Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

It means localization will be kept intact.

When CAPI ends a stream with `response.incomplete` or `response.failed`, the parser previously returned undefined and the downstream chatMLFetcher saw zero completions and fell to `ChatFetchResponseType.Unknown` ("Sorry, no response was returned.").

Map terminal events into ChatCompletions with the right FinishedCompletionReason so the existing chatMLFetcher switch handles them:

- response.incomplete + content_filter -> ContentFilter (+ FilterReason from CAPI content_filters labels, e.g. TextCopyright -> Copyright)

- response.incomplete + max_output_tokens -> Length

- response.failed -> ServerError

fix: replace typescript.tsdk.desc with new js/ts.tsdk.path

* agent host: handle elicitation requests from copilot SDK

- Implements the new `onElicitationRequest` hook from the Copilot SDK so that the copilot agent can surface elicitations (free-form, schema, and URL) as session input requests, dispatching the agent's reply back through the SDK once the user responds.
- Renders URL-mode elicitations in the chat UI as a proper `ChatElicitationRequestPart` that opens the URL via `IOpenerService` and dispatches Accept/Decline/Cancel, instead of falling through to the question-carousel fallback which was not designed for URL approvals.
- Adds unit tests covering the new agent-side elicitation flow as well as the workbench-side URL elicitation rendering, opener integration, decline/cancel paths, and external-completion echoes.

Fixes <no issue>

(Commit message generated by Copilot)

* address review feedback for url elicitation handling

- settle() is idempotent without short-circuiting on cancellation
- map server-side SessionInputCompleted to ElicitationState before hide()
- check IOpenerService.open() return value; treat false as Decline
- tighten boolean/number text coercion in elicitationAnswerToFieldValue
- handle free-form (no schema) accept by returning { answer: text }
- add tests covering server-side dismissal (Cancel) and opener=false

…back

Address PR feedback and round out the content-filter mapping:

- Map response.error (string-coded per OpenAI SDK) onto APIErrorResponse so
  it propagates through ChatCompletion.error -> ChatFetchResult.streamError
  and BYOK callers see the underlying server-side reason. The numeric code
  field can't hold OpenAI's string enum, so the string is stashed in
  metadata.code (BYOK JSON.stringify's the whole struct).
- Add protected_material_text / protected_material_code to the structured
  content_filter_results fallback. These are the Azure REST spec's copyright
  detectors; today the wire emits the legacy CAPI 'content_filter_raw' shape
  with action=BLOCK + label=TextCopyright, but the spec'd path is what Azure
  is rolling toward.
- Document the wire-vs-spec distinction on CapiResponseTerminalEvent.
- Type the test's completions array as ChatCompletion[] (avoid any[]).
- Add a regression test asserting response.failed.error propagates.

Plumbs an optional 'resource' field through IAuthenticationService get/createSession options and the authIssuers proposal so MCP authentication can request audience-restricted tokens. mainThreadMcp now forwards authDetails.resourceMetadata.resource into both calls.

In the microsoft-authentication extension, the resource is threaded into MSAL's acquireTokenInteractive, acquireTokenByDeviceCode, and acquireTokenSilent. Bumps @azure/msal-node and @azure/msal-node-extensions to ^5.1.5; adapts to ServerAuthorizationCodeResponse -> AuthorizeResponse and fromNativeBroker -> fromPlatformBroker renames.

Adds tests verifying that getSessions/createSession forward 'resource' to the provider, and that each MSAL flow (default, protocol handler, device code) forwards 'resource' to the underlying MSAL call.

#315886)

Tool search is now always enabled for gpt-5.4/gpt-5.5, matching the
messages API path. Aligns the responses API on the same
endpoint.supportsToolSearch capability flag.

Also registers ToolSearchTool for gpt-5.4/gpt-5.5 and the
claude-opus-4.7 variants so model-specific tool gating actually
matches the supported endpoints.

Responses API: translate terminal events into typed completions

… connect (#315897)

- The tunnel picker flow called `connect()` (which fired `onDidChangeConnections`)
  before `cacheTunnel()` (which fired `onDidChangeTunnels` and created the
  provider). The wire-up handler therefore ran with no provider, so the new
  connection was never bound and `listSessions` was never issued — tunnel
  sessions only appeared after the user started a new session on the tunnel.
- Move `cacheTunnel()` inside `connect()` (desktop + web) so the cache → provider
  creation → `addManagedConnection` → wire-up ordering is invariant regardless
  of caller, removing the need for defensive re-wiring in the contribution.
- Drop the now-redundant explicit `cacheTunnel` call from the picker action and
  the trailing `_onDidChangeTunnels.fire()` from both service impls (cacheTunnel
  already fires it).
- Add a regression test that asserts a freshly-cached tunnel binds to a
  subsequent live connection through the standard wire-up path.

Fixes #315059

(Commit message generated by Copilot)

* Improve "Export agent host logs" action

* fix

* chat: show agent host model pricing in turn details

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: show agent host response credits

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: include agent host live usage details

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: handle late agent host usage

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: read agent host usage cost

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: persist agent host usage details

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chat: remove agent host usage persistence

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* agentHost: test usage metadata

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Clicking a remote host row in the Remote tab of the session workspace
picker no longer opened the per-remote options popup (Reconnect /
Remove / Copy connection string / Open settings / Show output).

The remote rows are built with an inline `run` callback that invokes
`_showRemoteHostOptionsDelayed`. A recent refactor extracted dispatch
into a shared `_dispatchPickerItem` so the mobile sheet could reuse
it, but the desktop `_buildDelegate.onSelect` was rewritten inline
and dropped the `item.run` branch. Clicks fell through to
`commandService.executeCommand` with a synthetic id that isn't a
registered command, so nothing happened.

Wire the desktop `onSelect` to `_dispatchPickerItem` so both
presentations share the single source of truth.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>