`man` and `math` duplicated capabilities already reachable through
`bash`; `plan_agent` is better expressed as a `task_agent` running a
planning skill, and carried a large amount of special-case machinery
(plan-review gate, refinement loop, per-kind model routing). Removing
all three shrinks the tool surface and cuts per-call token cost.
Also removed, as dead-once-the-tools-are-gone:
- the `math` sandbox executor (`turnstone.core.sandbox`) and its
`[sandbox]` extra; the eval analyst now runs bash-only
- the read-only `AGENT_TOOLS` sub-agent tool set and the `agent`
tool-metadata key (`task_agent`/`TASK_AGENT_TOOLS` retained)
- the plan-review protocol end to end: the `on_plan_review` UI hook,
`resolve_plan`, `POST /v1/api/plan` + `POST /v1/api/route/plan`,
the `plan_review`/`plan_resolved` SSE events, and their Python SDK /
TypeScript SDK / OpenAPI / frontend / Discord+Slack bindings
- the `model.plan_alias` / `model.plan_effort` settings and the
registry `plan_model` / `plan_effort` routing fields
TOOLS 31->28, TASK_AGENT_TOOLS 13->11; COORDINATOR_TOOLS unchanged.
BREAKING CHANGE: removes the `man`, `math`, `plan_agent` tools, the
plan-review SSE/HTTP/SDK surface, and the plan_* model-routing settings
from the experimental 1.6 line.
Bundles the click-around polish on the console admin UX.
Home composer + schedule modals
- /v1/api/models now exposes coordinator_default_alias + judge_default_alias,
resolved through the same chain console/session_factory.py uses. Both the
home composer's MODEL / JUDGE MODEL placeholders and the schedule create /
edit modal model placeholders rewrite to "Default — alias (model)" once
the API responds. The `models_changed` SSE refresh keeps placeholders
current as operators edit per-role assignments.
- Composer.setOptionPlaceholder added so callers can update just the first
option's text without disturbing the rest of the choice list.
Admin → Models → Roles
- Channel adapter row added (channels.default_model_alias) — the migration
to the Roles sub-tab missed it. Key added to
_MODEL_AFFECTING_SETTING_KEYS so edits fire the SSE refresh, and to the
settings-tab roleKeys skip-list so it only renders in one place.
- Plan/Task agent rows now display "(inherit)" instead of the misleading
"(default — <alias>)" — those roles cascade through plan_model →
agent_model → session model, not a single concrete default.
- coordinator.reasoning_effort accepts "" (inherit), matching
model.plan_effort / model.task_effort.
- Blank options in each role's MODEL select now match the "alias (model)"
shape used by the other rows.
Toggle-switch component
- New .toggle-switch component (visually-hidden native checkbox + styled
track + label). 40×22 hit target meets WCAG 2.5.5 (AAA), inset ring on
the off state for ≥1.5:1 contrast against the modal surface.
- .toggle-stack groups toggles in a column with .toggle-group-divider for
conceptual grouping (used in the Add Model modal between "Active" and the
paired Reasoning toggles).
- .toggle--flush modifier zeroes the default top margin for toggles that
sit flush against a heading or a dynamically-rendered row.
Sweep — every admin-modal boolean checkbox is now a toggle:
schedule (cs/es-autoapprove, es-enabled), policy (ep/epp-enabled),
tool-mode (ctm/etm-default), skill (csk/esk-auto-approve, csk/esk-enabled),
MCP (mcp-auto-approve, mcp-enabled), Add Model (Active, surface-persisted-
reasoning, replay-reasoning), judge bool settings (cancel_on_approval et
al.), and the user-roles-modal role assignment list. The two
ogp-cred / eogp-cred inline credential checkboxes stay as compact inline
boxes since they sit beside text inputs in tight horizontal rows.
Add Model modal — the "Enabled" toggle promoted to "Active" and moved to
the very top of the form. Tooltip explains it gates dropdown visibility
without removing the definition.
MCP authorization — the three radio buttons replaced with a vertical
.segmented-control option list. Selected row paints --accent-dim plus a
filled .segmented-indicator; focus ring uses --accent so it stays visible
on the currently-selected option.
Role permissions modal — the 19 permission checkboxes are now
.toggle-switch.perm-toggle (monospace lowercase identifiers preserved).
The permissions are split into Scopes / Admin / Workstreams & Tools
sections under caps-styled section headers so the row-flow grid no longer
slices `admin.*` mid-column.
Judge bool toggles use a static "Enabled" caption rather than flipping
text on `.checked`; flipping lagged 50–300 ms behind the slider position
because the caption was sourced from the post-save reload.
CSS cleanup — dead `.admin-checkbox` / `.perm-checkbox` rules removed.
Specificity audit (scripts/css_specificity_audit.py) returns no conflicts
on any new component class.
Tests — 525 pass on the affected slices; new tests/test_console_available_
models.py pins each branch of the resolution chain in /v1/api/models so the
home composer placeholder stays correct as precedence rules evolve.
Three changes from PR review:
- Permission gating: hide the Roles sub-tab button when the user
lacks ``admin.settings``. The sub-tab loads/saves through
``/v1/api/admin/settings``, so an admin with ``admin.models`` but
no ``admin.settings`` would otherwise see a perpetual 403 loader.
When Roles is the active sub-tab and the permission check fails,
snap the panel back to Definitions so the user lands somewhere
usable.
- Drop the redundant ``/v1/api/admin/model-definitions`` fetch from
``loadAdminModelRoles``. Both entry points (initial Models-tab
open + ``models_changed`` SSE refresh) flow through
``loadAdminModels`` first, which already populates ``_modelDefs``
+ ``_modelDefaultAlias``; ``_saveModelRole`` doesn't touch model
definitions, so the cached snapshot stays accurate when the save
chains back here. Halves the per-render request count and
removes a wasted round-trip on every cluster-wide model edit.
- Add ``test_models_changed_event.py`` covering the SSE fanout the
prior commit introduced: each model-definition CRUD endpoint
emits exactly one ``models_changed``, settings PUT/DELETE only
emit for keys in ``_MODEL_AFFECTING_SETTING_KEYS`` (parametrised
over all eight), and unrelated settings (e.g.
``session.retention_days``) don't trigger spurious refreshes.
The expected key set is pinned in the test so a stray addition
to the allowlist doesn't silently bypass coverage.
Patrick Buckley