Strengthen template planning, reuse and independent review

This commit is contained in:
2026-10-12 23:10:37 +01:00
parent 03ed4e02e4
commit 143f237268
14 changed files with 424 additions and 46 deletions
+15
View File
@@ -100,6 +100,10 @@ Every submission, including agent-issued `submit`/`rpc`, still uses server valid
## Drafts in the TUI
The server admits one active run at a time. A new request key is rejected while
another run is active; inspect that run and wait for it to finish. Reusing its
original request key reattaches idempotently.
Use `:templates` for five simple, manual-only starters: task, summary, review,
research, and plan/implement/review. **Submit template** (`s` or Enter) asks for a
name without opening an editor. Enter saves a retained draft, then a separate
@@ -107,6 +111,17 @@ confirmation publishes it as a new pipeline. Esc before naming creates nothing;
Esc at publication keeps the draft. **Customize** (`e`) opens the editor picker
instead. Both paths inherit the configured default model and preserve existing
pipelines/history. The research starter requires configured web search support.
Starter stages use goal-appropriate tools: the task stage and the three-stage
implementer edit and run checks, the task, planner and review stages may
search/fetch official sources only when external knowledge is genuinely needed,
the three-stage implementer has no web tools and follows the planner's research,
the standalone review stage never edits or runs commands and says so explicitly,
and the three-stage reviewer independently inspects the real changes and receives
the planner-owned acceptance checks rather than the implementer's summary,
approving only when the applicable acceptance checks were independently observed
passing and no unresolved substantive issue remains. Editing a bundled template
source changes no installed or published definition; a starter becomes an
immutable version only after explicit authoring and publication.
Home's `n` / `:new` and **Customize** (`e`) on a template first ask how to author the new
pipeline: **nvim** opens a retained Markdown draft file, or a configured harness
+40
View File
@@ -405,3 +405,43 @@ This controlled fixture is **not** the actual new-account install/provider login
recorded in the 2026-10-11 FINAL INSTALLED section above, which this change does
not re-run. It is docs-and-ignore only, with no rendered UI and no live install or
provider evidence.
## 2026-10-12 run22 success, run23 live CSV fixture and run24 interruption
Source/structural and live-fixture evidence is kept separate from runtime
deployment; nothing in this section is a deployment claim.
- **run22 (structural/source checks, success):** the retained run22 verification
completed its structural/source checks of the scoped template and prompt changes
and passed.
- **run23 (live Pi CSV fixture):** a real exact-template Pi CSV run fetched the
official Python `csv` documentation through the stage's conditional
official-source webfetch and implemented CSV parsing with the standard library's
`csv.reader` through an existing shared helper, adding no duplicate preview
parser; both the implementer and reviewer checks actually passed. Root
independently checked full retained native tool results and protected-file
hashes against its saved baseline, rather than relying on model-written reports.
- **run24 (interrupted, not a pass):** the run24 implementation completed, but its
reviewer ignored the scope instruction and ran a prohibited filesystem-root scan
(`find /`), leaving a process in uninterruptible D-state and stalling Docker
mount/snapshot reads. Root canceled the run, made a consistent SQLite backup
(`integrity ok`), recovered Docker with the supported stop/start path, and
restored the existing ntfy/Pipelines services. The original definitions, run
history, credentials and settings were verified unchanged. run24 remains
retained as **interrupted**, not a success.
- **run25 (live Pi source-only review):** the reviewer identified duplicated
implementation, a hardcoded special case, suppressed errors and test gaps.
Root inspected retained native calls: only local read/search tools ran, with no
shell/edit/network calls. Original fixture hashes were unchanged; runtime
behavior was explicitly marked untested.
- **run26 (final maintenance review, success):** the scoped plan/implement/review
workflow passed package tests, vet, build and formatting checks. Root inspected
the actual retained outputs and changes. No rendered UI change was claimed.
The scoped prompt guidance asks stages to keep inspection/verification to relevant
repository paths and supported commands. That is a working instruction, **not** an
OS sandbox: it neither fixes Docker VM/disk bugs nor universally enforces tool
boundaries. At these recorded checkpoints the source changes had not been deployed.
Catalog deployment requires a separate check of the running server and its actual
template contents; these observations do not establish publication or deployment.