Six computed Flutter runs stopped at the export handoff gate because the
rendered session.html cap was 2 MiB while their complete sessions (well inside
the 8 MiB source read bound) rendered between 2.25 and 4.28 MiB once html
escaping and the readable projection duplicated native text.
Raise SessionExportFileLimit to 8 MiB, the server's existing per-artifact file
bound, so a complete export is still listed and served. Normal export
verification, versioned repair and the handoff gate keep using the single
shared constant. The source read bound is unchanged, and an over-cap render is
still visibly truncated and recorded partial.
Add focused regressions for a complete export above the old cap, an over-new-cap
file rejected as partial, repair above the old cap leaving original evidence
untouched, the gate accepting the larger repair, and the constant staying inside
the artifact file bound. Update the artifact, handoff-gate and operations docs
and record the diagnosis in docs/notes/session-export-render-cap.md.
Read OpenCode V2's resolved default Model.Info through its authenticated CLI API from HOME when saved profile fields are missing. Preserve valid saved models, explicit --model and unrelated settings. Record the selected stage model in the native server environment so web starters have an actual default.
Run the existing read-only model picker inside ./install when a terminal needs a choice; fail noninteractive or cancelled/incomplete setup before claiming ready or starting services. Do not parse JSONC, open login flows, create sessions or run inference. Document the one-step configuration path.
Checks: 61 mocked native installer/lifecycle tests, 8 entrypoint tests, sh -n install install.sh, git diff --check. API/schema checked against official OpenCode V2 documentation. No operator CLI/service/model calls, live install, restart, deployment or native Linux verification.
Select native installs only via explicit PIPELINES_PREFIX or the matching owned prefix/bin/pipelines executable. Route enable/status/disable to the existing native supervisor; validate registration ownership, label and command, keep preview read-only, and disable login registration before stopping. Never fall back to a standalone service for an invalid explicit prefix.
Fresh native installs explicitly enable authoring, while reinstalls preserve false or missing legacy role settings. Add explicit --allow-authoring/--no-authoring overrides and pass the server flag only for manifest true. Print a copyable native enable command and update installation help/docs. No Docker configuration changes.
Checks: 54 mocked native installer/lifecycle tests; 8 entrypoint tests; offline Go installation/CLI tests and vet; gofmt clean; shell syntax and diff checks. No live install, restart, deployment, permission/config changes, or native Linux verification.
Register the existing native supervisor with launchd/systemd, include the dependency-free authenticated web proxy, detect Node, and keep the API loopback by default. Preserve existing web credentials and configured host harness defaults. Clarify single-step setup, lifecycle selection, and optional ntfy limits.
Checks: 44 mocked native installer/lifecycle tests; 8 entrypoint tests; 42 Docker installer tests; GOPROXY=off GOTOOLCHAIN=local go test ./internal/installation ./cmd/pipelines; sh -n install install.sh; git diff --check. No live install, deployment, restart, downloads, real autostart/login verification or native Linux verification.
Store a chat's harness with its operator session, expose chat_backends and a
backend choice in New chat, and route each session through a manager. The Codex
adapter uses the App Server's Unix WebSocket for threads, turns, history,
questions and interrupt; OpenCode remains the default and Claude is not
advertised until its sidecar and login are wired.
Turn bodies were embedded verbatim, so a body's own ## headings looked like
sibling turns and could even duplicate the system's "Files added to public/"
line. Body headings are now demoted two levels (capped at H6) outside fences;
fenced code is untouched.
ParseOutput returned only the text after the outcome value, so a stage that wrote
its result first and "# outcome" last handed the next stage "(no output)" — the
probe's Compose and Critique turns were both lost this way. The body is now the
whole document with just the outcome heading and value line removed, in order,
byte for byte. Tests cover a trailing and a mid-document outcome.
Each model visit now gets <run>/stages/<seq>-<stage>/ with input.md,
memory.md, output.md, private/ and a shared run-level public/. The model
reads the two input files, follows the stage's instructions verbatim and
returns complete markdown; only the # outcome section is parsed.
- add internal/turn layout, render and output parsing
- write input.md/memory.md before a visit and output.md from the final
message; inventory all turn files as stage artifacts
- accumulate completed turns and system-written public file additions in
memory, including across retries and resume
- remove the JSON envelope, strict field validation, line format and the
repair ladder for model stages
- republish pipeline authoring prompts and docs in the new style
Checks: go build ./..., go vet ./..., go test -count=1 ./..., gofmt -l .
Drop the resource allocation feature end to end: store tables and migration, runner scheduling and cleanup, protocol types and commands, CLI commands, TUI screens, tests and docs. Existing databases open cleanly and definitions carrying a retired resources block still validate.
The operator's chat list showed ~99 stray "New chat" entries. The listing
was already fail-closed (registry-only); the fault was what got recorded: an
automated UI check drives the real page, so its throwaway chat was recorded as
an operator chat exactly like a manually created one and stayed in the list for
ever (each run added one).
Server: chat_create takes an optional ephemeral flag. The session is created,
bootstrapped, usable, closable and reopenable exactly like any other, but its
registry row is hidden, so chat_sessions never lists it. operator_sessions gains
an ephemeral column (idempotent migration, existing rows default to listed) and
the list query filters it; the single-row lookup does not, so close/reopen keep
working. RecordVerificationSession is the hidden recorder.
Web: the page marks a create ephemeral only when automation asks for it
(__pipelinesEphemeralChat, set by the UI smoke for its throwaway chat), so the
smoke's own runs stop polluting while a manual create is unchanged.
Tests: a hidden row is never listed yet is still looked up and closable; a
normal re-record of the same id lists it again; a pre-ephemeral database
migrates with every existing chat still listed. Live data pruned separately
(107 -> 8 registry rows, backed up).
The chat background-task bar now lists only tasks that are still running, so an
exited task no longer lingers and the bar disappears when the last one ends. The
one-line 'running now and recently observed exits' subtitle is replaced by a
compact 'Background tasks · N running' header, and the list is capped at three
touch-sized rows and scrolls beyond that instead of pushing the composer down the
screen. Unit-tested (running-only set and the row cap) and the stale note
updated.