web: shared chat stars, pipeline mini graphs and agent questions

- Persist chat stars in the operator-session registry (chat_star) so every
  browser/device shows the same Starred group; migrate old local stars once.
- Add a compact pipeline graph shape to list responses and draw a lightweight
  list miniature; replace the cryptic id/version line with the stage count.
- Surface OpenCode form questions as a chat card (chat_answer), replay a
  pending form to late subscribers, and notify for background questions.
- Make the mobile dock's Search cell equal to every destination, keep the
  tab row visible with 100svh, and let Source use the full pane height.
- Let a fresh sign-in auto-connect to its own origin; use a Lax session cookie
  with Expires so Remember me survives app/link launches.
- Keep shipped starters and the skill agnostic: no repository paths, project
  areas or personal device commands; add Diagnose/Fix and Research starters.
- Refresh the installed skill and document the new browser conventions.
This commit is contained in:
2026-10-20 03:11:37 +01:00
parent caae8a8038
commit 526c19fc21
46 changed files with 1547 additions and 611 deletions
+18 -27
View File
@@ -7,21 +7,15 @@ pipeline automatically; all templates are manual-only and have at most four stag
| --- | --- | --- |
| `task` | Complete a task, then commit it locally | Work: read/edit/shell and conditional web search/fetch; committer: read/shell |
| `review` | Read repository content and report findings | Read/glob/grep and conditional web search/fetch; no edit/shell |
| `research` | Research a topic, then write a sourced report | Web search/fetch, then none |
| `three-stage` | Plan → implement → review → commit | Planner read/glob/grep + conditional web; implementer read/glob/grep/edit/shell with no web (follows the planner's research); reviewer independent shell + conditional web; committer read/shell |
| `docs-fold` | Fold accumulated item documentation notes into the shared docs, then commit locally | Fold: read/glob/grep/edit/shell; committer: read/shell |
| `research` | Research a question, then write a sourced report | Web search/fetch, then none |
| `three-stage` | Plan → implement → review → commit | Planner read/glob/grep + conditional web; implementer read/glob/grep/edit/shell; reviewer independent shell + conditional web; committer read/shell |
| `debug` | Diagnose → fix → verify → commit | Diagnose read/shell; fix read/edit/shell; verify read/shell; committer read/shell |
Every workflow that changes the repository ends in a **committer** stage that
commits locally and never pushes. The committer inspects `git status` and the full
diff, stages this run's change (a model-declared list can be incomplete), then runs
the repository's required checks before committing. `task` and `three-stage` follow this;
`review` and `research` change nothing and so do not commit.
`docs-fold` is the deliberate **single documentation writer**. A per-item workflow never
edits a shared README or topic doc: when its change makes one stale it records a note at
`docs/notes/<slug>.md`, unique per item, and commits that note with the change. Running
the manual-only `docs-fold` pipeline later folds the accumulated notes into the shared
documentation and removes them.
diff, stages this run's change, and runs the repository's required checks before
committing. `task`, `three-stage` and `debug` follow this; `review` and `research`
change nothing and so do not commit.
Model and agent stages read the turn's `input.md` and `memory.md`, then return the
complete `output.md` markdown. The only required section is `# outcome` followed by
@@ -32,15 +26,13 @@ Web search/fetch is conditional: stages use it only when a task genuinely needs
external knowledge such as accepted industry approaches, framework or library
APIs, current security/compatibility guidance, or unfamiliar techniques, and they
state why when no research is needed. Trivial, fully understood local edits do not
force web access, and conditional research fails closed only when the required
reliable evidence cannot be obtained, not merely because one search failed. The
`three-stage` implementer has no web tools and works from the planner's research
with local read/edit/shell. The `three-stage` reviewer is an independent quality
gate: it receives the original task and the planner's plan/design/reuse
targets/acceptance checks, inspects the actual changed files and runs its own
checks, returns success only when the applicable acceptance checks were
independently observed passing and no unresolved substantive issue remains, and
otherwise rejects with concrete findings even when a stage reported success.
force web access. The `three-stage` implementer works from the planner's research;
the reviewer is independent and checks the actual change rather than trusting a
stage summary.
No template assumes a language, framework, repository layout, device, deployment
target or notification setup, and none pushes to a remote. They read the project's
own conventions instead of naming files that only exist in one repository.
In the TUI, use `:templates`, choose a starter, and press **s** or Enter on
**Submit template**. Type a name, press Enter to save a retained draft, then
@@ -55,14 +47,13 @@ pipelines drafts
pipelines submit /path/printed/by/new.md
```
New drafts inherit the server's configured default model. The checked-in files
contain a fallback model; direct file submission uses those configs as written.
Provider inference and search availability must be verified on your execution
server. Parsing a definition does not prove its model/tools can run.
A draft created through the UI or `new` inherits the server's configured default
model. The checked-in files carry an example provider/model for direct file
submission; replace it with one your execution server actually supports. Provider
availability and search support must be verified on that server.
Templates do not impose a language, framework, schedule, notification setup or
deployment, and they never push to a remote. Work-producing templates commit
locally through their committer stage; add a schedule, notifications or a
deployment, and they never push to a remote. Add a schedule, notifications or a
deployment step only when your own workflow requires it.
Editing these source files does not change any installed or published definition;