The fifteen files under `src/components/agents/` (including `skills/`)
and `src/components/skills/`. 15/15 erase byte-identically; bundle hash
unchanged.
Renaming raised 43 errors and 29 of them came from one thing: these
files carry 24 `/** @param {any} props */` annotations, one per
component, and JSDoc stops applying at the extension boundary. Without
them TypeScript infers every destructured prop as required, so a call
site passing seven of nine props is an error — which is how a file that
declared its props `any` ended up with fourteen complaints about missing
`className`. Restoring the author's own declaration as `: any` is not
blanket typing; it is the annotation that was already there, in the only
form that still works.
`Workspace` in `AgentCanvas` was the one component in that file its
author left without the hatch. It now matches its siblings.
The rest were five separate things:
- `React.isValidElement(children)` no longer narrows enough to read
`children.props.id`: React 19 types `ReactElement`'s props as
`unknown`. `isValidElement<any>` says what the `cloneElement` call
beneath it has always assumed. The migration plan predicted this
site by name.
- `useSkillSections(page, placement)` is called with one argument by
`UiEditingProvider`, which its doc comment explicitly permits —
"called with no placement it returns every section on the page". The
parameter simply lacked its optional marker. The marker erases, so
the emitted signature is unchanged.
- `new Date(b.at) - new Date(a.at)` is valueOf coercion, which
JavaScript performs and TypeScript refuses to describe. Cast rather
than rewritten to `.getTime()`: that would change the emitted code,
and this comparison orders the list.
- `Object.values<any>` on a tally, the same inference gap as earlier
batches, which also fixed a `ReactNode` complaint downstream of it.
All fifteen are linted under their new extensions, checked by name.
Measured against `446df7b`:
typecheck 6 errors, down from 9; no new error anywhere
lint exit 0, 0 errors, 289 warnings, 15/15 linted by name
npm test 1684/1691, the same 7 failures verbatim
build exit 0, identical bundle hash 74d17e2d…
type erasure 72/72 byte-identical across Phase 11 so far
No baseline artifact touched.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HBG1wnuRfJKCstGB8Fekr8
The key had two incompatible meanings running at once. CLAUDE.md §3 defines
subagents as "keys of other specs this may DELEGATE to" and §6 as a tool call
from the parent's perspective — the subagent runs its own turn, as the same
caller, out of the parent's budget, and returns an answer. The backend
implements exactly that.
This side did something else: agentSkillIds folded one level of subagent skills
into the parent's carried set, so a parent silently gained everything its
subagents carried, and the UI described it that way — "other agents whose
skills this one may also use", "borrowing them cannot reach data this page does
not hold".
Both are defensible readings. Only one is the specification, and running both
meant krow-workforce-agent carried eight delegation tools AND the flattened
skills of those same eight agents — able to answer a question directly or to
ask an agent that had already lent it the means to answer. Two ways to do one
thing, differing in cost and in what the trajectory records.
So an agent carries what it declares. Reaching another agent is delegation,
which the runtime does with its own budget and its own trajectory.
The blast radius was one check, which is the useful part of the answer: only
"a subagent cycle terminates" depended on the folding, because that traversal
was the only thing that could loop. Nothing walks subagents here now, so the
cycle question moved to where it belongs — refused at publish by
definition.FindSubagentCycle, bounded at run time by the depth cap. The
replacement checks assert the new meaning rather than deleting the old ones,
because the previous behaviour reads as perfectly reasonable and will be
reinvented otherwise.
The `agents` parameter stays on agentSkillIds and is no longer read. Removing
it is a wider edit for no behavioural gain, and agentScopedDisabledWith exists
precisely to pass it.
924/924 checks pass; production build clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g
TWO fixes, both found by using the product rather than reading it.
A question asked on a page that cannot answer it was lost. resolveIntent routes
to the page that can, and routing.js answered "That is on Candidates. Taking
you there now. Ask again once the page loads." — but the panel is page-scoped,
so it re-mounts on the new route and the navigation destroys the very message
explaining why the reader moved. What the reader saw was a different page and a
fresh greeting, with no trace of what they asked.
The question now travels with the destination. AssistantPanelContext sits ABOVE
the router and already has `ask` for exactly this — a page handing a question to
the panel — so the panel that mounts on the other side asks it. That is what
the reader wanted, and what "ask again once the page loads" was apologising for.
It cannot loop: resolveIntent only routes when the destination differs from the
page you are on, and answerableHere short-circuits before that.
The Test tab did not test. "Simulation & Scope Diagnostics" reads where a
question WOULD route — which skills are reachable, which tools are in scope,
what the classifier makes of it — and never calls the model. That is genuinely
useful and it is not what a tab called Test leads anyone to expect. A real test
did exist, but under Skills, as "Test in Owliver" on a capability card.
So the Simulated User Query the tab has always shown is now runnable, through
the same path that card uses: the existing Owliver panel, scoped to the draft's
own agent and disabled skills, so the answer comes from the agent being edited
rather than the published one. The diagnostics stay — they answer a different
and still useful question. The button is disabled when the agent does not cover
the selected page, with the reason in its title, rather than offering a run that
would decline.
924/924 checks pass and the production build is clean.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PJvibeSc1JYXjatankqM1g
