fix(tui): address CodeRabbit review on the theme catalog

- CHANGELOG: reconcile the --theme bullet with the named themes (was still
  documenting {auto|dark|light}).
- /theme usage string advertises the list and auto forms (/theme list is still
  accepted) so /help matches the command surface.
- Theme-persistence test parses the written config and asserts preferences.theme
  directly instead of a raw substring, so a wrong-key regression fails.

.github/workflows/release-artifacts.yml

@@ -54,10 +54,8 @@ jobs:
       # is published under the pushed git tag. If they disagree, install.sh/install.ps1
       # and the npm postinstall all build a download URL that 404s. Fail fast so a
       # forgotten version bump can never publish mis-versioned, un-installable assets.
-      # Matches on the ref (not event_name) because release-please dispatches this
-      # workflow at the tag ref — its GITHUB_TOKEN-created tag cannot fire `push`.
       - name: Check tag matches package.json version
-        if: ${{ startsWith(github.ref, 'refs/tags/v') }}
+        if: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
         shell: bash
         run: |
           pkg_version="$(node -p "require('./package.json').version")"
@@ -80,15 +78,13 @@ jobs:
           path: dist/release/*
           if-no-files-found: error
 
-      # On a `v*` tag ref (pushed manually, or dispatched at the tag by the
-      # release-please workflow), publish the packaged archive + .sha256 as GitHub
-      # Release assets so the documented `scripts/install.sh` / `install.ps1` path
-      # (which reads /releases/latest) works. Uses the preinstalled `gh` (no new
-      # action dependency); each matrix OS creates the release if absent
-      # (best-effort — release-please normally creates it first) then uploads its
-      # own assets with --clobber. Tags come from merging the release-please PR.
+      # On a `v*` tag push, publish the packaged archive + .sha256 as GitHub Release
+      # assets so the documented `scripts/install.sh` / `install.ps1` path (which reads
+      # /releases/latest) works. Uses the preinstalled `gh` (no new action dependency);
+      # each matrix OS creates the release if absent (best-effort) then uploads its own
+      # assets with --clobber. NOTE: maintainers must push the tag — this never tags.
       - name: Publish to GitHub Release
-        if: ${{ startsWith(github.ref, 'refs/tags/v') }}
+        if: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
         shell: bash
         env:
           GH_TOKEN: ${{ github.token }}
@@ -96,83 +92,3 @@ jobs:
           tag="${GITHUB_REF_NAME}"
           gh release create "$tag" --repo "$GITHUB_REPOSITORY" --title "$tag" --generate-notes 2>/dev/null || true
           gh release upload "$tag" dist/release/* --repo "$GITHUB_REPOSITORY" --clobber
-
-  # Publishes the npm wrapper (@gitlawb/zero) once every platform's release
-  # assets are live — the package's postinstall downloads its binary from the
-  # GitHub Release, so publishing before the assets exist would ship a package
-  # that fails to install.
-  #
-  # Auth is npm OIDC trusted publishing: no NPM_TOKEN secret. The package's
-  # npmjs.com settings must list this repo + workflow file as a trusted
-  # publisher, and provenance is then generated automatically. Note npm only
-  # allows configuring a trusted publisher on an EXISTING package, so the very
-  # first @gitlawb/zero publish is a one-time manual `npm publish` bootstrap.
-  publish-npm:
-    name: Publish npm package
-    needs: package
-    if: ${{ startsWith(github.ref, 'refs/tags/v') }}
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      id-token: write # OIDC token exchange for npm trusted publishing + provenance
-    steps:
-      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
-
-      # No registry-url here on purpose: setup-node's registry-url writes an
-      # .npmrc line referencing $NODE_AUTH_TOKEN, and npm hard-fails on the
-      # unset env var. Trusted publishing needs no token at all.
-      - name: Setup Node
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
-        with:
-          node-version: 24
-
-      # OIDC trusted publishing needs npm >= 11.5.1. Use the npm bundled with
-      # the pinned Node toolchain (Node 24 ships >= 11.5.1) rather than pulling
-      # npm@latest from the registry inside the publish path — an unpinned
-      # install there would be avoidable supply-chain exposure. Fail fast if a
-      # future runner/toolchain change ever regresses the bundled npm.
-      - name: Check npm supports trusted publishing
-        run: |
-          npm --version | node -e '
-            const version = require("fs").readFileSync(0, "utf8").trim();
-            const [major, minor, patch] = version.split(".").map(Number);
-            const ok =
-              major > 11 ||
-              (major === 11 && (minor > 5 || (minor === 5 && patch >= 1)));
-            if (!ok) {
-              console.error(
-                `::error::bundled npm ${version} is too old for OIDC trusted ` +
-                  `publishing (needs >= 11.5.1) — bump node-version in this job.`,
-              );
-              process.exit(1);
-            }
-            console.log(`npm ${version} supports trusted publishing.`);
-          '
-
-      # Probe the exact URLs postinstall will build (internal/release/release.go
-      # asset-name scheme) as an anonymous client. This also blocks publishing
-      # while the repo is still private — private release assets 404 without
-      # auth, exactly as they would for an installing user.
-      - name: Verify release assets are downloadable
-        shell: bash
-        run: |
-          version="$(node -p "require('./package.json').version")"
-          base="https://github.com/${GITHUB_REPOSITORY}/releases/download/v${version}"
-          for asset in \
-            "zero-v${version}-linux-x64.tar.gz" \
-            "zero-v${version}-linux-arm64.tar.gz" \
-            "zero-v${version}-macos-x64.tar.gz" \
-            "zero-v${version}-macos-arm64.tar.gz" \
-            "zero-v${version}-windows-x64.zip"; do
-            for url in "${base}/${asset}" "${base}/${asset}.sha256"; do
-              if ! curl -fsSLI -o /dev/null "$url"; then
-                echo "::error::${url} is not publicly downloadable — npm postinstall would fail. Is the repo public and are all assets uploaded?" >&2
-                exit 1
-              fi
-            done
-          done
-          echo "all release assets for v${version} are publicly downloadable."
-
-      - name: Publish to npm
-        run: npm publish --access public

.github/workflows/release-please.yml

@@ -1,35 +0,0 @@
-name: Release Please
-
-on:
-  push:
-    branches:
-      - main
-
-permissions:
-  contents: write # push the release-PR branch, create the tag + GitHub Release
-  pull-requests: write # open/update the release PR
-  issues: write # create/apply release-tracking labels on the release PR
-  actions: write # dispatch release-artifacts.yml once a release is cut
-
-jobs:
-  release-please:
-    name: Release PR / tag
-    runs-on: ubuntu-latest
-    steps:
-      - name: Run release-please
-        id: release
-        uses: googleapis/release-please-action@a02a34c4d625f9be7cb89156071d8567266a2445 # v4.2.0
-
-      # Tags created with the default GITHUB_TOKEN never fire `on: push: tags`
-      # workflows (GitHub suppresses workflows triggered by workflow-created
-      # events), so release-artifacts.yml would not run for a release-please
-      # tag. workflow_dispatch invoked through the API is exempt from that
-      # suppression — dispatch the artifacts build at the new tag explicitly.
-      - name: Build and publish release artifacts
-        if: ${{ steps.release.outputs.release_created }}
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: |
-          gh workflow run release-artifacts.yml \
-            --repo "$GITHUB_REPOSITORY" \
-            --ref "${{ steps.release.outputs.tag_name }}"

.release-please-manifest.json

@@ -1 +0,0 @@
-{}

internal/agent/loop.go

@@ -210,29 +210,27 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			}
 		}
 
-		// forwardedVisibleText flags forwarded final PROSE (OnText) specifically —
-		// the only output whose re-stream on a stall retry would visibly DUPLICATE
-		// answer text the user already read. Transient working indicators
-		// (reasoning previews, tool-call "writing…" previews) are deliberately NOT
-		// counted: a turn that streamed only those then stalled — the common
-		// gpt-5.x / ollama "froze mid-write_file" case — is safe to re-issue, since
-		// the TUI resets the tool-call preview on the next tool-call-start and a
-		// stalled turn is never appended to `messages` (it returns on the error
-		// before the append), so the retry re-sends clean context with no
-		// conversation-state duplication.
-		forwardedVisibleText := false
+		// Wrapped callbacks flag ANY output forwarded this turn, so a stall retry
+		// never re-streams on top of output the user already saw — even across the
+		// reactive-compaction retry below, which overwrites `collected`.
+		forwardedAnything := false
+		mark := func() { forwardedAnything = true }
+		// OnUsage is telemetry, not visible output, so it does NOT mark
+		// forwardedAnything: a provider that emits an early usage event (e.g. prompt
+		// tokens) then stalls with no content must still be safely retried. The gate
+		// only guards against re-streaming output the user actually SAW.
 		forwardingOpts := zeroruntime.CollectOptions{OnUsage: options.OnUsage}
 		if options.OnText != nil {
-			forwardingOpts.OnText = func(s string) { forwardedVisibleText = true; options.OnText(s) }
+			forwardingOpts.OnText = func(s string) { mark(); options.OnText(s) }
 		}
 		if options.OnReasoning != nil {
-			forwardingOpts.OnReasoning = func(s string) { options.OnReasoning(s) }
+			forwardingOpts.OnReasoning = func(s string) { mark(); options.OnReasoning(s) }
 		}
 		if options.OnToolCallStart != nil {
-			forwardingOpts.OnToolCallStart = func(id, name string) { options.OnToolCallStart(id, name) }
+			forwardingOpts.OnToolCallStart = func(id, name string) { mark(); options.OnToolCallStart(id, name) }
 		}
 		if options.OnToolCallDelta != nil {
-			forwardingOpts.OnToolCallDelta = func(id, fragment string) { options.OnToolCallDelta(id, fragment) }
+			forwardingOpts.OnToolCallDelta = func(id, fragment string) { mark(); options.OnToolCallDelta(id, fragment) }
 		}
 		// recoverStreamError applies the same non-stall recovery the initial stream
 		// gets to ANY collected error — including one from a reissued (stall-retry)
@@ -286,28 +284,15 @@ func Run(ctx context.Context, prompt string, provider Provider, options Options)
 			result.Messages = copyMessages(messages)
 			return result, ctx.Err()
 		}
-		// A stream idle/stall timeout is safely re-issued when the turn committed NO
-		// answer text — no forwarded visible prose (forwardedVisibleText) and no
-		// collected final text (collected.Text). This covers two cases:
-		//   1. Nothing streamed at all before the connection died (the original
-		//      macOS stale-pooled-connection hang past the response-header timeout).
-		//   2. The model streamed transient reasoning and began a tool call (e.g. a
-		//      large write_file) then froze mid-arguments — the common gpt-5.x /
-		//      ollama heartbeat-pause stall. That partial tool call is NEVER executed
-		//      (a turn with collected.Error returns before dispatch below) and NEVER
-		//      appended to `messages`, so a retry re-issues clean context; the only
-		//      re-render is transient previews, not duplicated answer text. This is
-		//      why the gate no longer excludes collected.ToolCalls: an incomplete
-		//      tool call from a timed-out stream is discard-and-retry, not output.
-		// A turn that forwarded real prose is NOT retried (it would duplicate visible
-		// answer text) and falls through to the error return below. Capped +
-		// exponential backoff, with a user-visible notice per attempt.
+		// A stream idle/stall timeout with NO output forwarded yet this turn can be
+		// safely re-issued on a fresh connection — nothing was shown, so there's no
+		// duplication (this recovers the macOS stale-pooled-connection hang when it
+		// slips past the transport's response-header timeout). A turn that already
+		// streamed partial text/tool-calls is NOT retried (it would duplicate) and
+		// falls through to the error return below. Capped + exponential backoff.
 		for attempt := 1; attempt <= maxStreamStallRetries &&
-			isStreamTimeoutError(collected.Error) && !forwardedVisibleText &&
-			collected.Text == ""; attempt++ {
-			if notify := stallRetryNoticeFor(options); notify != nil {
-				notify(attempt, maxStreamStallRetries)
-			}
+			isStreamTimeoutError(collected.Error) && !forwardedAnything &&
+			collected.Text == "" && len(collected.ToolCalls) == 0; attempt++ {
 			if err := sleepWithContext(ctx, backoffFor(attempt)); err != nil {
 				result.Messages = copyMessages(messages)
 				return result, err

internal/agent/reconnect.go

@@ -40,21 +40,6 @@ func reconnectNoticeFor(options Options) reconnectNotifier {
 	}
 }
 
-// stallRetryNoticeFor builds a notifier for the loop's content-stall retry (a
-// stream that connected and produced only transient output, then went silent).
-// Distinct wording from reconnectNoticeFor's "connection lost" because the
-// connection was fine — the model stalled. Surfaced through OnReasoning, the
-// non-content channel, so it never folds into the answer text. Nil when there
-// is no reasoning sink (the retry still happens silently).
-func stallRetryNoticeFor(options Options) reconnectNotifier {
-	if options.OnReasoning == nil {
-		return nil
-	}
-	return func(attempt, max int) {
-		options.OnReasoning(fmt.Sprintf("\n[no output — model stalled; retrying %d/%d…]\n", attempt, max))
-	}
-}
-
 // streamWithReconnect issues request via provider.StreamCompletion and, on a
 // transient disconnect error, retries the connect up to maxStreamReconnects
 // times with exponential backoff. It returns the live stream on success, or the

internal/agent/stall_retry_test.go

@@ -10,25 +10,19 @@ import (
 )
 
 // stallProvider connects successfully (HTTP 200) but the stream emits a stall/idle
-// timeout error for the first stallBefore calls, then succeeds with "done". The
-// pre-stall emission simulates different partial-output shapes:
-//   - partialText: forwarded PROSE (StreamEventText) — must NOT be retried
-//     (re-issuing would duplicate visible answer text).
-//   - reasoningText: transient reasoning preview — IS retried.
-//   - partialToolCall: a tool call started (+ arg delta) but never ended, the
-//     "froze mid-write_file" case — IS retried (the incomplete call is never
-//     executed or committed).
+// timeout error for the first stallBefore calls, then succeeds with "done". When
+// partialText is set it emits that text BEFORE the stall, simulating a stall after
+// partial output (which must NOT be retried — re-issuing would duplicate it).
 type stallProvider struct {
-	calls           int32
-	stallBefore     int32
-	partialText     string
-	reasoningText   string
-	partialToolCall string
+	calls         int32
+	stallBefore   int32
+	partialText   string
+	reasoningText string
 }
 
 func (p *stallProvider) StreamCompletion(_ context.Context, _ zeroruntime.CompletionRequest) (<-chan zeroruntime.StreamEvent, error) {
 	n := atomic.AddInt32(&p.calls, 1)
-	ch := make(chan zeroruntime.StreamEvent, 5)
+	ch := make(chan zeroruntime.StreamEvent, 3)
 	if n <= p.stallBefore {
 		if p.partialText != "" {
 			ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventText, Content: p.partialText}
@@ -36,16 +30,9 @@ func (p *stallProvider) StreamCompletion(_ context.Context, _ zeroruntime.Comple
 		if p.reasoningText != "" {
 			ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventReasoning, Content: p.reasoningText}
 		}
-		if p.partialToolCall != "" {
-			// A tool call that starts and streams a partial argument fragment but
-			// never gets StreamEventToolCallEnd, then the stream errors — exactly
-			// the gpt-5.x "began the big write_file then froze" shape.
-			ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallStart, ToolCallID: "tc_1", ToolName: p.partialToolCall}
-			ch <- zeroruntime.StreamEvent{Type: zeroruntime.StreamEventToolCallDelta, ToolCallID: "tc_1", ArgumentsFragment: `{"path":"x.html","content":"<!doctype`}
-		}
 		ch <- zeroruntime.StreamEvent{
 			Type:  zeroruntime.StreamEventError,
-			Error: "provider stream error: no output for 6m (the model produced nothing)",
+			Error: "provider stream error: no output for 10m (the model produced nothing)",
 		}
 		close(ch)
 		return ch, nil
@@ -85,54 +72,21 @@ func TestRunDoesNotRetryStallAfterPartialOutput(t *testing.T) {
 	}
 }
 
-// A stall after only transient REASONING was forwarded (no prose text, no
-// completed tool call) IS retried: reasoning is a "thinking" preview, not
-// committed answer text, so re-streaming it on a clearly-signalled retry is
-// acceptable and recovers the common "reasoned then froze" stall. Only
-// forwarded final prose (OnText) blocks the retry (collected.Text is empty
-// here, so this exercises the transient-vs-prose gate specifically).
-func TestRunRetriesStallAfterOnlyReasoning(t *testing.T) {
+// A stall after only REASONING was forwarded (no text/tool-calls) must NOT be
+// retried: the user already saw the reasoning, so re-issuing with callbacks
+// re-enabled would duplicate it. collected.Text is empty here, so this exercises
+// the turn-level forwarded-output gate specifically, not the text check.
+func TestRunDoesNotRetryStallAfterForwardedReasoning(t *testing.T) {
 	p := &stallProvider{stallBefore: 1, reasoningText: "thinking hard"}
-	result, err := Run(context.Background(), "go", p, Options{
+	_, err := Run(context.Background(), "go", p, Options{
 		Registry:    tools.NewRegistry(),
 		OnReasoning: func(string) {},
 	})
-	if err != nil {
-		t.Fatalf("a stall after only reasoning should retry to success, got %v", err)
+	if err == nil {
+		t.Fatal("a stall after forwarded reasoning must NOT be retried; want an error")
 	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("final answer = %q, want %q", result.FinalAnswer, "done")
-	}
-	if got := atomic.LoadInt32(&p.calls); got != 2 {
-		t.Fatalf("want 2 calls (1 stall + 1 retry), got %d", got)
-	}
-}
-
-// A stall mid-way through an INCOMPLETE tool call (started + partial args, never
-// ended) IS retried — the exact gpt-5.x / ollama "began the big write_file then
-// froze" case. The incomplete call is never executed (a turn returns on the
-// stall error before dispatch) and never committed to history, so re-issuing is
-// safe and recovers to success. This is the primary scenario this change fixes.
-func TestRunRetriesStallAfterIncompleteToolCall(t *testing.T) {
-	starts := 0
-	p := &stallProvider{stallBefore: 1, reasoningText: "planning", partialToolCall: "write_file"}
-	result, err := Run(context.Background(), "go", p, Options{
-		Registry:        tools.NewRegistry(),
-		OnReasoning:     func(string) {},
-		OnToolCallStart: func(string, string) { starts++ },
-		OnToolCallDelta: func(string, string) {},
-	})
-	if err != nil {
-		t.Fatalf("a stall mid-incomplete-tool-call should retry to success, got %v", err)
-	}
-	if result.FinalAnswer != "done" {
-		t.Fatalf("final answer = %q, want %q", result.FinalAnswer, "done")
-	}
-	if got := atomic.LoadInt32(&p.calls); got != 2 {
-		t.Fatalf("want 2 calls (1 stall + 1 retry), got %d", got)
-	}
-	if starts != 1 {
-		t.Fatalf("the incomplete tool call should have been forwarded once before the stall, got %d starts", starts)
+	if got := atomic.LoadInt32(&p.calls); got != 1 {
+		t.Fatalf("reasoning-then-stall must not retry, got %d calls", got)
 	}
 }
 

internal/agenteval/benchmark_test.go

@@ -455,15 +455,11 @@ func TestHarnessTimeoutCancelsBlockedAgent(t *testing.T) {
 
 	// The timeout is longer than materialization of the small fixture even on
 	// slower Windows CI runners, so the agent is reached before it blocks until
-	// the deadline fires. 10s wasn't generous enough in practice — it failed
-	// on an otherwise-unrelated PR merge (materialization alone consumed the
-	// full budget on a contended Windows runner, so the agent was never
-	// reached); widened for headroom, since the assertions below still bound
-	// worst-case test time via that same deadline, not this constant.
+	// the deadline fires.
 	report := harness.Run(context.Background(), suitePath, suite, BenchmarkInput{
 		TaskID:   "document-stream-json-verify-events",
 		WorkRoot: t.TempDir(),
-		Timeout:  30 * time.Second,
+		Timeout:  10 * time.Second,
 	})
 
 	if !agentReached {

internal/cli/auth.go

@@ -283,9 +283,6 @@ func newAuthManager(deps appDeps, out io.Writer) (*oauth.Manager, error) {
 		// carries no token material. A real browser launch is intentionally not
 		// performed (the sandbox/headless contexts make printing the safer default).
 		OpenBrowser: func(string) error { return nil },
-		// `zero auth login <preset>` (e.g. xai) should resolve the baked-in preset
-		// without the operator exporting ZERO_OAUTH_ALLOW_PRESETS first.
-		AllowPresets: true,
 	})
 }
 

internal/cli/oauth_provider.go

@@ -43,9 +43,6 @@ func oauthResolverForProfile(profile config.ProviderProfile) providerio.TokenRes
 	manager, err := oauth.NewManager(oauth.ManagerOptions{
 		Store:      store,
 		HTTPClient: &http.Client{Timeout: 30 * time.Second},
-		// Refreshing a token the user logged into (possibly a preset provider like
-		// xAI) re-resolves that provider's OAuth config, which needs the preset.
-		AllowPresets: true,
 	})
 	if err != nil {
 		return nil

internal/oauth/manager.go

@@ -44,17 +44,10 @@ type Manager struct {
 
 // ManagerOptions configures a Manager.
 type ManagerOptions struct {
-	Store      *Store
-	Registry   *Registry
-	HTTPClient *http.Client
-	Env        map[string]string
-	// AllowPresets opts this manager into the baked-in OAuth presets without the
-	// operator exporting ZERO_OAUTH_ALLOW_PRESETS — used by the interactive wizard
-	// and CLI login (and the runtime token refresh) for a provider the user chose
-	// to sign into, whose preset client identity is public (e.g. xAI). It layers the
-	// flag onto Env (or the process environment when Env is nil), preserving any
-	// ZERO_OAUTH_<NAME>_* overrides. Leave false for hermetic tests.
-	AllowPresets  bool
+	Store         *Store
+	Registry      *Registry
+	HTTPClient    *http.Client
+	Env           map[string]string
 	Now           func() time.Time
 	RefreshBuffer time.Duration
 	Out           io.Writer
@@ -90,13 +83,9 @@ func NewManager(opts ManagerOptions) (*Manager, error) {
 	if open == nil {
 		open = func(string) error { return nil }
 	}
-	env := opts.Env
-	if opts.AllowPresets {
-		env = envWithPresetsAllowed(env)
-	}
 	return &Manager{
 		store: opts.Store, registry: registry, client: client,
-		env: env, now: now, buffer: buffer, out: out, openBrowser: open,
+		env: opts.Env, now: now, buffer: buffer, out: out, openBrowser: open,
 	}, nil
 }
 

internal/oauth/manager_test.go

@@ -52,30 +52,6 @@ func managerFor(t *testing.T, env map[string]string, openBrowser func(string) er
 	return m
 }
 
-// AllowPresets layers the opt-in onto the manager's env so a login/refresh for a
-// preset provider resolves; without it (and no Env) the env stays nil so callers
-// and tests remain hermetic.
-func TestNewManagerAllowPresetsForcesOptIn(t *testing.T) {
-	store, err := NewStore(StoreOptions{FilePath: filepath.Join(t.TempDir(), "tok.json")})
-	if err != nil {
-		t.Fatalf("NewStore: %v", err)
-	}
-	m, err := NewManager(ManagerOptions{Store: store, AllowPresets: true})
-	if err != nil {
-		t.Fatalf("NewManager: %v", err)
-	}
-	if m.env["ZERO_OAUTH_ALLOW_PRESETS"] != "1" {
-		t.Fatalf("AllowPresets should force the opt-in; got env[%q]=%q", "ZERO_OAUTH_ALLOW_PRESETS", m.env["ZERO_OAUTH_ALLOW_PRESETS"])
-	}
-	m2, err := NewManager(ManagerOptions{Store: store})
-	if err != nil {
-		t.Fatalf("NewManager: %v", err)
-	}
-	if m2.env != nil {
-		t.Fatalf("env should stay nil without AllowPresets, got %v", m2.env)
-	}
-}
-
 func TestManagerLoginLoopback(t *testing.T) {
 	fp := newFakeProvider(t, `{"access_token":"at","refresh_token":"rt","token_type":"Bearer","expires_in":3600}`)
 	env := map[string]string{

internal/oauth/presets.go

@@ -1,33 +1,6 @@
 package oauth
 
-import (
-	"os"
-	"strings"
-)
-
-// envWithPresetsAllowed returns an env map that opts into the baked-in presets
-// (as if ZERO_OAUTH_ALLOW_PRESETS=1 were exported) so an interactive wizard/CLI
-// login for a well-known public client (e.g. xAI) can use the preset without the
-// operator setting the flag themselves. It copies base — or snapshots the process
-// environment when base is nil — because envValue treats a non-nil map as hermetic
-// (a missing key does NOT fall back to os.Getenv), so a partial map would silently
-// drop the operator's ZERO_OAUTH_<NAME>_* overrides. The flag is then forced on.
-func envWithPresetsAllowed(base map[string]string) map[string]string {
-	env := make(map[string]string, len(base)+1)
-	if base == nil {
-		for _, kv := range os.Environ() {
-			if eq := strings.IndexByte(kv, '='); eq > 0 {
-				env[kv[:eq]] = kv[eq+1:]
-			}
-		}
-	} else {
-		for k, v := range base {
-			env[k] = v
-		}
-	}
-	env["ZERO_OAUTH_ALLOW_PRESETS"] = "1"
-	return env
-}
+import "strings"
 
 // providerPreset is a baked-in default OAuth configuration for a well-known
 // provider. Every field is overridable per provider via ZERO_OAUTH_<NAME>_*

internal/oauth/presets_test.go

@@ -46,46 +46,6 @@ func TestResolveConfigUsesXAIPreset(t *testing.T) {
 	}
 }
 
-// envWithPresetsAllowed lets a caller (the wizard / CLI login / runtime refresh)
-// opt into the preset without exporting ZERO_OAUTH_ALLOW_PRESETS: an otherwise-inert
-// xAI config now resolves from the baked-in preset.
-func TestEnvWithPresetsAllowedEnablesPreset(t *testing.T) {
-	r := NewRegistry()
-	// Baseline: a hermetic empty map keeps the preset inert.
-	if _, _, err := r.ResolveConfig("xai", map[string]string{}); err == nil {
-		t.Fatal("xai should not resolve without the opt-in")
-	}
-	// The helper forces the opt-in so the preset resolves.
-	cfg, _, err := r.ResolveConfig("xai", envWithPresetsAllowed(map[string]string{}))
-	if err != nil {
-		t.Fatalf("envWithPresetsAllowed should enable the xai preset: %v", err)
-	}
-	if cfg.ClientID != "b1a00492-073a-47ea-816f-4c329264a828" {
-		t.Fatalf("client_id = %q", cfg.ClientID)
-	}
-}
-
-// The helper copies the base map (never mutating it) and keeps ZERO_OAUTH_<NAME>_*
-// overrides — critical because envValue treats a non-nil map as hermetic, so a
-// partial map would silently drop them.
-func TestEnvWithPresetsAllowedPreservesOverrides(t *testing.T) {
-	base := map[string]string{"ZERO_OAUTH_XAI_CLIENT_ID": "custom-id"}
-	env := envWithPresetsAllowed(base)
-	if env["ZERO_OAUTH_ALLOW_PRESETS"] != "1" {
-		t.Fatalf("opt-in flag not set: %v", env)
-	}
-	if _, mutated := base["ZERO_OAUTH_ALLOW_PRESETS"]; mutated {
-		t.Fatal("envWithPresetsAllowed mutated the caller's base map")
-	}
-	cfg, _, err := NewRegistry().ResolveConfig("xai", env)
-	if err != nil {
-		t.Fatalf("ResolveConfig with override env: %v", err)
-	}
-	if cfg.ClientID != "custom-id" {
-		t.Fatalf("override dropped through the helper: client_id = %q", cfg.ClientID)
-	}
-}
-
 func TestResolveConfigEnvOverridesPreset(t *testing.T) {
 	r := NewRegistry()
 	env := map[string]string{

internal/providermodeldiscovery/discovery.go

@@ -85,104 +85,6 @@ func Discover(ctx context.Context, profile config.ProviderProfile, options Optio
 	}
 }
 
-// DiscoverOllamaContextWindow asks a local Ollama daemon for a model's context
-// length via its native /api/show endpoint. The generic /v1/models probe
-// (parseModelsResponse) only ever returns id/description — OpenAI-compatible
-// listings don't carry context-window metadata, and a custom/local model tag
-// (e.g. a user's own Ollama pull, including a ":cloud"-tagged model proxied
-// through the local daemon) has no curated-catalog entry to borrow one from
-// either, so modelContextWindow has nothing to show for it without this. Only
-// meaningful for the local Ollama provider (baseURL like
-// http://localhost:11434/v1) — Ollama Cloud's hosted API is a different
-// service and isn't assumed to expose the same endpoint.
-func DiscoverOllamaContextWindow(ctx context.Context, baseURL string, model string, options Options) (int, error) {
-	model = strings.TrimSpace(model)
-	if model == "" {
-		return 0, fmt.Errorf("model name is required")
-	}
-	endpoint, err := ollamaShowEndpoint(baseURL)
-	if err != nil {
-		return 0, err
-	}
-	payload, err := json.Marshal(struct {
-		Model string `json:"model"`
-	}{Model: model})
-	if err != nil {
-		return 0, err
-	}
-	request, err := http.NewRequestWithContext(ctx, http.MethodPost, endpoint, strings.NewReader(string(payload)))
-	if err != nil {
-		return 0, err
-	}
-	request.Header.Set("Content-Type", "application/json")
-	request.Header.Set("Accept", "application/json")
-
-	client := options.HTTPClient
-	if client == nil {
-		client = &http.Client{Timeout: 10 * time.Second}
-	}
-	response, err := client.Do(request)
-	if err != nil {
-		return 0, err
-	}
-	defer response.Body.Close()
-
-	body, err := io.ReadAll(io.LimitReader(response.Body, 1<<20))
-	if err != nil {
-		return 0, err
-	}
-	if response.StatusCode < 200 || response.StatusCode >= 300 {
-		return 0, fmt.Errorf("ollama show endpoint returned %s: %s", response.Status, strings.TrimSpace(string(body)))
-	}
-	return parseOllamaShowContextWindow(body)
-}
-
-// ollamaShowEndpoint derives the native Ollama API root from the
-// OpenAI-compatible base URL Zero stores for the provider (".../v1") and
-// appends /api/show.
-func ollamaShowEndpoint(baseURL string) (string, error) {
-	baseURL = strings.TrimSpace(baseURL)
-	if baseURL == "" {
-		return "", fmt.Errorf("provider base URL is required for ollama model discovery")
-	}
-	parsed, err := url.Parse(baseURL)
-	if err != nil || parsed.Scheme == "" || parsed.Host == "" {
-		return "", fmt.Errorf("invalid provider base URL %q", baseURL)
-	}
-	path := strings.TrimRight(parsed.Path, "/")
-	path = strings.TrimSuffix(path, "/v1")
-	parsed.Path = strings.TrimRight(path, "/") + "/api/show"
-	parsed.RawQuery = ""
-	parsed.Fragment = ""
-	return parsed.String(), nil
-}
-
-// parseOllamaShowContextWindow extracts the context length from an
-// /api/show response. Ollama reports it under model_info with an
-// architecture-prefixed key (e.g. "llama.context_length",
-// "qwen2.context_length") — the prefix varies by model family, so this scans
-// for any key ending in ".context_length" rather than hardcoding one.
-func parseOllamaShowContextWindow(body []byte) (int, error) {
-	// model_info mixes value types (strings like "general.architecture", numbers
-	// like "*.context_length"), so decode values generically and only try to
-	// read a number out of the one key we actually care about.
-	var payload struct {
-		ModelInfo map[string]any `json:"model_info"`
-	}
-	if err := json.Unmarshal(body, &payload); err != nil {
-		return 0, fmt.Errorf("decode ollama show response: %w", err)
-	}
-	for key, value := range payload.ModelInfo {
-		if !strings.HasSuffix(key, ".context_length") {
-			continue
-		}
-		if window, ok := value.(float64); ok && window > 0 {
-			return int(window), nil
-		}
-	}
-	return 0, fmt.Errorf("ollama show response did not report a context length")
-}
-
 func discoverOpenAIModels(ctx context.Context, profile config.ProviderProfile, options Options) ([]Model, error) {
 	endpoint, err := modelsEndpoint(profile.BaseURL)
 	if err != nil {

internal/providermodeldiscovery/discovery_test.go

@@ -2,7 +2,6 @@ package providermodeldiscovery
 
 import (
 	"context"
-	"io"
 	"net/http"
 	"net/http/httptest"
 	"strings"
@@ -268,61 +267,3 @@ func modelIDs(models []Model) []string {
 	}
 	return ids
 }
-
-// TestDiscoverOllamaContextWindowFetchesFromNativeShowEndpoint: the generic
-// /v1/models probe never carries context-window metadata (parseModelsResponse
-// only extracts id/description), so a custom/local Ollama model tag with no
-// curated-catalog match has no other source for it. This exercises the
-// Ollama-native /api/show fallback that fills that gap.
-func TestDiscoverOllamaContextWindowFetchesFromNativeShowEndpoint(t *testing.T) {
-	var gotPath, gotMethod, gotBody string
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		gotPath = r.URL.Path
-		gotMethod = r.Method
-		body, _ := io.ReadAll(r.Body)
-		gotBody = string(body)
-		w.Header().Set("Content-Type", "application/json")
-		_, _ = w.Write([]byte(`{
-			"model_info": {
-				"general.architecture": "qwen2",
-				"qwen2.context_length": 131072
-			}
-		}`))
-	}))
-	defer server.Close()
-
-	window, err := DiscoverOllamaContextWindow(context.Background(), server.URL+"/v1", "kimi-k2.7-code:cloud", Options{HTTPClient: server.Client()})
-	if err != nil {
-		t.Fatalf("DiscoverOllamaContextWindow returned error: %v", err)
-	}
-	if window != 131072 {
-		t.Fatalf("context window = %d, want 131072", window)
-	}
-	if gotPath != "/api/show" {
-		t.Fatalf("requested path = %q, want /api/show (not under /v1)", gotPath)
-	}
-	if gotMethod != http.MethodPost {
-		t.Fatalf("method = %q, want POST", gotMethod)
-	}
-	if !strings.Contains(gotBody, `"kimi-k2.7-code:cloud"`) {
-		t.Fatalf("request body = %q, want it to name the model", gotBody)
-	}
-}
-
-func TestDiscoverOllamaContextWindowRequiresModelName(t *testing.T) {
-	if _, err := DiscoverOllamaContextWindow(context.Background(), "http://localhost:11434/v1", "", Options{}); err == nil {
-		t.Fatal("expected an error for an empty model name")
-	}
-}
-
-func TestDiscoverOllamaContextWindowErrorsWhenShowOmitsContextLength(t *testing.T) {
-	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		w.Header().Set("Content-Type", "application/json")
-		_, _ = w.Write([]byte(`{"model_info": {"general.architecture": "qwen2"}}`))
-	}))
-	defer server.Close()
-
-	if _, err := DiscoverOllamaContextWindow(context.Background(), server.URL+"/v1", "some-model", Options{HTTPClient: server.Client()}); err == nil {
-		t.Fatal("expected an error when no *.context_length key is present")
-	}
-}

internal/providers/providerio/providerio.go

@@ -6,12 +6,10 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"math"
 	"net/http"
 	"net/url"
 	"os"
 	"regexp"
-	"runtime"
 	"strconv"
 	"strings"
 	"time"
@@ -27,9 +25,9 @@ var ErrStreamIdle = errors.New("idle timeout (upstream stopped sending data)")
 
 // ErrStreamStalled reports that a streaming upstream kept the connection alive
 // (SSE keep-alives reset the idle watchdog, so it never fired) but produced no
-// actual output for ContentStallTimeout(idle). Without this an upstream that
-// heartbeats-but-stalls — observed on chatgpt/gpt-5.x and ollama reasoning
-// models — would hang the agent indefinitely.
+// actual output for streamContentStallFactor × the idle timeout. Without this an
+// upstream that heartbeats-but-stalls — observed on chatgpt/gpt-5.x and ollama
+// reasoning models — would hang the agent indefinitely.
 var ErrStreamStalled = errors.New("stream stalled (upstream kept the connection alive but produced no output)")
 
 // StreamTimeoutMessage returns the human-readable detail for a stream-timeout
@@ -40,7 +38,7 @@ var ErrStreamStalled = errors.New("stream stalled (upstream kept the connection
 // stuck or very slow.
 func StreamTimeoutMessage(err error, idleTimeout time.Duration) string {
 	if errors.Is(err, ErrStreamStalled) {
-		return fmt.Sprintf("no output for %s (the model kept the connection alive but produced nothing — it may be stuck; try a faster model or lower reasoning effort)", ContentStallTimeout(idleTimeout))
+		return fmt.Sprintf("no output for %s (the model kept the connection alive but produced nothing — it may be stuck; try a faster model or lower reasoning effort)", idleTimeout*streamContentStallFactor)
 	}
 	return fmt.Sprintf("idle timeout after %s (upstream stopped sending data)", idleTimeout)
 }
@@ -55,32 +53,13 @@ func StreamTimeoutMessage(err error, idleTimeout time.Duration) string {
 // Override globally with ZERO_STREAM_IDLE_TIMEOUT.
 const DefaultStreamIdleTimeout = 5 * time.Minute
 
-// ContentStallTimeout bounds a heartbeat-but-no-output stream: keep-alives reset
-// the idle watchdog (a heartbeating upstream is not "dead"), but if NO real data
-// line arrives for this long the stream is aborted (ErrStreamStalled). Scaled
-// above idleTimeout (so a slow-but-producing request that emits data between
-// heartbeats is never killed — the watchdog only ever fires when NOTHING real
-// arrives), but only 1.2× rather than the old 2×: a genuine heartbeat-pause
-// stall on chatgpt/gpt-5.x rarely recovers, so a ~10-minute dead wait (at the 5m
-// idle default) was a terrible UX for a doomed turn. At the default idle this is
-// 6 minutes; it still scales with ZERO_STREAM_IDLE_TIMEOUT. A returned value <= 0
-// (idle watchdog disabled) leaves the content watchdog off too.
-func ContentStallTimeout(idleTimeout time.Duration) time.Duration {
-	if idleTimeout <= 0 {
-		return 0
-	}
-	// 1.2× computed as idle + idle/5 (not idle*6/5), plus a clamp: a
-	// pathologically large ZERO_STREAM_IDLE_TIMEOUT could make idle*6 overflow
-	// int64 and wrap to a NEGATIVE duration, which would arm the content timer
-	// to fire immediately and abort every stream. Clamping to the max duration
-	// on overflow just means "effectively no content watchdog" — the sane
-	// result for an absurd idle timeout.
-	extra := idleTimeout / 5
-	if idleTimeout > math.MaxInt64-extra {
-		return math.MaxInt64
-	}
-	return idleTimeout + extra
-}
+// streamContentStallFactor bounds a heartbeat-but-no-output stream. Keep-alives
+// reset the idle watchdog (a heartbeating upstream is not "dead"), but if NO real
+// data line arrives for streamContentStallFactor × the idle timeout, the stream is
+// treated as stalled and aborted (ErrStreamStalled). It is > 1 so a slow-but-
+// producing request — one that emits data between heartbeats — is never killed; the
+// content watchdog only catches a stream that heartbeats while producing nothing.
+const streamContentStallFactor = 2
 
 // streamIdleTimeoutEnv is the global override for the stream idle timeout. It
 // accepts a Go duration ("5m", "300s", "90s") or a bare number of seconds
@@ -143,21 +122,6 @@ func NormalizeBaseURL(baseURL string, defaultBaseURL string, label string) (stri
 //     unaffected (the stream-idle + content watchdogs cover that).
 //   - IdleConnTimeout is shortened so a connection that went idle across a pause
 //     is closed (and re-dialed fresh) rather than reused after it has gone stale.
-//   - DisableKeepAlives on darwin only: ResponseHeaderTimeout/IdleConnTimeout
-//     above catch a reused connection that's fully dead (never responds) or
-//     idle past the timeout, but not one that's alive-but-severely-degraded —
-//     e.g. reused shortly after a prior request on the same host (well within
-//     30s, common across quick retries of the same turn), where it still
-//     delivers real bytes, just at a crippled rate, resetting Zero's stream
-//     idle/content-stall watchdogs (which only fire on true silence) without
-//     ever recovering. That degraded-not-dead case is indistinguishable from
-//     genuine backend slowness from inside the stream, so the only reliable
-//     fix is removing pooling from the equation entirely on the one platform
-//     where this class of bug has actually reproduced. A fresh TCP+TLS
-//     handshake per request costs low tens of milliseconds — negligible next
-//     to the minutes-long stalls this avoids — and this doesn't touch
-//     Linux/Windows, where the underlying OS doesn't keep dead/degraded
-//     pooled connections around as long.
 var sharedHTTPClient = func() *http.Client {
 	transport := http.DefaultTransport.(*http.Transport).Clone()
 	// 120s, not 60s: a slow cloud proxy (e.g. ollama `*:cloud`) can withhold its
@@ -168,7 +132,6 @@ var sharedHTTPClient = func() *http.Client {
 	// content-stall watchdogs.
 	transport.ResponseHeaderTimeout = 120 * time.Second
 	transport.IdleConnTimeout = 30 * time.Second
-	transport.DisableKeepAlives = runtime.GOOS == "darwin"
 	return &http.Client{Transport: transport}
 }()
 
@@ -322,7 +285,7 @@ func ScanSSEDataWithContext(
 		// Content watchdog: only real data lines reset it (keep-alives do not), so a
 		// stream that heartbeats without producing output is bounded instead of
 		// hanging forever.
-		contentTimeout := ContentStallTimeout(idleTimeout)
+		contentTimeout := idleTimeout * streamContentStallFactor
 		content := time.NewTimer(contentTimeout)
 		defer content.Stop()
 		contentC = content.C

internal/providers/providerio/providerio_test.go

@@ -4,9 +4,7 @@ import (
 	"context"
 	"errors"
 	"io"
-	"math"
 	"net/http"
-	"runtime"
 	"strings"
 	"testing"
 	"time"
@@ -205,36 +203,11 @@ func TestUpstreamUnreachable(t *testing.T) {
 	}
 }
 
-// ContentStallTimeout is 1.2× the idle timeout, disabled (0) when idle is
-// disabled, and must never overflow to a negative duration for an absurdly
-// large idle timeout (which would arm the content timer to fire immediately
-// and abort every stream).
-func TestContentStallTimeout(t *testing.T) {
-	cases := []struct {
-		idle time.Duration
-		want time.Duration
-	}{
-		{5 * time.Minute, 6 * time.Minute},
-		{30 * time.Second, 36 * time.Second},
-		{100 * time.Millisecond, 120 * time.Millisecond},
-		{0, 0},
-		{-1, 0},
-	}
-	for _, c := range cases {
-		if got := ContentStallTimeout(c.idle); got != c.want {
-			t.Fatalf("ContentStallTimeout(%v) = %v, want %v", c.idle, got, c.want)
-		}
-	}
-	// Overflow guard: idle*6 would wrap negative; the clamp keeps it positive.
-	if got := ContentStallTimeout(math.MaxInt64); got <= 0 {
-		t.Fatalf("ContentStallTimeout(MaxInt64) = %v, must stay positive (no overflow wrap)", got)
-	}
-}
-
 // A heartbeating-but-output-less upstream must not hang forever: SSE keep-alives
 // feed the idle watchdog (so it never fires), but the content watchdog
-// (ContentStallTimeout(idle)) aborts with ErrStreamStalled when no real data
-// line arrives. This is the gpt-5.x / ollama "still generating forever" hang.
+// (idleTimeout × streamContentStallFactor) aborts with ErrStreamStalled when no
+// real data line arrives. This is the gpt-5.x / ollama "still generating forever"
+// hang.
 func TestScanSSEDataWithContextAbortsOnContentStall(t *testing.T) {
 	pr, pw := io.Pipe()
 	defer func() { _ = pw.Close() }()
@@ -262,8 +235,7 @@ func TestScanSSEDataWithContextAbortsOnContentStall(t *testing.T) {
 
 	done := make(chan error, 1)
 	go func() {
-		// idle 100ms → content stall at 120ms (ContentStallTimeout = idle*1.2).
-		// Keep-alives reset idle but not content.
+		// idle 100ms → content stall at 200ms. Keep-alives reset idle but not content.
 		done <- ScanSSEDataWithContext(context.Background(), cancel, pr, 100*time.Millisecond, func(string) bool { return true })
 	}()
 
@@ -286,7 +258,7 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
 	pr, pw := io.Pipe()
 
 	go func() {
-		// One data line every 30ms for ~300ms (well past the 120ms content window,
+		// One data line every 30ms for ~300ms (well past the 200ms content window,
 		// with comfortable slack under the 100ms idle timeout), so the content
 		// watchdog keeps resetting, then close cleanly.
 		for i := 0; i < 10; i++ {
@@ -318,16 +290,16 @@ func TestScanSSEDataWithContextContentResetsOnData(t *testing.T) {
 }
 
 // StreamTimeoutMessage must give a stalled stream a distinct, accurate detail —
-// it reports the content window (ContentStallTimeout) and must NOT claim the
-// upstream "stopped sending data" (keep-alives were still arriving).
+// it reports the content window (idle × factor) and must NOT claim the upstream
+// "stopped sending data" (keep-alives were still arriving).
 func TestStreamTimeoutMessage(t *testing.T) {
 	idle := 5 * time.Minute
 	if msg := StreamTimeoutMessage(ErrStreamIdle, idle); !strings.Contains(msg, "idle timeout after 5m") {
 		t.Fatalf("idle message = %q, want it to mention the 5m idle timeout", msg)
 	}
 	stalled := StreamTimeoutMessage(ErrStreamStalled, idle)
-	if !strings.Contains(stalled, "no output for 6m") {
-		t.Fatalf("stalled message = %q, want it to report the 6m content window (idle 5m × 1.2)", stalled)
+	if !strings.Contains(stalled, "no output for 10m") {
+		t.Fatalf("stalled message = %q, want it to report the 10m content window", stalled)
 	}
 	if strings.Contains(stalled, "stopped sending data") {
 		t.Fatalf("stalled message must not claim the upstream stopped sending data: %q", stalled)
@@ -352,17 +324,6 @@ func TestHTTPClientReturnsStallHardenedSharedClient(t *testing.T) {
 	if tr.IdleConnTimeout != 30*time.Second {
 		t.Fatalf("IdleConnTimeout = %v, want 30s", tr.IdleConnTimeout)
 	}
-	// DisableKeepAlives is the stronger mitigation scoped to darwin only: the
-	// two timeouts above catch a reused connection that's fully dead or idle
-	// too long, but not one that's alive-and-degraded (still delivers real
-	// bytes, just at a crippled rate) — which resets Zero's stream watchdogs
-	// without ever recovering. Removing pooling from the equation entirely is
-	// only worth its reconnect cost on the platform this class of bug has
-	// actually reproduced on.
-	wantDisableKeepAlives := runtime.GOOS == "darwin"
-	if tr.DisableKeepAlives != wantDisableKeepAlives {
-		t.Fatalf("DisableKeepAlives = %v, want %v (GOOS=%s)", tr.DisableKeepAlives, wantDisableKeepAlives, runtime.GOOS)
-	}
 	if HTTPClient(nil) != got {
 		t.Fatal("HTTPClient(nil) must return a shared instance so the conn pool is reused")
 	}

internal/specialist/output_tool_test.go

@@ -124,16 +124,10 @@ func TestOutputToolBlocksUntilTaskCompletes(t *testing.T) {
 	tool := NewOutputTool(manager)
 	tool.PollInterval = time.Millisecond
 
-	// timeout is a ceiling, not a target: the test still returns as soon as the
-	// 5ms write lands (PollInterval keeps it responsive), it just tolerates a
-	// slow/contended CI runner without failing. A 100ms budget against a 5ms
-	// write only left 20x margin, which Windows CI runners (coarser default
-	// timer granularity, heavier scheduling contention than Linux/macOS) blew
-	// through and failed the test on an otherwise-unrelated PR merge.
 	result := tool.Run(context.Background(), map[string]any{
 		"task_id": "child_task",
 		"block":   true,
-		"timeout": 2000,
+		"timeout": 100,
 	})
 
 	if result.Status != tools.StatusOK || !strings.Contains(result.Output, "output:\nfinished") {

internal/tools/exec_command.go

@@ -630,16 +630,6 @@ func (session *execSession) collect(ctx context.Context, wait time.Duration) (st
 			if session.output.consumeTruncated() {
 				truncated = true
 			}
-			// A background process that keeps writing output faster than this
-			// loop can drain it (a chatty dev server, a watch-mode rebuild loop,
-			// a crash-restart spew) would otherwise never let drainString return
-			// empty, so the deadline check below — only reached on an empty
-			// drain — would never fire. That turns `wait` into an unbounded
-			// block regardless of what the caller asked for. Check it here too,
-			// so continuous output can never starve the timeout.
-			if time.Now().After(deadline) {
-				return finish()
-			}
 			continue
 		}
 		if session.doneClosed() {

internal/tools/exec_command_test.go

@@ -450,65 +450,6 @@ func TestExecToolResultSurfacesBufferTruncationOutsideByteBudget(t *testing.T) {
 	}
 }
 
-// TestCollectRespectsDeadlineUnderContinuousOutput asserts collect() returns
-// close to its requested deadline even while output keeps arriving. Before
-// the corresponding fix, the deadline was only checked in the branch reached
-// when drainString returns empty — a background process producing output
-// fast/continuously enough to keep the buffer perpetually non-empty could
-// theoretically starve that check indefinitely. This synthetic writer
-// (8 goroutines, tight loop) did not reliably reproduce that starvation under
-// Go's scheduler in practice — the reader still won the race often enough —
-// so this test doesn't prove the old code could hang; it just pins down the
-// intended behavior (bounded by wait) going forward.
-func TestCollectRespectsDeadlineUnderContinuousOutput(t *testing.T) {
-	session := &execSession{
-		id:     1000,
-		output: newExecOutputBuffer(),
-		done:   make(chan struct{}),
-	}
-
-	stop := make(chan struct{})
-	var wg sync.WaitGroup
-	// Several concurrent writers, each pushing a decent-sized chunk in a tight
-	// loop: a single slow writer lets the reader win the race often enough
-	// (the runtime schedules a gap between writes) to mask the bug. Enough
-	// parallel writers keep the buffer non-empty essentially continuously,
-	// closer to a real chatty process whose PTY reads land in bursts.
-	const writers = 8
-	chunk := []byte(strings.Repeat("x", 256))
-	wg.Add(writers)
-	for i := 0; i < writers; i++ {
-		go func() {
-			defer wg.Done()
-			for {
-				select {
-				case <-stop:
-					return
-				default:
-					session.output.Write(chunk)
-				}
-			}
-		}()
-	}
-	t.Cleanup(func() {
-		close(stop)
-		wg.Wait()
-	})
-
-	const wait = 200 * time.Millisecond
-	start := time.Now()
-	_, _ = session.collect(context.Background(), wait)
-	elapsed := time.Since(start)
-
-	// Generous slack over `wait` for scheduling jitter under a continuously
-	// writing goroutine — this must stay a small multiple of wait, not
-	// "however long the writer keeps going" (which is what the bug produced:
-	// this test would hang past the 30s test timeout without the fix).
-	if elapsed > 3*wait {
-		t.Fatalf("collect took %v under continuous output, want close to the %v deadline", elapsed, wait)
-	}
-}
-
 // resilientTempDir is like t.TempDir() but tolerates the Windows handle-release
 // lag: a SIGKILL'd child process that had the dir as its cwd may not have
 // released it the instant it is reaped, so the immediate RemoveAll t.TempDir()

internal/tui/clipboard.go

@@ -56,13 +56,6 @@ func pasteFromClipboardCmd() tea.Cmd {
 // spec prompt, the MCP manager, an open picker, the detailed transcript) swallow
 // the paste; empty content is a no-op.
 func (m model) routePaste(content string) (tea.Model, tea.Cmd) {
-	// A paste is a deliberate action, same as a keypress or click — it means
-	// the user moved on to something else, so it disarms a stale Esc
-	// cancel-confirmation. tea.PasteMsg/clipboardReadMsg aren't
-	// tea.KeyPressMsg, so they don't go through that generic keypress hook;
-	// do it once here, before any early return, so both the bracketed-paste
-	// and right-click-paste paths are covered uniformly.
-	m = m.disarmCancelConfirmation()
 	if content == "" {
 		// Empty text clipboard — the user may have pasted a screenshot.
 		// Probe the OS clipboard for image content asynchronously.

internal/tui/command_center.go

@@ -490,16 +490,16 @@ func (m model) handleModelCommand(args string) (model, string) {
 // picker calls this when a model from a non-active provider is chosen, so the
 // picker can list every saved provider and switch across them (like a unified
 // provider+model selector). The key is loaded from the encrypted store / env.
-func (m model) switchProviderModel(providerName, modelID string) (model, string, tea.Cmd) {
+func (m model) switchProviderModel(providerName, modelID string) (model, string) {
 	if m.pending {
-		return m, "Model\nCannot switch providers while a run is active.", nil
+		return m, "Model\nCannot switch providers while a run is active."
 	}
 	if m.newProvider == nil {
-		return m, "Model\nProvider rebuild is not available for this TUI session.", nil
+		return m, "Model\nProvider rebuild is not available for this TUI session."
 	}
 	target, ok := m.savedProviderByName(providerName)
 	if !ok {
-		return m, "Model\nunknown provider " + strconv.Quote(providerName), nil
+		return m, "Model\nunknown provider " + strconv.Quote(providerName)
 	}
 	target = m.profileWithCredential(target)
 	target.Model = strings.TrimSpace(modelID)
@@ -508,11 +508,11 @@ func (m model) switchProviderModel(providerName, modelID string) (model, string,
 	// was deleted/unreadable the marker can still be set, and building a keyless
 	// provider would only fail later with a 401. Local/no-auth providers need no key.
 	if strings.TrimSpace(target.APIKey) == "" && strings.TrimSpace(target.AuthHeaderValue) == "" && !(hasDescriptor && descriptor.Local) {
-		return m, "Model\nprovider " + strconv.Quote(providerName) + " has no usable credential — run setup or `zero auth login " + providerName + "`.", nil
+		return m, "Model\nprovider " + strconv.Quote(providerName) + " has no usable credential — run setup or `zero auth login " + providerName + "`."
 	}
 	next, err := m.newProvider(target)
 	if err != nil {
-		return m, "Model\n" + redaction.RedactString(err.Error(), redaction.Options{ExtraSecretValues: []string{target.APIKey}}), nil
+		return m, "Model\n" + redaction.RedactString(err.Error(), redaction.Options{ExtraSecretValues: []string{target.APIKey}})
 	}
 	m.provider = next
 	m.providerProfile = target
@@ -524,19 +524,7 @@ func (m model) switchProviderModel(providerName, modelID string) (model, string,
 		_, _ = config.SetActiveProvider(m.userConfigPath, target.Name)
 		_, _ = config.SetProviderModel(m.userConfigPath, target.Name, target.Model)
 	}
-	// Warm discovery for the provider we just switched to, same as Init() does
-	// for the provider active at launch — otherwise the context-usage gauge has
-	// no window for this provider until /model happens to be opened separately.
-	var cmds []tea.Cmd
-	if hasDescriptor {
-		if cmd := m.modelPickerProviderDiscoveryCmd(descriptor, target); cmd != nil {
-			cmds = append(cmds, cmd)
-		}
-		if cmd := m.ollamaContextWindowDiscoveryCmd(descriptor, target.BaseURL, target.Model); cmd != nil {
-			cmds = append(cmds, cmd)
-		}
-	}
-	return m, fmt.Sprintf("Model\nSwitched to %s · %s", target.Name, target.Model), tea.Batch(cmds...)
+	return m, fmt.Sprintf("Model\nSwitched to %s · %s", target.Name, target.Model)
 }
 
 // profileWithCredential fills a profile's APIKey for provider construction the same

internal/tui/context_gauge_test.go

@@ -27,29 +27,3 @@ func TestContextWindowSegment(t *testing.T) {
 		t.Fatalf("gauge = %q, want 161K/200K · 81%%", got)
 	}
 }
-
-// TestStatusLineDoesNotDuplicateTokenFigureNextToGauge: the gauge's "used"
-// figure and the plain usage segment's token count both read the exact same
-// latestUsageTokens value — once the gauge is showing it, the usage segment
-// must fall back to cost-only, or the same number renders twice side by
-// side in the footer (e.g. "◔ 161K/200K · 81% │ 161K tok").
-func TestStatusLineDoesNotDuplicateTokenFigureNextToGauge(t *testing.T) {
-	m := newModel(t.Context(), Options{ModelName: "claude-sonnet-4.5"})
-	if _, err := m.usageTracker.Record(usage.RecordInput{
-		ModelID: "claude-sonnet-4.5",
-		Usage:   zeroruntime.Usage{InputTokens: 160_000, OutputTokens: 1000},
-	}); err != nil {
-		t.Fatalf("Record: %v", err)
-	}
-
-	status := plainRender(t, m.statusLine(110))
-	if !strings.Contains(status, "161K/200K") {
-		t.Fatalf("status line = %q, expected the context gauge to render", status)
-	}
-	if strings.Count(status, "161K") != 1 {
-		t.Fatalf("status line = %q, the 161K token figure must appear exactly once, not duplicated next to the gauge", status)
-	}
-	if strings.Contains(status, "tok") {
-		t.Fatalf("status line = %q, the plain token segment should be suppressed once the gauge shows the same figure", status)
-	}
-}

internal/tui/flush_test.go

@@ -122,8 +122,6 @@ func TestEscCancellationLeavesVisibleMarker(t *testing.T) {
 
 	updated, _ := m.Update(testKey(tea.KeyEsc))
 	next := updated.(model)
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
 	if !transcriptContains(next.transcript, "Run cancelled.") {
 		t.Fatalf("expected visible cancellation marker, got %#v", next.transcript)
 	}

internal/tui/init_window_size_test.go

@@ -1,59 +0,0 @@
-package tui
-
-import (
-	"context"
-	"reflect"
-	"testing"
-
-	tea "charm.land/bubbletea/v2"
-)
-
-// TestInitRequestsWindowSize: Bubble Tea documents an initial WindowSizeMsg as
-// delivered automatically on program start, but that's the terminal
-// proactively pushing a size — if it's ever missed (a slow/unusual terminal,
-// a multiplexer, a startup race), nothing else asks again, m.height stays 0
-// forever, and transcriptView's `if m.altScreen && m.height > 0` gate falls
-// back to the unpadded, non-fullscreen render path for the whole session (the
-// alt-screen viewport never gets filled below the actual content). Init must
-// explicitly request it too, the same way it already explicitly requests the
-// background color rather than relying solely on an unprompted push.
-func TestInitRequestsWindowSize(t *testing.T) {
-	m := newModel(context.Background(), Options{ModelName: "gpt-4"})
-	cmd := m.Init()
-	if cmd == nil {
-		t.Fatal("Init() must return a non-nil command")
-	}
-
-	want := reflect.ValueOf(tea.RequestWindowSize).Pointer()
-	if !batchContainsCmd(t, cmd, want) {
-		t.Error("Init() must request the window size (tea.RequestWindowSize), not rely solely on the terminal's unprompted initial WindowSizeMsg")
-	}
-}
-
-// batchContainsCmd reports whether cmd (Init()'s single top-level
-// tea.Batch(...)) contains a sub-command matching want, compared by pointer
-// (the same technique TestThemeAutoReProbesBackground uses for
-// tea.RequestBackgroundColor — reliable for named top-level functions like
-// tea.RequestWindowSize, not closures). Invokes cmd itself once to unpack the
-// tea.BatchMsg, but only pointer-compares the sub-commands — never calls
-// them, since Init()'s batch also carries real closures (e.g. provider model
-// discovery) that make live network calls and must not fire in a unit test.
-func batchContainsCmd(t *testing.T, cmd tea.Cmd, want uintptr) bool {
-	t.Helper()
-	if cmd == nil {
-		return false
-	}
-	if reflect.ValueOf(cmd).Pointer() == want {
-		return true
-	}
-	batch, ok := cmd().(tea.BatchMsg)
-	if !ok {
-		return false
-	}
-	for _, sub := range batch {
-		if sub != nil && reflect.ValueOf(sub).Pointer() == want {
-			return true
-		}
-	}
-	return false
-}

internal/tui/keybinding_help.go

@@ -31,7 +31,7 @@ var keybindingGroups = []keybindingGroup{
 		bindings: []keybinding{
 			{"Enter", "send the message"},
 			{"Alt+Enter", "insert a newline (multi-line compose)"},
-			{"Esc (×2)", "cancel the run / dismiss a popup / clear the input"},
+			{"Esc", "cancel the run / dismiss a popup / clear the input"},
 			{"Ctrl+C", "cancel the run, then quit"},
 			{"?", "show this help (on an empty input)"},
 		},

internal/tui/model.go

@@ -25,7 +25,6 @@ import (
 	"github.com/Gitlawb/zero/internal/notify"
 	"github.com/Gitlawb/zero/internal/providerhealth"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
-	"github.com/Gitlawb/zero/internal/providers/providerio"
 	"github.com/Gitlawb/zero/internal/sandbox"
 	"github.com/Gitlawb/zero/internal/sessions"
 	"github.com/Gitlawb/zero/internal/streamjson"
@@ -41,15 +40,6 @@ const chatWheelScrollLines = 5
 const ctrlCExitConfirmDuration = 3 * time.Second
 const ctrlCExitConfirmText = "Press Ctrl+C again to exit"
 
-// escCancelConfirmDuration/escCancelConfirmText guard Esc cancelling a running
-// turn, mirroring ctrlCExitConfirmDuration/ctrlCExitConfirmText's pattern (same
-// window, same amber footer treatment) so the two "stop it" keybinds feel
-// consistent. Without this, a single stray Esc — e.g. meant to dismiss a
-// suggestion overlay that had already closed — silently threw away an
-// in-progress run with no chance to reconsider.
-const escCancelConfirmDuration = 3 * time.Second
-const escCancelConfirmText = "Press Esc again to cancel"
-
 // dragEdgeScrollInterval/dragEdgeScrollStep drive the smooth-glide auto-scroll
 // while a drag holds past the transcript edge (see edgeScrollDelta). A small step
 // on a short, steady cadence reads as a smooth continuous scroll; the wheel-scroll
@@ -58,41 +48,40 @@ const dragEdgeScrollInterval = 70 * time.Millisecond
 const dragEdgeScrollStep = 1
 
 type model struct {
-	ctx                         context.Context
-	cwd                         string
-	userCommands                []usercommands.Command // file-sourced /commands (.zero/commands)
-	userConfigPath              string
-	doctorUserConfigPath        string
-	projectConfigPath           string
-	gitBranch                   string
-	providerName                string
-	modelName                   string
-	providerProfile             config.ProviderProfile
-	savedProviders              []config.ProviderProfile
-	provider                    zeroruntime.Provider
-	newProvider                 func(config.ProviderProfile) (zeroruntime.Provider, error)
-	probeProviderHealth         func(context.Context, providerhealth.Options) providerhealth.Result
-	discoverProviderModels      func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
-	discoverOllamaContextWindow func(ctx context.Context, baseURL string, model string) (int, error)
-	registry                    *tools.Registry
-	sessionStore                *sessions.Store
-	sandboxStore                *sandbox.GrantStore
-	mcpConfig                   config.MCPConfig
-	mcpPermissionStore          *internalmcp.PermissionStore
-	mcpTokenStore               *internalmcp.TokenStore
-	mcpCommand                  func(context.Context, []string) MCPCommandResult
-	sandboxSetupCommand         func(context.Context) SandboxSetupCommandResult
-	mcpViewStateCache           MCPViewState
-	mcpViewStateReady           bool
-	mcpCommandSeq               int
-	mcpCommandCancel            context.CancelFunc
-	sandboxSetupSeq             int
-	sandboxSetupInFlight        bool
-	doctorCommandSeq            int
-	doctorInFlight              bool
-	doctorFrame                 int
-	activeSession               sessions.Metadata
-	sessionEvents               []sessions.Event
+	ctx                    context.Context
+	cwd                    string
+	userCommands           []usercommands.Command // file-sourced /commands (.zero/commands)
+	userConfigPath         string
+	doctorUserConfigPath   string
+	projectConfigPath      string
+	gitBranch              string
+	providerName           string
+	modelName              string
+	providerProfile        config.ProviderProfile
+	savedProviders         []config.ProviderProfile
+	provider               zeroruntime.Provider
+	newProvider            func(config.ProviderProfile) (zeroruntime.Provider, error)
+	probeProviderHealth    func(context.Context, providerhealth.Options) providerhealth.Result
+	discoverProviderModels func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
+	registry               *tools.Registry
+	sessionStore           *sessions.Store
+	sandboxStore           *sandbox.GrantStore
+	mcpConfig              config.MCPConfig
+	mcpPermissionStore     *internalmcp.PermissionStore
+	mcpTokenStore          *internalmcp.TokenStore
+	mcpCommand             func(context.Context, []string) MCPCommandResult
+	sandboxSetupCommand    func(context.Context) SandboxSetupCommandResult
+	mcpViewStateCache      MCPViewState
+	mcpViewStateReady      bool
+	mcpCommandSeq          int
+	mcpCommandCancel       context.CancelFunc
+	sandboxSetupSeq        int
+	sandboxSetupInFlight   bool
+	doctorCommandSeq       int
+	doctorInFlight         bool
+	doctorFrame            int
+	activeSession          sessions.Metadata
+	sessionEvents          []sessions.Event
 	// titledSessions records session ids for which a model-generated title has
 	// already been attempted this process, so a finished turn re-fires the title
 	// generator at most once per session (even before its async result lands).
@@ -307,14 +296,6 @@ type model struct {
 	copyStatusSeq     int
 	exitConfirmActive bool
 	exitConfirmSeq    int
-	// cancelConfirmActive/cancelConfirmSeq mirror exitConfirmActive/exitConfirmSeq
-	// (same seq-gated tea.Tick pattern) but guard a DIFFERENT action: Esc
-	// cancelling a running turn. The two are deliberately separate state (not a
-	// shared flag) since they're different actions with different consequences
-	// (quit the app vs. cancel the current run) that are armed by different
-	// keys — Ctrl+C and Esc respectively.
-	cancelConfirmActive bool
-	cancelConfirmSeq    int
 	// edgeScrollDelta drives the smooth-glide auto-scroll while a drag holds past
 	// the transcript's top/bottom edge: 0 when idle, else the signed per-tick step
 	// (matches transcriptEdgeScrollDelta's sign convention). A self-scheduling
@@ -349,12 +330,6 @@ type model struct {
 	// catalog descriptor ID), so /model shows each provider's real current models —
 	// the same list the provider-setup wizard discovers — not the static catalog.
 	modelPickerLiveByProvider map[string][]providermodeldiscovery.Model
-	// ollamaContextWindowByModel holds context-window sizes fetched from a local
-	// Ollama daemon's native /api/show endpoint (keyed by model name), for
-	// custom/local models that have no curated-catalog entry and whose
-	// OpenAI-compatible /v1/models listing doesn't carry that metadata at all —
-	// see modelContextWindow.
-	ollamaContextWindowByModel map[string]int
 
 	// pendingImages holds image attachments staged by /image for the next user
 	// turn; pendingImageLabels are their display names (base(path)) for the chip
@@ -383,12 +358,6 @@ type exitConfirmExpiredMsg struct {
 	seq int
 }
 
-// cancelConfirmExpiredMsg mirrors exitConfirmExpiredMsg for the Esc
-// cancel-a-run confirmation (see cancelConfirmActive).
-type cancelConfirmExpiredMsg struct {
-	seq int
-}
-
 // dragEdgeScrollTickMsg advances the smooth-glide auto-scroll one step (see
 // edgeScrollDelta). seq must match m.edgeScrollSeq or the tick is stale (the
 // drag moved back into the body, released, or was otherwise stopped since this
@@ -676,57 +645,56 @@ func newModel(ctx context.Context, options Options) model {
 	notifier.SetFocused(true)
 
 	m := model{
-		ctx:                         ctx,
-		cwd:                         cwd,
-		swarmDoneAt:                 map[string]time.Time{},
-		userCommands:                loadedUserCommands,
-		composerCursorVisible:       true,
-		userConfigPath:              options.UserConfigPath,
-		doctorUserConfigPath:        doctorUserConfigPath,
-		projectConfigPath:           options.ProjectConfigPath,
-		savedProviders:              options.SavedProviders,
-		gitBranch:                   gitBranch(cwd),
-		providerName:                options.ProviderName,
-		modelName:                   options.ModelName,
-		providerProfile:             options.ProviderProfile,
-		favoriteModels:              favoriteModelSet(options.FavoriteModels),
-		recapsEnabled:               options.RecapsEnabled,
-		provider:                    options.Provider,
-		newProvider:                 options.NewProvider,
-		probeProviderHealth:         options.ProbeProviderHealth,
-		discoverProviderModels:      options.DiscoverProviderModels,
-		discoverOllamaContextWindow: options.DiscoverOllamaContextWindow,
-		registry:                    registry,
-		sessionStore:                sessionStore,
-		sandboxStore:                sandboxStore,
-		mcpConfig:                   options.MCPConfig,
-		mcpPermissionStore:          options.MCPPermissionStore,
-		mcpTokenStore:               options.MCPTokenStore,
-		mcpCommand:                  options.MCPCommand,
-		sandboxSetupCommand:         options.SandboxSetupCommand,
-		agentOptions:                options.AgentOptions,
-		sessionCompactor:            options.SessionCompactor,
-		runtimeMessageSink:          options.RuntimeMessageSink,
-		permissionMode:              permissionMode,
-		reasoningEffort:             options.ReasoningEffort,
-		responseStyle:               defaultedResponseStyle(options.ResponseStyle),
-		themeMode:                   resolveThemeMode(options.Theme, os.Getenv("ZERO_THEME"), options.SavedTheme),
-		hasDarkBg:                   true,
-		userAgent:                   options.UserAgent,
-		usageTracker:                usageTracker,
-		transcript:                  initialTranscript(),
-		transcriptBodyHeights:       newTranscriptBodyHeightCache(defaultTranscriptBodyHeightCacheMaxEntries),
-		prService:                   prService,
-		prState:                     prService.GetState(),
-		input:                       input,
-		spinner:                     runSpinner,
-		now:                         time.Now,
-		notifier:                    notifier,
-		altScreen:                   options.AltScreen,
-		liveUsageCounts:             map[int]int{},
-		swarmSessionMap:             map[string]string{},
-		setup:                       newSetupState(options.Setup),
-		setupSave:                   options.Setup.Save,
+		ctx:                    ctx,
+		cwd:                    cwd,
+		swarmDoneAt:            map[string]time.Time{},
+		userCommands:           loadedUserCommands,
+		composerCursorVisible:  true,
+		userConfigPath:         options.UserConfigPath,
+		doctorUserConfigPath:   doctorUserConfigPath,
+		projectConfigPath:      options.ProjectConfigPath,
+		savedProviders:         options.SavedProviders,
+		gitBranch:              gitBranch(cwd),
+		providerName:           options.ProviderName,
+		modelName:              options.ModelName,
+		providerProfile:        options.ProviderProfile,
+		favoriteModels:         favoriteModelSet(options.FavoriteModels),
+		recapsEnabled:          options.RecapsEnabled,
+		provider:               options.Provider,
+		newProvider:            options.NewProvider,
+		probeProviderHealth:    options.ProbeProviderHealth,
+		discoverProviderModels: options.DiscoverProviderModels,
+		registry:               registry,
+		sessionStore:           sessionStore,
+		sandboxStore:           sandboxStore,
+		mcpConfig:              options.MCPConfig,
+		mcpPermissionStore:     options.MCPPermissionStore,
+		mcpTokenStore:          options.MCPTokenStore,
+		mcpCommand:             options.MCPCommand,
+		sandboxSetupCommand:    options.SandboxSetupCommand,
+		agentOptions:           options.AgentOptions,
+		sessionCompactor:       options.SessionCompactor,
+		runtimeMessageSink:     options.RuntimeMessageSink,
+		permissionMode:         permissionMode,
+		reasoningEffort:        options.ReasoningEffort,
+		responseStyle:          defaultedResponseStyle(options.ResponseStyle),
+		themeMode:              resolveThemeMode(options.Theme, os.Getenv("ZERO_THEME"), options.SavedTheme),
+		hasDarkBg:              true,
+		userAgent:              options.UserAgent,
+		usageTracker:           usageTracker,
+		transcript:             initialTranscript(),
+		transcriptBodyHeights:  newTranscriptBodyHeightCache(defaultTranscriptBodyHeightCacheMaxEntries),
+		prService:              prService,
+		prState:                prService.GetState(),
+		input:                  input,
+		spinner:                runSpinner,
+		now:                    time.Now,
+		notifier:               notifier,
+		altScreen:              options.AltScreen,
+		liveUsageCounts:        map[int]int{},
+		swarmSessionMap:        map[string]string{},
+		setup:                  newSetupState(options.Setup),
+		setupSave:              options.Setup.Save,
 	}
 	// Apply an explicit theme immediately; auto stays on the dark default until
 	// Init's terminal background probe resolves it (see Init / BackgroundColorMsg).
@@ -791,18 +759,6 @@ func composerBlinkCmd() tea.Cmd {
 
 func (m model) Init() tea.Cmd {
 	cmds := []tea.Cmd{textinput.Blink, composerBlinkCmd()}
-	// Bubble Tea documents an initial WindowSizeMsg as delivered automatically
-	// on program start, so m.height/m.width are normally set before the first
-	// render. But that's the terminal proactively pushing a size — if it's
-	// ever missed (a slow/unusual terminal, a multiplexer, a startup race),
-	// nothing else ever asks again: m.height stays its zero value forever,
-	// `if m.altScreen && m.height > 0` (transcriptView) falls back to the
-	// unpadded, non-fullscreen render path for the rest of the session, and
-	// the alt-screen viewport never gets filled below the actual content.
-	// Explicitly requesting it here means Zero doesn't depend solely on the
-	// terminal's unprompted push — mirrors the RequestBackgroundColor request
-	// below for the same reason.
-	cmds = append(cmds, tea.RequestWindowSize)
 	// In auto mode, ask the terminal for its background color; the reply arrives
 	// as tea.BackgroundColorMsg and selects light vs dark (see updateModel).
 	if m.themeMode == themeAuto {
@@ -817,13 +773,6 @@ func (m model) Init() tea.Cmd {
 		if cmd := m.modelPickerProviderDiscoveryCmd(descriptor, m.providerProfile); cmd != nil {
 			cmds = append(cmds, cmd)
 		}
-		// The generic discovery above has no source for a local Ollama model's
-		// context window (see ollamaContextWindowDiscoveryCmd); probe its
-		// native /api/show separately so the gauge works for custom/local
-		// Ollama models too, not just ones in the curated catalog.
-		if cmd := m.ollamaContextWindowDiscoveryCmd(descriptor, m.providerProfile.BaseURL, m.modelName); cmd != nil {
-			cmds = append(cmds, cmd)
-		}
 	}
 	if m.prService != nil && m.runtimeMessageSink != nil {
 		service := m.prService
@@ -900,14 +849,6 @@ func (m model) disarmExitConfirmation() model {
 	return m
 }
 
-func (m model) disarmCancelConfirmation() model {
-	if m.cancelConfirmActive {
-		m.cancelConfirmActive = false
-		m.cancelConfirmSeq++
-	}
-	return m
-}
-
 // Update routes every message through updateModel, then advances the flush
 // frontier for inline rendering. Alt-screen runs keep rows in the managed view
 // instead of printing into terminal scrollback (see flush.go).
@@ -986,11 +927,6 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 			m.exitConfirmActive = false
 		}
 		return m, nil
-	case cancelConfirmExpiredMsg:
-		if msg.seq == m.cancelConfirmSeq {
-			m.cancelConfirmActive = false
-		}
-		return m, nil
 	case dragEdgeScrollTickMsg:
 		if msg.seq != m.edgeScrollSeq || m.edgeScrollDelta == 0 || !m.transcriptSelection.active {
 			return m, nil // stale, or the chain was stopped since this tick was scheduled
@@ -1038,13 +974,6 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 		if !keyCtrl(msg, 'c') {
 			m = m.disarmExitConfirmation()
 		}
-		// Mirrors the exit-confirmation reset above: any key that isn't itself
-		// the confirming Esc means the user moved on to something else, so a
-		// later, unrelated Esc must arm a fresh confirmation rather than
-		// silently cancel off a stale press from seconds ago.
-		if !keyIs(msg, tea.KeyEsc) {
-			m = m.disarmCancelConfirmation()
-		}
 		// The `?` help overlay is modal: `?`, Esc, q, or Enter close it; every
 		// other key is swallowed so nothing types into the hidden composer.
 		if m.helpOverlay {
@@ -1067,15 +996,6 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 			}
 			return m.appendSystemNotice("Mouse interaction re-enabled."), nil
 		case keyIs(msg, tea.KeyEsc):
-			// Esc is heavily overloaded below (subchat exit, MCP cancel, ask-user,
-			// permission deny, wizard/picker/suggestions dismiss, ...) before ever
-			// reaching the run-cancel fallback. Capture whether this press really
-			// is the confirming second Esc BEFORE any of those branches can fire,
-			// then disarm unconditionally: an Esc that gets consumed by one of
-			// them wasn't a confirm, so it must not leave cancelConfirmActive
-			// armed for some later, unrelated Esc to silently act on.
-			wasConfirmingCancel := m.pending && m.cancelConfirmActive
-			m = m.disarmCancelConfirmation()
 			// Subchat view exits on Esc (returns to main chat).
 			if m.subchat.active {
 				m.chatScrollOffset = m.subchat.exit()
@@ -1141,24 +1061,11 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 			if m.hasQueuedMessage() {
 				return m.clearQueuedMessage(), nil
 			}
+			m.clearComposer()
 			m.clearSuggestions()
 			if m.pending {
-				if wasConfirmingCancel {
-					m.clearComposer()
-					m.cancelRun()
-					return m, nil
-				}
-				// First Esc only arms the confirmation — preserve whatever
-				// draft the user has typed, since nothing has actually been
-				// cancelled yet and they may not press Esc again.
-				m.cancelConfirmActive = true
-				m.cancelConfirmSeq++
-				seq := m.cancelConfirmSeq
-				return m, tea.Tick(escCancelConfirmDuration, func(time.Time) tea.Msg {
-					return cancelConfirmExpiredMsg{seq: seq}
-				})
+				m.cancelRun()
 			}
-			m.clearComposer()
 			return m, nil
 		case keyIs(msg, tea.KeyEnter):
 			if m.transcriptDetailed {
@@ -1714,7 +1621,6 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 		}
 		m.clearStreamingToolCall() // active run finished — drop any lingering "writing" block
 		m.pending = false
-		m = m.disarmCancelConfirmation() // the run finished on its own — nothing left to confirm cancelling
 		// Fully reset the fade state at stream end. The next render
 		// emits the final row in solid ink (no settling animation), and
 		// the pending streamingFadeTickMsg that lands after this point
@@ -2016,14 +1922,6 @@ func (m model) updateModel(msg tea.Msg) (tea.Model, tea.Cmd) {
 		return m.applySetupOAuthDeviceCode(msg)
 	case modelPickerModelsDiscoveredMsg:
 		return m.applyModelPickerModelsDiscovered(msg), nil
-	case ollamaContextWindowDiscoveredMsg:
-		if msg.err == nil && msg.contextWindow > 0 {
-			if m.ollamaContextWindowByModel == nil {
-				m.ollamaContextWindowByModel = map[string]int{}
-			}
-			m.ollamaContextWindowByModel[msg.modelName] = msg.contextWindow
-		}
-		return m, nil
 	case mcpCommandResultMsg:
 		return m.applyMCPCommandResultMessage(msg), nil
 	}
@@ -2235,18 +2133,15 @@ func (m model) footerView(width int) string {
 		footer.WriteString(fitStyledLine(joinHeaderLine("  "+left, right, width), width))
 	}
 	footer.WriteString("\n")
-	// A message typed while a run is active is queued for the next turn; show its
-	// preview directly ABOVE the input box (not below), so it reads as "waiting to
-	// send" sitting on top of what you're currently typing.
-	if queued := renderQueuedMessagePreview(m.queuedMessage, width); queued != "" {
-		footer.WriteString(queued)
-		footer.WriteString("\n")
-	}
 	footer.WriteString(m.composerBox(width))
 	if hint := m.composerDescriptionHint(width); hint != "" {
 		footer.WriteString("\n")
 		footer.WriteString(hint)
 	}
+	if queued := renderQueuedMessagePreview(m.queuedMessage, width); queued != "" {
+		footer.WriteString("\n")
+		footer.WriteString(queued)
+	}
 	footer.WriteString("\n")
 	footer.WriteString(m.statusLine(width))
 	return footer.String()
@@ -2822,15 +2717,6 @@ const quietWorkingHint = 8 * time.Second
 // quietGenerationHint returns a "still generating…" cue with an advancing
 // quiet-timer when the active turn has produced no streamed output for a while,
 // else "". The advancing number is itself the liveness signal.
-//
-// Past half the provider's idle timeout, the cue escalates to name what's
-// actually happening and when Zero will act on its own: a heartbeating-but-
-// silent stream (observed on chatgpt/gpt-5.x and ollama reasoning models,
-// see providerio.ErrStreamStalled) is bounded by the content-stall watchdog at
-// providerio.ContentStallTimeout(idle), but until it fires this exact same
-// plain "still generating… Xs" text is indistinguishable from a genuine hang —
-// the ticking number was the only signal, and it looks identical whether real
-// (if slow) content is coming or nothing ever will.
 func (m model) quietGenerationHint() string {
 	if m.activeRunID == 0 {
 		return ""
@@ -2846,10 +2732,6 @@ func (m model) quietGenerationHint() string {
 	if quiet < quietWorkingHint {
 		return ""
 	}
-	if idleTimeout := providerio.ResolveStreamIdleTimeout(0); idleTimeout > 0 && quiet >= idleTimeout/2 {
-		ceiling := providerio.ContentStallTimeout(idleTimeout)
-		return fmt.Sprintf("still generating… %s — unusually quiet, Zero will auto-recover by ~%s if it doesn't resume", formatWorkingElapsed(quiet), formatWorkingElapsed(ceiling))
-	}
 	return "still generating… " + formatWorkingElapsed(quiet)
 }
 
@@ -3412,13 +3294,12 @@ func (m model) choosePicker() (tea.Model, tea.Cmd) {
 		}
 		return m, nil
 	}
-	var cmd tea.Cmd
 	switch picker.kind {
 	case pickerModel:
 		text := ""
 		if owner := strings.TrimSpace(item.OwnerProvider); owner != "" && !strings.EqualFold(owner, strings.TrimSpace(m.providerName)) {
 			// A model from another saved provider: switch provider + model together.
-			m, text, cmd = m.switchProviderModel(owner, item.Value)
+			m, text = m.switchProviderModel(owner, item.Value)
 		} else {
 			m, text = m.handleModelCommand(item.Value)
 		}
@@ -3448,7 +3329,7 @@ func (m model) choosePicker() (tea.Model, tea.Cmd) {
 			return m, tea.RequestBackgroundColor
 		}
 	}
-	return m, cmd
+	return m, nil
 }
 
 func (m model) chooseSuggestion() (tea.Model, tea.Cmd) {
@@ -3972,8 +3853,7 @@ func (m *model) cancelRun() {
 	m.pending = false
 	m.runCancel = nil
 	m.activeRunID = 0
-	m.cancelConfirmActive = false // whatever path got here, there's nothing left to confirm cancelling
-	m.plan.frozenAt = m.now()     // freeze the plan clock while idle (no run in flight)
+	m.plan.frozenAt = m.now() // freeze the plan clock while idle (no run in flight)
 	m.pendingPermission = nil
 	m.pendingAskUser = nil
 	// The interim block renders streamingText live; a cancelled run's partial

internal/tui/model_catalog.go

@@ -84,13 +84,6 @@ func (m model) modelContextWindow(modelName string) int {
 			return window
 		}
 	}
-	// A custom/local Ollama model tag has no curated-catalog entry, and its
-	// OpenAI-compatible /v1/models listing (the discoveredContextWindow source
-	// above) doesn't carry context-window metadata at all — see
-	// ollamaContextWindowDiscoveryCmd, the only other source for this.
-	if window := m.ollamaContextWindowByModel[trimmed]; window > 0 {
-		return window
-	}
 	// Unknown: report 0 so display gauges show no denominator. Compaction enablement
 	// applies its own positive fallback via modelregistry.AgentContextWindow.
 	return 0

internal/tui/model_test.go

@@ -1108,221 +1108,25 @@ func TestPromptSubmitDoesNotStartAnotherRunWhilePending(t *testing.T) {
 	}
 }
 
-func TestEscRequiresSecondPressToCancelPendingRun(t *testing.T) {
+func TestEscCancelsPendingRun(t *testing.T) {
 	m := newModel(context.Background(), Options{})
 	cancelled := false
 	m.pending = true
 	m.activeRunID = 1
 	m.runCancel = func() { cancelled = true }
 
-	updated, cmd := m.Update(testKey(tea.KeyEsc))
+	updated, _ := m.Update(testKey(tea.KeyEsc))
 	next := updated.(model)
 
-	if cancelled {
-		t.Fatal("first Esc should not cancel the pending run")
-	}
-	if !next.pending {
-		t.Fatal("first Esc should leave the run pending")
-	}
-	if !next.cancelConfirmActive {
-		t.Fatal("first Esc should arm cancel confirmation")
-	}
-	if cmd == nil {
-		t.Fatal("first Esc should schedule confirmation expiry")
-	}
-	status := plainRender(t, next.statusLine(80))
-	if !strings.Contains(status, escCancelConfirmText) {
-		t.Fatalf("status line = %q, want cancel confirmation", status)
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-
 	if !cancelled {
-		t.Fatal("second Esc should cancel pending run")
+		t.Fatal("expected Esc to cancel pending run")
 	}
 	if next.pending {
-		t.Fatal("expected second Esc to clear pending state")
+		t.Fatal("expected Esc to clear pending state")
 	}
 	if next.activeRunID != 0 || next.runCancel != nil {
 		t.Fatalf("expected active run state to clear, got id=%d cancel=%v", next.activeRunID, next.runCancel)
 	}
-	if next.cancelConfirmActive {
-		t.Fatal("cancelling should clear cancel confirmation")
-	}
-}
-
-// TestEscArmingCancelConfirmationPreservesComposerDraft: the first Esc only
-// arms the confirmation — nothing has actually been cancelled yet, so it
-// must not destroy a draft the user is still typing. Only the confirming
-// second Esc (the one that actually cancels the run) clears the composer.
-func TestEscArmingCancelConfirmationPreservesComposerDraft(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-	m.pending = true
-	m.activeRunID = 1
-	m.runCancel = func() {}
-	m.input.SetValue("draft prompt")
-
-	updated, _ := m.Update(testKey(tea.KeyEsc))
-	next := updated.(model)
-
-	if !next.cancelConfirmActive {
-		t.Fatal("first Esc should arm cancel confirmation")
-	}
-	if next.composerValue() != "draft prompt" {
-		t.Fatalf("first Esc should preserve the draft, got %q", next.composerValue())
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-
-	if next.pending {
-		t.Fatal("second Esc should cancel the pending run")
-	}
-	if next.composerValue() != "" {
-		t.Fatalf("the confirming second Esc should clear the draft, got %q", next.composerValue())
-	}
-}
-
-// TestPasteDisarmsCancelConfirmation: a paste isn't a keypress, so it never
-// went through the generic "any non-Esc key disarms it" hook. Pasting is a
-// deliberate action just like typing or clicking — it must disarm a stale
-// confirmation too, or a later, unrelated Esc could silently cancel the run.
-func TestPasteDisarmsCancelConfirmation(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-	cancelled := false
-	m.pending = true
-	m.activeRunID = 1
-	m.runCancel = func() { cancelled = true }
-
-	updated, _ := m.Update(testKey(tea.KeyEsc))
-	next := updated.(model)
-	if !next.cancelConfirmActive {
-		t.Fatal("first Esc should arm cancel confirmation")
-	}
-
-	updated, _ = next.Update(testPaste("pasted text"))
-	next = updated.(model)
-	if next.cancelConfirmActive {
-		t.Fatal("a paste should disarm the stale cancel confirmation")
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-	if cancelled {
-		t.Fatal("Esc after a paste should re-arm, not immediately cancel")
-	}
-	if !next.cancelConfirmActive {
-		t.Fatal("Esc after a paste should arm a fresh confirmation")
-	}
-}
-
-func TestEscCancelConfirmationExpires(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-	m.pending = true
-	m.activeRunID = 1
-	m.runCancel = func() {}
-
-	updated, _ := m.Update(testKey(tea.KeyEsc))
-	next := updated.(model)
-	seq := next.cancelConfirmSeq
-
-	updated, _ = next.Update(cancelConfirmExpiredMsg{seq: seq - 1})
-	next = updated.(model)
-	if !next.cancelConfirmActive {
-		t.Fatal("stale expiry should not clear active cancel confirmation")
-	}
-
-	updated, _ = next.Update(cancelConfirmExpiredMsg{seq: seq})
-	next = updated.(model)
-	if next.cancelConfirmActive {
-		t.Fatal("matching expiry should clear cancel confirmation")
-	}
-	if !next.pending {
-		t.Fatal("expiring the confirmation should not cancel the run")
-	}
-}
-
-// TestEscCancelConfirmationDisarmsOnInterveningKey mirrors
-// TestCtrlCExitConfirmationDisarmsOnInterveningKey: an intervening key other
-// than Esc (typing, Ctrl+O, etc.) means the user moved on to something else,
-// so a later, unrelated Esc must arm a fresh confirmation instead of
-// silently cancelling off a stale press from seconds ago.
-func TestEscCancelConfirmationDisarmsOnInterveningKey(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-	cancelled := false
-	m.pending = true
-	m.activeRunID = 1
-	m.runCancel = func() { cancelled = true }
-
-	updated, _ := m.Update(testKey(tea.KeyEsc))
-	next := updated.(model)
-	if !next.cancelConfirmActive {
-		t.Fatal("first Esc should arm cancel confirmation")
-	}
-	seq := next.cancelConfirmSeq
-
-	updated, _ = next.Update(testKey('h'))
-	next = updated.(model)
-	if next.cancelConfirmActive {
-		t.Fatal("an intervening non-Esc key should disarm cancel confirmation")
-	}
-	if next.cancelConfirmSeq == seq {
-		t.Fatal("disarming should advance the sequence so a stale expiry tick is ignored")
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-	if cancelled {
-		t.Fatal("Esc after an intervening key should re-arm, not cancel")
-	}
-	if !next.cancelConfirmActive {
-		t.Fatal("Esc after an intervening key should arm a fresh confirmation")
-	}
-}
-
-// TestEscCancelConfirmationDisarmsWhenStolenByAskUser: a mid-turn ask_user
-// prompt lands between the two Esc presses. The user's second Esc denies the
-// questionnaire (an earlier branch in the Esc handler), not a confirm, so it
-// must not leave cancelConfirmActive armed for a later, unrelated Esc to
-// silently cancel the run.
-func TestEscCancelConfirmationDisarmsWhenStolenByAskUser(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-	cancelled := false
-	m.pending = true
-	m.activeRunID = 1
-	m.runCancel = func() { cancelled = true }
-
-	updated, _ := m.Update(testKey(tea.KeyEsc))
-	next := updated.(model)
-	if !next.cancelConfirmActive {
-		t.Fatal("first Esc should arm cancel confirmation")
-	}
-
-	request := agent.AskUserRequest{Questions: []agent.AskUserQuestion{{Question: "name?"}}}
-	next.pendingAskUser = &pendingAskUserPrompt{
-		request: request,
-		answer:  func([]string) {},
-		states:  newAskUserStates(request.Questions),
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-	if cancelled {
-		t.Fatal("an Esc consumed by the ask-user prompt must not cancel the run")
-	}
-	if next.cancelConfirmActive {
-		t.Fatal("an Esc consumed by the ask-user prompt must disarm the stale cancel confirmation")
-	}
-
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
-	if cancelled {
-		t.Fatal("the next Esc should arm a fresh confirmation, not immediately cancel")
-	}
-	if !next.cancelConfirmActive {
-		t.Fatal("the next Esc should arm a fresh confirmation")
-	}
 }
 
 func TestAgentResponseCompletesStuckPlan(t *testing.T) {

internal/tui/mouse.go

@@ -40,15 +40,6 @@ func (m model) handleMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 	if m.providerWizard != nil && m.providerWizard.oauthPending {
 		return m, nil
 	}
-	// A click is a deliberate action, same as a keypress — it means the user
-	// moved on to something else, so it disarms a stale Esc cancel-confirmation
-	// rather than leaving it armed for some later, unrelated Esc to act on.
-	// Scoped to actual clicks (not hover/motion/wheel), since motion events fire
-	// continuously while the mouse merely sits over the terminal and would
-	// otherwise defeat the confirmation window on every render tick.
-	if mouseLeftPress(msg) || mouseRightPress(msg) {
-		m = m.disarmCancelConfirmation()
-	}
 	// A right-click pastes the clipboard straight into the focused field — no
 	// menu. pasteFromClipboardCmd reads the clipboard off the Update goroutine; the
 	// clipboardReadMsg result is routed by routePaste to wherever input is focused

internal/tui/oauth_device.go

@@ -44,9 +44,6 @@ func oauthDevicePrepare(name string) (oauth.DeviceAuth, oauth.Config, error) {
 		Store:       store,
 		HTTPClient:  &http.Client{Timeout: 60 * time.Second},
 		OpenBrowser: browser.OpenURL,
-		// Device-flow providers (e.g. Hugging Face) rely on the baked-in preset for
-		// their endpoints; opt in so the device code can be requested.
-		AllowPresets: true,
 	})
 	if err != nil {
 		return oauth.DeviceAuth{}, oauth.Config{}, err
@@ -65,9 +62,8 @@ func oauthDeviceComplete(name string, cfg oauth.Config, auth oauth.DeviceAuth) e
 		return err
 	}
 	manager, err := oauth.NewManager(oauth.ManagerOptions{
-		Store:        store,
-		HTTPClient:   &http.Client{Timeout: 60 * time.Second},
-		AllowPresets: true, // preset config is needed to poll/exchange the device token
+		Store:      store,
+		HTTPClient: &http.Client{Timeout: 60 * time.Second},
 	})
 	if err != nil {
 		return err
@@ -88,9 +84,8 @@ func oauthStoredToken(ctx context.Context, providerID string) string {
 		return ""
 	}
 	manager, err := oauth.NewManager(oauth.ManagerOptions{
-		Store:        store,
-		HTTPClient:   &http.Client{Timeout: 30 * time.Second},
-		AllowPresets: true, // refreshing a preset-provider token re-resolves its config
+		Store:      store,
+		HTTPClient: &http.Client{Timeout: 30 * time.Second},
 	})
 	if err != nil {
 		return ""

internal/tui/options.go

@@ -20,33 +20,32 @@ import (
 
 // Options configures the reusable Zero terminal UI shell.
 type Options struct {
-	Cwd                         string
-	UserConfigPath              string
-	DoctorUserConfigPath        string
-	ProjectConfigPath           string
-	ProviderName                string
-	ModelName                   string
-	ProviderProfile             config.ProviderProfile
-	SavedProviders              []config.ProviderProfile // all configured providers, for the /model multi-provider list
-	FavoriteModels              []string
-	RecapsEnabled               bool
-	Provider                    zeroruntime.Provider
-	NewProvider                 func(config.ProviderProfile) (zeroruntime.Provider, error)
-	ProbeProviderHealth         func(context.Context, providerhealth.Options) providerhealth.Result
-	DiscoverProviderModels      func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
-	DiscoverOllamaContextWindow func(ctx context.Context, baseURL string, model string) (int, error)
-	RuntimeMessageSink          func(tea.Msg)
-	Registry                    *tools.Registry
-	SessionStore                *sessions.Store
-	SandboxStore                *sandbox.GrantStore
-	MCPConfig                   config.MCPConfig
-	MCPPermissionStore          *mcp.PermissionStore
-	MCPTokenStore               *mcp.TokenStore
-	MCPCommand                  func(context.Context, []string) MCPCommandResult
-	SandboxSetupCommand         func(context.Context) SandboxSetupCommandResult
-	UsageTracker                *usage.Tracker
-	SessionCompactor            SessionCompactor
-	PrService                   *PrService
+	Cwd                    string
+	UserConfigPath         string
+	DoctorUserConfigPath   string
+	ProjectConfigPath      string
+	ProviderName           string
+	ModelName              string
+	ProviderProfile        config.ProviderProfile
+	SavedProviders         []config.ProviderProfile // all configured providers, for the /model multi-provider list
+	FavoriteModels         []string
+	RecapsEnabled          bool
+	Provider               zeroruntime.Provider
+	NewProvider            func(config.ProviderProfile) (zeroruntime.Provider, error)
+	ProbeProviderHealth    func(context.Context, providerhealth.Options) providerhealth.Result
+	DiscoverProviderModels func(context.Context, config.ProviderProfile) ([]providermodeldiscovery.Model, error)
+	RuntimeMessageSink     func(tea.Msg)
+	Registry               *tools.Registry
+	SessionStore           *sessions.Store
+	SandboxStore           *sandbox.GrantStore
+	MCPConfig              config.MCPConfig
+	MCPPermissionStore     *mcp.PermissionStore
+	MCPTokenStore          *mcp.TokenStore
+	MCPCommand             func(context.Context, []string) MCPCommandResult
+	SandboxSetupCommand    func(context.Context) SandboxSetupCommandResult
+	UsageTracker           *usage.Tracker
+	SessionCompactor       SessionCompactor
+	PrService              *PrService
 
 	AgentOptions    agent.Options
 	PermissionMode  agent.PermissionMode

internal/tui/picker.go

@@ -565,46 +565,6 @@ type modelPickerModelsDiscoveredMsg struct {
 	err        error
 }
 
-// ollamaContextWindowDiscoveredMsg carries the result of an async /api/show
-// probe against a local Ollama daemon (see ollamaContextWindowDiscoveryCmd).
-// A zero contextWindow (or a non-nil err) means the probe found nothing
-// usable and the map is left untouched, not zeroed out.
-type ollamaContextWindowDiscoveredMsg struct {
-	modelName     string
-	contextWindow int
-	err           error
-}
-
-// ollamaContextWindowDiscoveryCmd probes a local Ollama daemon's native
-// /api/show endpoint for modelName's context length. Scoped to the local
-// Ollama provider only (catalog ID "ollama", not "ollama-cloud" — a
-// different hosted service this endpoint isn't assumed to exist on): the
-// generic /v1/models discovery has no source for this metadata for
-// custom/local model tags, so without this the context gauge just never
-// shows for them (see modelContextWindow).
-func (m model) ollamaContextWindowDiscoveryCmd(descriptor providercatalog.Descriptor, baseURL string, modelName string) tea.Cmd {
-	if descriptor.ID != "ollama" {
-		return nil
-	}
-	modelName = strings.TrimSpace(modelName)
-	baseURL = strings.TrimSpace(baseURL)
-	if modelName == "" || baseURL == "" {
-		return nil
-	}
-	discover := m.discoverOllamaContextWindow
-	if discover == nil {
-		discover = func(ctx context.Context, baseURL string, model string) (int, error) {
-			return providermodeldiscovery.DiscoverOllamaContextWindow(ctx, baseURL, model, providermodeldiscovery.Options{})
-		}
-	}
-	return func() tea.Msg {
-		ctx, cancel := context.WithTimeout(m.ctx, 8*time.Second)
-		defer cancel()
-		window, err := discover(ctx, baseURL, modelName)
-		return ollamaContextWindowDiscoveredMsg{modelName: modelName, contextWindow: window, err: err}
-	}
-}
-
 func (m model) normalizeProfileForProvider(provider providercatalog.Descriptor) config.ProviderProfile {
 	profile := m.providerProfile
 	normalizeIdentity := profileMatchesProviderBaseURL(profile, provider) ||

internal/tui/picker_test.go

@@ -14,7 +14,6 @@ import (
 
 	"github.com/Gitlawb/zero/internal/config"
 	"github.com/Gitlawb/zero/internal/modelregistry"
-	"github.com/Gitlawb/zero/internal/providercatalog"
 	"github.com/Gitlawb/zero/internal/providermodeldiscovery"
 	"github.com/Gitlawb/zero/internal/zeroruntime"
 )
@@ -879,100 +878,4 @@ func TestModelContextWindowResolution(t *testing.T) {
 	if got := m.modelContextWindow(""); got != 0 {
 		t.Fatalf("empty model name should yield 0, got %d", got)
 	}
-	// A custom/local Ollama model tag has no curated-catalog entry and its
-	// generic /v1/models listing carries no window either — the only source is
-	// the Ollama-specific /api/show probe, landed via ollamaContextWindowByModel.
-	m.ollamaContextWindowByModel = map[string]int{"kimi-k2.7-code:cloud": 131072}
-	if got := m.modelContextWindow("kimi-k2.7-code:cloud"); got != 131072 {
-		t.Fatalf("ollama-discovered window should be used for an unregistered model, got %d", got)
-	}
-}
-
-// TestOllamaContextWindowDiscoveryCmdScopedToLocalOllama: the /api/show probe
-// only makes sense against a local Ollama daemon (catalog ID "ollama") — a
-// different provider like "ollama-cloud" is a distinct hosted service this
-// endpoint isn't assumed to exist on, and every other provider already has
-// its context window covered by the curated catalog or /v1/models discovery.
-func TestOllamaContextWindowDiscoveryCmdScopedToLocalOllama(t *testing.T) {
-	m := model{ctx: context.Background()}
-
-	ollama, ok := providercatalog.Get("ollama")
-	if !ok {
-		t.Fatal("expected \"ollama\" to be a registered catalog descriptor")
-	}
-	if cmd := m.ollamaContextWindowDiscoveryCmd(ollama, "http://localhost:11434/v1", "kimi-k2.7-code:cloud"); cmd == nil {
-		t.Fatal("expected a discovery command for the local ollama provider")
-	}
-
-	ollamaCloud, ok := providercatalog.Get("ollama-cloud")
-	if !ok {
-		t.Fatal("expected \"ollama-cloud\" to be a registered catalog descriptor")
-	}
-	if cmd := m.ollamaContextWindowDiscoveryCmd(ollamaCloud, "https://ollama.com/v1", "qwen3-coder:480b"); cmd != nil {
-		t.Fatal("ollama-cloud is a different hosted service; must not probe /api/show against it")
-	}
-
-	if cmd := m.ollamaContextWindowDiscoveryCmd(ollama, "", "kimi-k2.7-code:cloud"); cmd != nil {
-		t.Fatal("an empty base URL should yield no command")
-	}
-	if cmd := m.ollamaContextWindowDiscoveryCmd(ollama, "http://localhost:11434/v1", ""); cmd != nil {
-		t.Fatal("an empty model name should yield no command")
-	}
-}
-
-// TestOllamaContextWindowDiscoveredMsgPopulatesMap verifies the Update()
-// handler for the async probe's result actually reaches modelContextWindow's
-// fallback source, and that a failed/zero probe leaves the map untouched
-// rather than caching a bogus zero.
-func TestOllamaContextWindowDiscoveredMsgPopulatesMap(t *testing.T) {
-	m := newModel(context.Background(), Options{})
-
-	updated, cmd := m.Update(ollamaContextWindowDiscoveredMsg{modelName: "kimi-k2.7-code:cloud", contextWindow: 131072})
-	next := updated.(model)
-	if cmd != nil {
-		t.Fatal("applying a discovered window should not schedule further work")
-	}
-	if got := next.modelContextWindow("kimi-k2.7-code:cloud"); got != 131072 {
-		t.Fatalf("modelContextWindow after discovery = %d, want 131072", got)
-	}
-
-	updated, _ = next.Update(ollamaContextWindowDiscoveredMsg{modelName: "other-model", contextWindow: 0, err: errors.New("boom")})
-	next = updated.(model)
-	if got := next.modelContextWindow("other-model"); got != 0 {
-		t.Fatalf("a failed probe must not populate a window, got %d", got)
-	}
-}
-
-// TestSwitchProviderModelWarmsDiscoveryForTheNewProvider: switching providers
-// mid-session (e.g. via the /model picker) previously fired no discovery at
-// all for the newly active provider — Init() only warms the provider active
-// at launch — so the context gauge stayed blank for the rest of the session
-// unless /model happened to be reopened separately. Switching to Ollama
-// specifically must also warm the /api/show probe, the only source of a
-// context window for custom/local Ollama models.
-func TestSwitchProviderModelWarmsDiscoveryForTheNewProvider(t *testing.T) {
-	m := newModel(context.Background(), Options{
-		ProviderName:    "openai",
-		ModelName:       "gpt-5.1",
-		Provider:        &fakeProvider{},
-		ProviderProfile: config.ProviderProfile{Name: "openai", CatalogID: "openai", Model: "gpt-5.1"},
-		SavedProviders: []config.ProviderProfile{
-			{Name: "openai", CatalogID: "openai", Model: "gpt-5.1"},
-			{Name: "ollama", CatalogID: "ollama", ProviderKind: config.ProviderKindOpenAICompatible, BaseURL: "http://localhost:11434/v1", Model: "kimi-k2.7-code:cloud"},
-		},
-		NewProvider: func(config.ProviderProfile) (zeroruntime.Provider, error) {
-			return &fakeProvider{}, nil
-		},
-	})
-
-	next, text, cmd := m.switchProviderModel("ollama", "kimi-k2.7-code:cloud")
-	if !strings.Contains(text, "Switched to ollama") {
-		t.Fatalf("switch notice = %q, want it to confirm the switch", text)
-	}
-	if next.modelName != "kimi-k2.7-code:cloud" || next.providerName != "ollama" {
-		t.Fatalf("model/provider not switched: modelName=%q providerName=%q", next.modelName, next.providerName)
-	}
-	if cmd == nil {
-		t.Fatal("switching to ollama should warm both the generic and ollama-specific discovery commands")
-	}
 }

internal/tui/provider_wizard.go

@@ -166,10 +166,6 @@ func runProviderTokenLogin(name string) error {
 		Store:       store,
 		HTTPClient:  &http.Client{Timeout: 60 * time.Second},
 		OpenBrowser: browser.OpenURL,
-		// The user explicitly chose to sign in with this provider's OAuth, so opt
-		// into its baked-in preset (e.g. xAI's public client_id); without this the
-		// config never resolves and the browser never opens.
-		AllowPresets: true,
 	})
 	if err != nil {
 		return err
@@ -1233,29 +1229,9 @@ func (wizard *providerWizardState) renderProviderStep(width int) []string {
 	for offset, provider := range wizard.providers[start : start+maxVisible] {
 		lines = append(lines, wizard.renderSelectableProvider(width, start+offset, provider))
 	}
-	// A failed OAuth attempt leaves the wizard on this list (it does not advance),
-	// so the error must render here or the click looks like a silent no-op. The
-	// credential step renders its own copy for the ctrl+o path.
-	if wizard.oauthMode && wizard.oauthErr != "" {
-		lines = append(lines, "", zeroTheme.red.Render("OAuth login failed: "+wizard.oauthErr))
-		if hint := providerWizardOAuthErrHint(wizard.currentProvider()); hint != "" {
-			lines = append(lines, zeroTheme.faint.Render(hint))
-		}
-	}
 	return lines
 }
 
-// providerWizardOAuthErrHint returns a provider-specific next step for a failed
-// OAuth login. Hugging Face ships no public client_id (unlike xAI), so a login
-// can only work once the operator registers an app and supplies its client_id.
-func providerWizardOAuthErrHint(provider providercatalog.Descriptor) string {
-	if strings.EqualFold(provider.ID, "huggingface") {
-		return "Hugging Face needs your own app: create one at " +
-			"https://huggingface.co/settings/applications/new, then set ZERO_OAUTH_HUGGINGFACE_CLIENT_ID."
-	}
-	return ""
-}
-
 func (wizard *providerWizardState) renderSelectableProvider(width int, index int, provider providercatalog.Descriptor) string {
 	selected := index == wizard.selectedProvider
 	surface := transparentSurface

internal/tui/provider_wizard_oauth_test.go

@@ -125,36 +125,6 @@ func TestProviderWizardDeviceCodeMsgShowsCodeAndPolls(t *testing.T) {
 	}
 }
 
-// A failed OAuth attempt leaves the wizard on the provider list; the error must be
-// rendered there (not just on the credential step) so a click isn't a silent
-// no-op, and Hugging Face gets an actionable client_id hint.
-func TestProviderStepSurfacesOAuthError(t *testing.T) {
-	m := mouseTestModel()
-	m.providerWizard = m.newProviderWizard()
-	wizard := m.providerWizard
-	wizard.oauthMode = true
-	wizard.providers = providerWizardOAuthDescriptors()
-	found := false
-	for i, p := range wizard.providers {
-		if strings.EqualFold(p.ID, "huggingface") {
-			wizard.selectedProvider = i
-			found = true
-		}
-	}
-	if !found {
-		t.Fatal("huggingface should be an OAuth-capable provider")
-	}
-	wizard.oauthErr = `oauth: provider "huggingface" is not configured; set ZERO_OAUTH_HUGGINGFACE_CLIENT_ID`
-
-	view := strings.Join(wizard.renderProviderStep(72), "\n")
-	if !strings.Contains(view, "OAuth login failed") {
-		t.Fatalf("provider step should surface the OAuth error:\n%s", view)
-	}
-	if !strings.Contains(view, "huggingface.co/settings/applications/new") {
-		t.Fatalf("Hugging Face hint should point at app registration:\n%s", view)
-	}
-}
-
 func TestProviderWizardDeviceErrorSurfaced(t *testing.T) {
 	m := mouseTestModel()
 	m.providerWizard = m.newProviderWizard()

internal/tui/queued_message_test.go

@@ -55,38 +55,6 @@ func TestQueuedPromptPreviewAppearsInView(t *testing.T) {
 	}
 }
 
-// TestQueuedPromptPreviewSitsAboveComposer: the queued-message preview must
-// render ABOVE the input box, not below it — a message waiting to send should
-// sit on top of what you're currently typing.
-func TestQueuedPromptPreviewSitsAboveComposer(t *testing.T) {
-	m := newQueuedMessageTestModel(t)
-	m.pending = true
-	m.activeRunID = 1
-	m.runID = 1
-	m.width = 96
-	m.input.SetValue("summarize the failing test output")
-	updated, _ := m.Update(testKey(tea.KeyEnter))
-	next := updated.(model)
-
-	footer := plainRender(t, next.footerView(96))
-	lines := strings.Split(footer, "\n")
-	queuedLine, composerTopLine := -1, -1
-	for i, ln := range lines {
-		if queuedLine < 0 && strings.Contains(ln, "queued") {
-			queuedLine = i
-		}
-		if composerTopLine < 0 && strings.Contains(ln, "╭") { // composer box top border
-			composerTopLine = i
-		}
-	}
-	if queuedLine < 0 || composerTopLine < 0 {
-		t.Fatalf("expected both a queued line and a composer box; queued=%d composer=%d\n%s", queuedLine, composerTopLine, footer)
-	}
-	if queuedLine >= composerTopLine {
-		t.Fatalf("queued preview (line %d) must sit ABOVE the composer box top border (line %d):\n%s", queuedLine, composerTopLine, footer)
-	}
-}
-
 func TestAgentResponseLaunchesQueuedPrompt(t *testing.T) {
 	provider := &scriptedProvider{scripts: [][]zeroruntime.StreamEvent{{
 		{Type: zeroruntime.StreamEventText, Content: "queued answer"},

internal/tui/rendering.go

@@ -36,7 +36,7 @@ func pickerBusyText(name string) string {
 			Title: "Busy",
 			Lines: []string{"Can't change " + label + " while a run is in progress."},
 		}},
-		Hints: []string{"press Esc twice to cancel the run, then try again"},
+		Hints: []string{"press Esc to cancel the run, then try again"},
 	})
 }
 

internal/tui/session_test.go

@@ -775,8 +775,6 @@ func TestEscCancelRecordsSessionError(t *testing.T) {
 		t.Fatal("expected prompt submit to start an agent run")
 	}
 
-	updated, _ = next.Update(testKey(tea.KeyEsc))
-	next = updated.(model)
 	updated, _ = next.Update(testKey(tea.KeyEsc))
 	next = updated.(model)
 
@@ -838,10 +836,7 @@ func TestCancelledRunFlushesCheckpointSessionEvents(t *testing.T) {
 		next = updated.(model)
 		if _, ok := runtimeMsg.(permissionRequestMsg); ok {
 			// Cancel mid-run via Esc while the permission prompt is pending: this
-			// unblocks the goroutine through ctx cancellation. Esc now requires a
-			// second press within the confirmation window to actually cancel.
-			updated, _ = next.Update(testKey(tea.KeyEsc))
-			next = updated.(model)
+			// unblocks the goroutine through ctx cancellation.
 			updated, _ = next.Update(testKey(tea.KeyEsc))
 			next = updated.(model)
 			cancelled = true

internal/tui/view.go

@@ -201,9 +201,6 @@ func (m model) statusLine(width int) string {
 		if m.exitConfirmActive {
 			return fitStyledLine(prefix+zeroTheme.amber.Render("●")+" "+zeroTheme.amber.Render(ctrlCExitConfirmText), width)
 		}
-		if m.cancelConfirmActive {
-			return fitStyledLine(prefix+zeroTheme.amber.Render("●")+" "+zeroTheme.amber.Render(escCancelConfirmText), width)
-		}
 		return fitStyledLine(left, width)
 	}
 
@@ -213,8 +210,6 @@ func (m model) statusLine(width int) string {
 	}
 	if m.exitConfirmActive {
 		left = prefix + zeroTheme.amber.Render("●") + " " + zeroTheme.amber.Render(ctrlCExitConfirmText)
-	} else if m.cancelConfirmActive {
-		left = prefix + zeroTheme.amber.Render("●") + " " + zeroTheme.amber.Render(escCancelConfirmText)
 	} else if summary := m.backgroundTerminalSummary(); summary != "" {
 		left += separator + zeroTheme.muted.Render(summary)
 	}
@@ -223,19 +218,15 @@ func (m model) statusLine(width int) string {
 	// Context-fill gauge: surface it down to the narrow tier (where it matters
 	// most), but skip it when the context sidebar is already showing the % so the
 	// figure isn't duplicated.
-	gaugeShown := false
 	if tier >= tierNarrow && !m.sidebarActive() {
 		if gauge := m.contextWindowSegment(); gauge != "" {
 			rightGroups = append(rightGroups, gauge)
-			gaugeShown = true
 		}
 	}
-	// The sidebar pins the token readout at its floor, and the gauge's "used"
-	// figure is the exact same number (both read latestUsageTokens) — either
-	// one showing means the plain usage segment must drop its own token count
-	// to just the cost, or the count renders twice side by side.
+	// The sidebar pins the token readout at its floor, so when it's open keep
+	// only the cost here — otherwise the token figure shows on both sides.
 	usage := m.usageStatusSegment()
-	if m.sidebarActive() || gaugeShown {
+	if m.sidebarActive() {
 		usage = m.usageCostSegment()
 	}
 	if usage != "" {

internal/tui/working_status_test.go

@@ -106,46 +106,6 @@ func TestQuietGenerationHint(t *testing.T) {
 	}
 }
 
-// TestQuietGenerationHintEscalatesPastHalfIdleTimeout: a heartbeating-but-
-// silent stream (chatgpt/gpt-5.x, ollama reasoning models — see
-// providerio.ErrStreamStalled) and a genuinely healthy-but-slow one look
-// identical under the plain "still generating… Xs" cue — the ticking number
-// is the only signal, whether real content is still coming or nothing ever
-// will. Past half the provider's idle timeout the cue must say so explicitly
-// and name when Zero's own content-stall watchdog will act, rather than
-// leaving the user to guess whether this is a hang.
-func TestQuietGenerationHintEscalatesPastHalfIdleTimeout(t *testing.T) {
-	// 30s idle timeout: half (15s) sits comfortably above quietWorkingHint (8s),
-	// leaving a clean window to observe the plain cue before it escalates.
-	t.Setenv("ZERO_STREAM_IDLE_TIMEOUT", "30s")
-	base := time.Date(2026, 6, 25, 12, 0, 0, 0, time.UTC)
-	m := model{now: func() time.Time { return base }}
-	m.activeRunID = 7
-	m.turnStartedAt = base
-
-	// Quiet past quietWorkingHint but under half the (30s) idle timeout -> the
-	// plain cue, same as TestQuietGenerationHint's normal case.
-	m.lastStreamActivity = base.Add(-10 * time.Second)
-	got := m.quietGenerationHint()
-	if !strings.Contains(got, "still generating") {
-		t.Fatalf("under half the idle timeout: want the plain cue, got %q", got)
-	}
-	if strings.Contains(got, "auto-recover") {
-		t.Fatalf("under half the idle timeout: should not have escalated yet, got %q", got)
-	}
-
-	// Quiet for >= half the idle timeout -> escalates to name the watchdog and
-	// its ceiling (providerio.ContentStallTimeout(30s) = 30s*1.2 = 36s here).
-	m.lastStreamActivity = base.Add(-15 * time.Second)
-	got = m.quietGenerationHint()
-	if !strings.Contains(got, "unusually quiet") || !strings.Contains(got, "auto-recover") {
-		t.Fatalf("past half the idle timeout: want an escalated cue naming the watchdog, got %q", got)
-	}
-	if !strings.Contains(got, "36s") {
-		t.Fatalf("escalated cue should name the content-stall ceiling (ContentStallTimeout(30s) = 36s), got %q", got)
-	}
-}
-
 // TestQuietHintHiddenWhenSidebarShowsIt: when the context sidebar is up (it
 // carries the "generating…" pulse in ACTIVITY), the working line must NOT also
 // show the hint — it appears in exactly one place.

release-please-config.json

@@ -1,12 +0,0 @@
-{
-  "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json",
-  "release-type": "node",
-  "include-component-in-tag": false,
-  "bootstrap-sha": "02f0c0929bec65f5fc41bdcab3eb518d2b0b329a",
-  "packages": {
-    ".": {
-      "package-name": "@gitlawb/zero",
-      "release-as": "0.1.0"
-    }
-  }
-}