark-gfm + rehype-slug. It was a
  deliberate zero-dep renderer for "the subset the refiner emits", and that
  subset stopped matching reality: agent briefs are largely GFM pipe tables,
  which it showed as literal pipes. MissionOutputReader and RefineDiffModal use
  the same component and gain tables for free.
- Heading ids come from rehype-slug and `outlineOf` slugs with the same
  GithubSlugger, so the outline rail's anchors still resolve. A test pins that
  invariant, including duplicate headings.

Styles live in globals.css under `.md-view`: the markup is generated so there
are no class hooks, and this project has no styled-jsx registry — the app-router
requirement is documented in next/dist/docs/01-app/02-guides/css-in-js.md, which
frontend/AGENTS.md exists to make me read.

The artifacts tab moved to `MissionArtifacts.tsx`. MissionCanvas was 1341 lines
against a 1250 limit BEFORE this change — already failing lint; it is now 1248.

238 backend lib tests, 20 backend test binaries, 89 frontend tests, clean tsc,
clean eslint on every file touched, production build succeeds.

2026-08-07 12:19:06 -07:00