The Web overlay disables base's 32 agent-plane rows and mounts the preset
roster instead, so each session composes its own tools and prompt rather than
sharing one process-wide set. The TUI keeps base unchanged: it is single-session
and composing its agent process-wide is correct there.
`roots` is patched in by AppCLIEntry, like `distIndex`: the shipped presets sit
beside the composition that names them and the user's live under the Harness
home, neither of which a config author chooses.
A session's preset is fixed at creation. Naming a different one for an existing
identity is `agent-preset-conflict` rather than a switch, because that
session's history was produced under the first preset's tools. The guard sits
after `await creation`, beside the cwd check, so it covers every path that
yields a live agent — freshly created, adopted live, resumed, or recovered by
the concurrent-creation catch. A request naming no preset adopts the session as
it is, keeping reconnect and retry ordinary.
Two bugs the real-composition test caught, both invisible to unit tests:
`PresetTree` now refuses to write. The Loader persists a tree whose plugin
self-disposed, and tearing an agent down disposes its whole subtree — inherited,
that rewrote the shipped composition, truncating a 241-line preset to `[]` the
first time a session ended.
`dsh-tool-skill` compared against a lookup of its own name in the global layer,
so it threw inside any preset: `register()` files into the calling context's
scope. It now compares against the definition it registered, which is what the
identity check meant all along.
The `standard` catalog is asserted exactly, not spot-checked: a row that
registers into the wrong layer mounts cleanly and simply contributes nothing, so
an omission is this design's quietest failure. It matches the shipped TUI
catalog plus `glob`/`grep`, the pair that composition documents as
ripgrep-dependent.
Re-records `cordis-inspect-jsdoc`, whose rendered `SessionHeader` gains the
`agentPreset` field. `fs-glob-sampling` fails identically on pristine master
and is untouched here.
The browser e2e scaffold gains the roster fact AppCLIEntry supplies. `roots` is
resolved and patched in by the CLI entry, like `distIndex` on the webserver row,
and this lane boots the shipped tree without that entry — so it has to supply
the same fact or the roster resolves nothing and every session in the lane
composes an agent with no tools, no persona, and no token meter. Only the
shipped root: a developer's own `~/.dsh/.agent-presets` must not decide a golden. The
`cordis:group` builtin comes with it, exactly as `boot()` registers it, because
a preset resolving package names from its own directory cannot reach
`@cordisjs/plugin-group` by name.
The lane stays red through this layer and the next four for the reason stated
above — the api-proxy injects `subagents`, `workspace`, and `tools`, so
`api-gateway` cannot activate and the browser has no `/api` at all. It goes
green again in the layer that returns those registries to the host plane; this
change is what makes that layer's fix sufficient rather than partial.
The profile rework left references to the old entry modes behind. Renames
the user patch-layer API and its spec file (watchPersonalPatches ->
watchUserPatches, personal-config.spec.ts -> user-patches.spec.ts) and
retargets the prose that still named `config.yaml`, `--config`, raw-config
mode, and surface overlays: repository-plugin and mcp-memory READMEs, the
credentials-local anchor into app-boot, vendor manifest items 12-13, the
vendored include/hmr comments, and install.sh.
Restores the boot-failure guard the rework dropped with raw mode: the
built-bin case now boots `--profile web --patch <invalid>` and asserts the
settled diagnostic and exit 1, so the HMR initial-scan deadlock stays
covered; its orphaned raw fixture is renamed and the unused one deleted.
The superseded personal-config Agent Note and its superseding profile note
are now cross-linked.
A profile manifest and a bundle manifest are different kinds and shared one
flat `dsh` section: `dsh.plugins` listed bundles (not plugins) and `dsh.patch`
declared a bundle's layer. Each kind now names its role — a bundle declares
`dsh.bundle.patch`, a profile declares `dsh.profile.bundles` — so a
package.json states which role it plays and the list name matches its contents.
`DEFAULT_PROFILE_PLUGINS` becomes `DEFAULT_PROFILE_BUNDLES`, and
`DshManifestSection` splits into `DshBundleManifest`/`DshProfileManifest`.
Pre-release: no compatibility shim; turtle-ui moved with it (bd5ff10).
Master stabilized two of the three hand-built markdown fixtures by spacing
their event times, so the stats line's LLM segment stops depending on how fast
the replay ran. `markdown-images` was left on the old shape and kept failing
for exactly that reason — a different test each run, always the same one-line
difference.
Pin it the same way and record the segment its golden now always shows. This
supersedes the normalizer that dropped those segments outright, reverted here:
pinning the fixture keeps a real part of the page in the goldens instead of
hiding it from every one of them, and master's two goldens already record it.
`StatsLine` renders its LLM, tool-call, and throughput segments only while the
matching measurement exceeds zero, and all three are wall clock taken during
the replay. A machine that finishes a step inside one millisecond drops the
segment a slower one keeps, so a golden recorded what the recording machine's
speed was rather than what the page shows. Goldens across this suite already
disagreed about the LLM segment for that reason, and CI failed on whichever
test landed on a slow enough runner — a different test each run, always the
same one-line difference.
Tokenizing the values was never enough, because presence is what moves. The
normalizer now drops those segments outright, each taking one adjacent
separator so nothing is left holding a dangling separator or a doubled space,
and the recorded goldens are normalized the same way. `TTFT avg` stays: it
gates on a step count the fixture determines.
The Models page could name a provider's key and little else. Adding an
OpenAI-compatible gateway meant opening $DSH_HOME/settings.yaml and
knowing the profile shape; correcting a stale context window meant the
same. This layer puts both on the page: a card that declares a route
pi-ai does not ship — id, endpoint, protocol, key, models — and a model
list on the pi-ai editor that can ask the provider what it serves and
adopt the answer.
It follows the DeepSeek catalog editor that landed in #1050 rather than
inventing a second look for the same job. Both editors now share the
section shell and heading, the danger-tinted delete, the add-model
button, the empty state, the per-row validator that names a bad row by
its position, and one K/M capacity vocabulary — 256K and 1M are read and
spelled back, while settings.yaml still stores plain token counts. The
row type is structurally open like that editor's, so a profile field
this card does not edit survives an edit here.
Three of that editor's decisions replaced weaker ones this branch had
made. Inheritance now reads the composition base rather than the
effective value, which would echo an override back the moment a reset
dropped it. Validation names the offending row instead of stating a
blanket problem. And emptying the list is no longer conflated with
handing the catalog back to the adapter — those are separate acts, with
separate affordances.
The create write carries the revision the card opened at, so a route
another tab declared meanwhile is a conflict rather than a silent
overwrite of its profile.
- Clone patch lists per generation (boot + composeLive): the include pushes
insert rows by reference and mutates them in place, so a reused object
baked user overrides into bundle rows and removal could not revert; the
built-bin hot-reload e2e now asserts an override AND its removal reverting.
- The headless runner awaits Loader settlement before prompting (its inject
gate covers only apiProxy/httpServer) and abandons cleanly when the tree
died during the wait.
- healProfilesModuleFallback walks the app's full dependency+peer closure:
out-of-tree plugins import seam packages (dsh-compact, dsh-subprocess, ...)
that only implementations reach, and peers are how seams are declared.
- Profile init writes pnpm-workspace.yaml (nodeLinker: hoisted), not .npmrc
— pnpm >=10 reads settings from the workspace manifest.
- Web dumps reject boot-only flags instead of printing a tree that differs
from the same invocation's boot; --port validates at the flag;
--dump-default-config no longer parses the (possibly broken) user layer;
trustedHosts flag derivation merges over the composed value instead of
replacing it; web-runtime gains surfaceContext (headless disables the GUI
prompt/bash-vars the old -p never mounted); 'node_modules' is a reserved
profile name; plugin-warning names the recovery step; client AGENTS.md
registration surfaces point at the web-app bundle.
- Ship session-reference/tmux-context/tool-ask-user as app dependencies for
terminal front-door patch layers (turtle-ui), same stance as mcp-client.
dsh --profile <name> replaces the fixed entry modes: --config and -p are
removed, --patch adds overlays over the composed profile, a positional task
selects one-shot mode (requires the headless-runner row), and dsh web stays as
the alias for --profile web carrying the Web flag family as patches. dsh
plugin --profile <name> forwards verbatim to pnpm in the profile directory,
initializes on first use, and reconciles the dsh.plugins layer list after
add/remove (patch-less packages warn and stay plain dependencies). Config
dumps and the keyless web e2e scaffold compose the same bundle layers over the
same empty root as the boot.
The token-meter projections now subtract compact/summary's
shadowedTokenCount verbatim, so the seeded-history fixture's hand-picked
10k count drove the message figure negative and killed the projections
baseline. Realize the seed first (realizeSeedFixture, idempotent, shared
with seedSession) and derive the count from the shadowed rows through
the composed meter, reproducing the previous per-node fold bit for bit —
the recorded aria goldens pass unchanged.
The TTFT and tok/s readings divide by measured wall time, so they are not
reproducible: the same replayed scenario yielded 69 and 70 tok/s on
consecutive local runs, and a 3 ms replayed stream reads 26333 tok/s. Baking
those into committed goldens made the Web lane flaky by construction, and the
goldens for the readings themselves were never refreshed.
Three fixes, then a refresh:
The footer's decorative dots are `aria-hidden`, so the readings concatenated
into one accessible string — `Ran for 13sTTFT 0.2s12 tok/s`. That is a real
defect on its own (a reader hears one run-on instead of three facts) and it
also denied `{{duration}}` the word boundary it matches on, so even the
previously-stable `Ran for` duration started leaking raw. The separators now
carry flanking spaces.
`normalizeAria` gains `{{throughput}}` beside `{{duration}}`, and its duration
alternation accepts the stats line's compact `2m42s` as well as the
message-chrome template's `2m 42s` — the compact form had no pattern at all,
which is why `LLM 382m39s` survived the first refresh.
Refreshed 17 goldens. They also record that the stats line's `LLM` group now
renders at all: it folds assistant `timing`, which the live transcript adapter
only began attaching in this branch, so the group was previously dead in Chat.
Verified by running the lane in replay three times after the refresh: 41/41
files green each time, goldens untouched. Before this change two consecutive
runs disagreed on both the values and the failure count.
