84 files spanning provider capabilities, model routing, headless
runtime, sf auto subsystems, gitbook docs, and test coverage. Snapshotted
so headless auto can resume M004 (Production Readiness) S03
(Verification Gate Validation) on a clean tree.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pi-mono Tier 0 #4 — manual port (sf went off-task; ported directly).
undici's default 300s bodyTimeout aborts long local-LLM SSE streams
(e.g. vLLM buffering a large tool call) with UND_ERR_BODY_TIMEOUT.
retry.provider.timeoutMs cannot lift this cap — it controls the
provider SDK's AbortController, not undici's per-socket idle timer.
Pass {bodyTimeout: 0, headersTimeout: 0} to EnvHttpProxyAgent. Provider
SDKs continue to enforce their own deadlines.
Type-check passes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pi-mono Tier 0 #2 — sf-driven port of PR #3650.
Some LLM providers reject API calls when `tools: []` is sent (an empty
array), but accept the call when the tools field is omitted entirely.
This guards each provider's request-body builder to omit `tools` when
the tool list is empty, instead of serialising the empty array.
Files (5 provider builders):
- packages/pi-ai/src/providers/openai-completions.ts
- packages/pi-ai/src/providers/openai-responses.ts
- packages/pi-ai/src/providers/openai-codex-responses.ts
- packages/pi-ai/src/providers/azure-openai-responses.ts
- packages/pi-ai/src/providers/anthropic-shared.ts (covers anthropic
and anthropic-vertex which both import buildParams from it)
Pattern: `if (context.tools)` → `if (context.tools && context.tools.length > 0)`.
Preserved: the `else if (hasToolHistory(context.messages))` branch in
openai-completions.ts that intentionally emits `tools: []` for
LiteLLM/Anthropic-proxy compatibility is unchanged.
Type-check passes.
Co-Authored-By: sf v2.75.1 (session 38ed0a48)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pi-mono Tier 0 #1 (security) — sf-driven port.
Two upstream security fixes (pi-mono PR #3819, #3883) that escape
user-controlled session content before embedding in HTML exports.
Crafted session content (image mime types, image data, model IDs,
tool names, entry IDs) could otherwise inject markup at the export
boundary.
What sf changed in
packages/pi-coding-agent/src/core/export-html/template.js:
- Image tags: escape `mimeType` and `data` attributes for both
tool-result and user-message image renders (PR #3819).
- Session metadata: escape `msg.toolName`, `msg.role`, `entry.modelId`,
`entry.thinkingLevel`, `entry.type`, `entry.id`, and
`globalStats.models` (PR #3883).
- DOM id construction: renamed `entryId` → `entryDomId` and escape
`entry.id` to prevent attribute-breakout from a crafted id.
The existing `escapeHtml()` helper was used at every site; no new
helper introduced. Type-check passes.
Co-Authored-By: sf v2.75.1 (session 150fe2c1)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Pi-mono Tier 0 #5 — first sf-driven port. sf-from-source dispatched the
task in print mode and produced this fix autonomously.
Adds getModelMatchCandidates(modelId, modelName?) helper that normalizes
both inputs to lowercase and dash-separated form
(s.replace(/[\s_.:]+/g, "-")). Inference profile ARNs don't embed the
model name; the helper lets capability checks match against either the
inference profile ARN or the underlying model name.
Updated:
- supportsAdaptiveThinking — uses the helper; consolidates the
opus-4.6/opus-4-6 dot-vs-dash variants.
- mapThinkingLevelToEffort — same pattern.
- supportsPromptCaching — same pattern (also from pi-mono PR #3527).
- streamSimpleBedrock and buildAdditionalModelRequestFields — pass
model.name through to capability checks.
Type-check passes (cd packages/pi-ai && npx tsc --noEmit).
Co-Authored-By: sf v2.75.1 (session 911dd2de)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds direct xiaomi token-plan API access alongside the existing
OpenRouter-routed xiaomi entries. ADDITIVE only — OpenRouter cleanup is
a separate follow-up.
Three new region providers:
- xiaomi-token-plan-ams (Amsterdam, default for plain `xiaomi`)
- xiaomi-token-plan-sgp (Singapore)
- xiaomi-token-plan-cn (China)
All use Anthropic Messages API. Env-var resolution: XIAOMI_API_KEY →
XIAOMI_TOKEN_PLAN_API_KEY → MIMO_API_KEY (in that fallback order).
Three xiaomi MiMo models registered under each direct provider:
- mimo-v2-flash (256k ctx, 64k output, text-only, reasoning)
- mimo-v2-omni (256k ctx, 128k output, text+image, reasoning)
- mimo-v2-pro (1M ctx, 128k output, text-only, reasoning)
Same model literals × 4 provider keys, different baseUrls per region.
Test count assertion bumped 22 → 26 providers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two codex-rescue tasks landed together:
1. Auto-coerce JSON-schema validator: when a tool field declares
{type:"array", items:{type:"string"}} and the model sends a single
string, wrap it in [string] before validation instead of hard-rejecting.
Fixes the recurring "keyDecisions: must be array" rejection on
sf_complete_task that wasted retries.
2. Provider_model_allow filter (proper implementation with helpers):
- resolveProviderModelAllowList / isProviderModelAllowed /
filterModelsByProviderModelAllow helpers in preferences-models
- Wired into model-registry and auto-model-selection
- New tests/provider-model-allow.test.ts
Tools coerced: sf_complete_task, sf_complete_milestone, sf_plan_milestone,
sf_plan_slice, sf_replan_slice, sf_reassess_roadmap (key list fields).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: OpenAI Codex <noreply@openai.com>
Cherry-pick of gsd-build/gsd-2 65ca5aa2e — applies the security hardening
hunks that conflicted minimally:
- mcp-server/env-writer: validate writes against a strict allowlist
- web/api/files: enforce path containment via web/lib/secure-path
- vscode-extension: read binaryPath/autoStart only from trusted
global/default scopes (resolveTrustedSfStartupConfig), avoiding
workspace-controlled override (renamed Gsd → Sf for sf naming)
- New regression tests: mcp-client-security, vscode-startup-security,
web-files-symlink
Skipped hunks (drifted): mcp-server/server.ts, mcp-client/index.ts,
mcp-server/README.md.
Co-Authored-By: Jeremy <jeremy@fluxlabs.net>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
reassess-roadmap: flip default from true → false. Most reassess units
conclude "roadmap is fine" burning a session for no change; the
plan-slice prompt now carries a JIT preamble at zero cost. (#4778)
tool-execution: always prefer toolDefinition.label when non-empty,
even when label === name — allows tools to display their canonical
name explicitly. (#4758)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Real bugs from 2nd-pass scan:
1. extension-registry.ts: discoverAllManifests skipped symlinked extension
dirs because Dirent.isDirectory() returns false for symlinks. Dev-workflow
symlinks under ~/.sf/agent/extensions/ were invisible to list/enable/
disable/info. Matches the regression documented in
symlink-extension-discovery.test.ts — the test inlines the correct logic,
but this callsite still had the buggy form. Now accepts isDirectory() ||
isSymbolicLink().
2. headless.ts SIGINT handler: client.stop() failures were double-silenced
(inner .catch(()=>{}), outer try{}catch{}). Interactive mode logs stop
errors to stderr. Restored head/headless parity — still fire-and-forget
(exit code is forced via process.exit) but failures are observable.
3. openai-codex-responses.ts SSE parser: malformed data frames were silently
dropped so broken streams looked identical to clean ones. Now debug-logs
the parse error with the chunk context so broken streams are
distinguishable in logs. Stream continues on bad chunk (one bad frame
shouldn't kill the whole generation).
4. web/cleanup-service.ts generated script: bare 'catch {}' around four native
git calls (nativeBranchList, nativeDetectMainBranch, nativeBranchListMerged,
nativeForEachRef). A failed main-branch detection silently left mainBranch
undefined-shaped, then the next native call operated on garbage. Now emits
console.warn so failures surface in the subprocess log.
5. web/undo-service.ts generated script: git revert failure was silenced;
when --no-commit failed, user saw commitsReverted=0 with no reason. Now
logs the revert error before attempting --abort (abort itself remains
best-effort silent).
False positives from the same scan (investigated and dismissed):
- auto-worktree.ts #2505: code uses ':(exclude).sf/milestones' pathspec +
shelter-and-restore, which is a better fix than the 'drop --include-untracked'
approach the test comment describes. Test comment is stale; source is correct.
- Lifecycle handler unhandled rejections across 5 extensions: extensions/runner.ts
already try/catches handler invocations and routes to emitError. Wrapping the
individual handlers would be redundant.
showDeprecationWarnings ran setRawMode(true)/once('data')/setRawMode(false)/
pause() right before pi-tui's own stdin setup. That handoff is fragile —
buffered bytes and mode flips between the migration prompt and the TUI's
raw-mode setup can leave stdin cooked and line-buffered, producing the
'Enter does nothing + garbled typing' symptom.
Warnings now print non-blocking. They stay visible in scrollback above
the TUI, so users still see them without a blocking acknowledge step.
RequestedThinkingLevel adds "auto" to the reasoning option. Each provider
handles it natively:
- Claude 4.x (anthropic/bedrock): adaptive thinking, no effort constraint
- Gemini 2.5 Pro/Flash (google/vertex/gemini-cli): THINKING_LEVEL_UNSPECIFIED
- GPT-5+ (openai-responses/azure): reasoning.effort omitted, model decides
- Kimi (kimi-coding): {"type":"enabled"} without budget_tokens via new
capabilities.thinkingNoBudget flag — model manages reasoning depth
- GLM (zai, thinkingFormat:zai): enable_thinking:true already correct
- MiniMax (anthropic API): explicit budget_tokens required, resolves to medium
ModelCapabilities.thinkingNoBudget: new flag for Anthropic-compatible providers
that accept {"type":"enabled"} without a budget (Kimi API).
models.generated.ts: add Kimi K2.6 (id: kimi-for-coding, beta API); add
thinkingNoBudget capability to all kimi-coding models.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
generate-models.ts now imports @google/gemini-cli-core's
VALID_GEMINI_MODELS set and iterates it to produce SF's google-gemini-cli
provider entries. Single source of truth: when Google ships a new Gemini
model, it lands in cli-core first, then flows into SF on
`npm update @google/gemini-cli-core` + `generate-models.ts` re-run —
no more hand-editing the generate script.
Before: 6 hardcoded entries (gemini-2.0/2.5/3 flash + pro preview, etc.)
After: 7 entries sourced dynamically, filtered to drop `-customtools`
variants which require a different tool protocol:
gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite,
gemini-3-pro-preview, gemini-3-flash-preview,
gemini-3.1-pro-preview, gemini-3.1-flash-lite-preview
Capability tagging uses cli-core's isProModel / isPreviewModel so
reasoning=true for pro + 3.x preview variants (excluding flash-lite).
Context-window / max-output-tokens kept in an SF-local override table
since cli-core doesn't publish those per-model.
Pre-existing 4 test failures (zai glm-5.1 x3, anthropic resolveBaseUrl
#4140) unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the handwritten fetch() + SSE-parsing + custom retry loop in
packages/pi-ai/src/providers/google-gemini-cli.ts with direct calls into
`CodeAssistServer.generateContentStream()` from @google/gemini-cli-core.
Requests to cloudcode-pa.googleapis.com are now byte-identical to what
the real `gemini` CLI sends — same User-Agent, same Client-Metadata,
same retry semantics — which preserves Google's subsidised free-OAuth
quota treatment and eliminates third-party-bot ban risk.
File size: 798 → 511 lines (~290 lines deleted net).
What went away:
- DEFAULT_ENDPOINT, GEMINI_CLI_HEADERS (cli-core sets these itself)
- MAX_RETRIES, BASE_DELAY_MS, MAX_EMPTY_STREAM_RETRIES, EMPTY_STREAM_BASE_DELAY_MS
- CLAUDE_THINKING_BETA_HEADER (was antigravity-only)
- extractRetryDelay(), isRetryableError(), extractErrorMessage(),
sleep() — cli-core handles 429/5xx retry with Retry-After honoured
- needsClaudeThinkingBetaHeader() — antigravity-only stub
- CloudCodeAssistRequest + CloudCodeAssistResponseChunk interfaces
(replaced by @google/genai's GenerateContentParameters +
GenerateContentResponse — already unwrapped by cli-core)
- ~200-line SSE body-reader block (response.body.getReader() + decoder
+ 'data:' line parsing) — cli-core yields parsed objects directly
- Empty-stream retry workaround — handled upstream now
What stayed (pure SF adapter code):
- convertMessages() → @google/genai Content[]
- convertTools() → functionDeclarations
- AssistantMessageEventStream — our event shape
- Part-by-part processing: text vs thinking blocks, function-call
translation to ToolCall, thoughtSignature retention, usage token
extraction
New helper:
- buildCodeAssistServer(token, projectId) constructs an OAuth2Client
(google-auth-library) seeded with the SF-cached access token and
wraps it in a CodeAssistServer instance. Ready for future promotion
to cli-core's getOauthClient() for full auto-refresh; today we
still pass the token through from SF's auth storage (Strategy A
from the plan doc).
Live verified end-to-end against gemini-2.5-flash using the user's
cached ~/.gemini/oauth_creds.json — got real streaming response,
correct stopReason, usage tokens accounted.
Models registry test updated from 23 → 22 providers (antigravity gone).
Remaining 4 pi-ai test failures are pre-existing and unrelated
(custom-zai glm-5.1, resolveAnthropicBaseUrl #4140).
Type note: cli-core bundles its own nested copy of @google/genai, so
TypeScript sees two structurally-identical Content types. Runtime is
fine; a single `as any` cast at the generateContentStream call site
handles the nominal split.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Continues the antigravity rip-out (previous commit covered SF + pi-coding-
agent UI layer). This commit removes the code from pi-ai:
- Delete packages/pi-ai/src/utils/oauth/google-antigravity.ts (313 lines)
- Update oauth/index.ts: drop antigravityOAuthProvider, refreshAntigravityToken,
loginAntigravity exports + registry entry. Add comment explaining why
(no vendor core lib + Google ban risk).
- google-gemini-cli.ts: strip ANTIGRAVITY_* constants, ANTIGRAVITY_ENDPOINT_FALLBACKS,
getAntigravityHeaders(), ANTIGRAVITY_SYSTEM_INSTRUCTION, and all
isAntigravity branching from streamGoogleGeminiCli + buildRequest.
File header rewritten. needsClaudeThinkingBetaHeader() collapses to
always-false (antigravity was the only path that needed it).
- google-shared.ts: strip stale Antigravity comments (file still shared
between google, google-gemini-cli, google-vertex).
- types.ts: drop "google-antigravity" from Api / KnownProvider union.
- models.generated.ts: remove google-antigravity provider block (~170 lines,
4 claude-* models that were only served via Antigravity).
- models.generated.test.ts: drop from expected-providers snapshot.
- scripts/generate-models.ts: remove antigravity model emission + context-
window override so future regenerations don't re-add it.
Reasoning (same as previous commit): Antigravity has no vendor-published
core library we can embed. Hand-rolled OAuth against
daily-cloudcode-pa.sandbox.googleapis.com was exactly the pattern
Google is banning for third-party tools. Removing it eliminates the
risk surface.
Breaking change: users with google-antigravity configured in their
models.* block will need to migrate to google-gemini-cli (OAuth via
the real `gemini` CLI), google (API key), or google-vertex (GCP auth).
Build passes. Next commit wires the google-gemini-cli provider to
@google/gemini-cli-core per the plan.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Antigravity (Google's IDE sandbox product, different from Gemini CLI) is
removed from:
src/onboarding.ts — drop from LLM_PROVIDER_IDS + OAuth-flow picker
src/pi-migration.ts — drop from LLM_PROVIDER_IDS migration list
src/web/onboarding-service.ts — drop from web-UI provider list
src/tests/integration/web-onboarding-contract.test.ts — update contract
src/resources/extensions/sf/doctor-providers.ts — drop from CLI_AUTH_PROVIDERS
src/resources/extensions/sf/key-manager.ts — drop UI listing
src/resources/extensions/sf-usage-bar/index.ts — delete entire quota fetcher block (~200 lines)
packages/pi-coding-agent/src/cli/args.ts — drop PI_AI_ANTIGRAVITY_VERSION doc
packages/pi-coding-agent/src/utils/proxy-server.ts — drop from claude provider chain
Reason: antigravity has no vendor-published core library we can embed
(unlike @google/gemini-cli-core for the Gemini CLI). Continuing to
hand-roll OAuth against daily-cloudcode-pa.sandbox.googleapis.com is
exactly the pattern Google has started banning for third-party tools.
Removing the code removes the ban risk.
pi-ai provider code, OAuth util, and models.generated entries for
google-antigravity are removed in follow-up commits (separated for
reviewability — each layer verified independently).
Build passes. Note: this is a breaking change for any user who had
google-antigravity configured — they'll need to migrate to
google-gemini-cli (OAuth), google (API key), or google-vertex.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Installs Google's official core library that powers the `gemini` CLI
binary. This is the first step of re-platforming pi-ai's
`google-gemini-cli` provider to use cli-core's transport instead of
handwritten fetch() calls against cloudcode-pa.googleapis.com.
Why:
- cli-core requests are byte-for-byte identical to the official
gemini CLI — preserves Google's subsidised free-OAuth quota and
eliminates bot-detection drift risk from our reverse-engineered
User-Agent / Client-Metadata headers.
- Auto-inherit upstream improvements (new tool formats, grounding,
session caching, quota displays) on `npm update`.
- The `genai-proxy` extension (localhost proxy for gemini-cli-format
clients) becomes "the CLI, but programmable" — same upstream
behavior, hookable SF routing underneath.
Auth model (unchanged for users):
- User runs the real `gemini` CLI once to OAuth; credentials land
in ~/.gemini/oauth_creds.json (or keychain on newer installs).
- SF reads those credentials via cli-core's own storage helpers;
no SF-side OAuth flow, no separate login.
Scope for this commit: dependency only. The transport refactor
(replacing the fetch() calls in google-gemini-cli.ts with
CodeAssistServer.generateContentStream()) is queued as the next
task and documented in google-gemini-cli-core-plan.md with a
detailed API map, two integration strategies (transport-only vs
full cli-core auth), and a step-by-step implementation checklist.
Note: this commit adds 66 transitive deps to pi-ai (ajv, zod,
glob, mime, open, etc.). google-antigravity provider stays on
handwritten code — different sandbox endpoints, different auth
contract, not in cli-core's scope.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Prior PROXY_FAMILY_PRIORITY table conflated "direct provider" with
"failover provider that happens to serve this family". Observed case:
claude-* family listed anthropic, google-antigravity, and
github-copilot all as "providers" — but only anthropic is the direct
vendor. google-antigravity re-serves Claude via Google's sandbox
IDE product (same endpoint as gemini-cli, different auth contract);
github-copilot re-serves via GitHub's paid platform.
This matters for the 429 fallback chain: a broken anthropic key
should try genuinely-vendored endpoints first (none, for Claude),
then fall into family_failover (antigravity, copilot), and only then
reach the generic GLOBAL_PROVIDER_FALLBACK (opencode, opencode-go,
openrouter, ollama-cloud). The old all-flat list hid this distinction.
New shape:
{ providers: [...], family_failover?: [...] }
Corrections applied:
claude-*: providers=[anthropic], failover=[google-antigravity, github-copilot]
gemini-*: providers=[google-gemini-cli, google, google-vertex],
failover=[github-copilot]
gpt-* / o* / codex-*: providers=[openai],
failover=[azure-openai-responses, openai-codex, github-copilot]
mimo-*: providers=[xiaomi] (new: was [] — Xiaomi MiMo Open Platform
is direct API at api.xiaomimimo.com / token-plan-sgp.xiaomimimo.com)
buildCandidateOrder stitches [direct, family_failover, global_fallback]
with deduplication. User overrides via settings.proxy.providerPriority
continue to replace only the direct-provider list, keeping family
failover and global fallback intact.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Four related improvements that landed in the working tree after the
auto-hardening merge but hadn't been committed:
1. auth_error as a distinct error type (auth-storage + retry-handler).
Previously invalid/expired API keys would retry the same failing
credential until the retry budget exhausted. Now:
- classifyErrorType() recognizes 401s, "invalid api key",
"authentication error", "unauthorized" etc as "auth_error"
- RetryHandler triggers cross-provider fallback on auth_error just
like it does for rate_limit and quota_exhausted — switch
providers rather than burning retries on a broken key
Outcome: a stale OPENCODE_API_KEY in sops now fails over to kimi or
minimax immediately instead of stalling the unit.
2. Multi-provider search-key detection (native-search.ts).
The "Web search: Set BRAVE_API_KEY" warning fired whenever a
non-Anthropic model lacked BRAVE_API_KEY, even when the user had
TAVILY_API_KEY or OLLAMA_API_KEY available. Now: the warning
suppresses if any of BRAVE/TAVILY/OLLAMA keys is present, and the
warning text lists all three options. Matches the preferences-
validation allow-list for search_provider.
3. MiniMax-M2.7-highspeed benchmark entry (model-benchmarks.json).
Routes the fast-tier variant of M2.7 through the Bayesian blender
with inherited RULER scores. Lets dynamic routing consider the
highspeed model when speed matters more than peak quality.
No regressions: the 41 pre-existing test failures in pi-coding-agent
(FallbackResolver chain-membership + LSP integration) are unchanged
relative to the prior commit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- compaction: fix repeated compaction dropping kept messages (#2608)
Re-summarize from previous compaction's firstKeptEntryId instead of
prevCompactionIndex+1; use buildSessionContext for accurate tokensBefore
- edit: add multi-edit support via edits[] array
Single call can update multiple disjoint regions in one file;
applyEditsToNormalizedContent matches all edits against original content
and applies in reverse order for stable offsets
- bash: persist full output when line-count truncation occurs (#2852)
ensureTempFile now called on any truncation, not only byte overflow;
prevents data loss when output exceeds line limit before byte threshold
- bash-executor: same fix for remote/operations-based execution
ensureTempFile includes SF cleanup registration (registerTempCleanup,
bashTempFiles tracking)
- grep: include lineText from rg JSON events to avoid per-match file reads
Eliminates stall when context=0 on broad searches (#3148)
- agent-session: forward isError override from afterToolCall extension hook
Allows extensions to change error status of tool results (#3051)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Anthropic OAuth was removed in v2.74.0 for TOS compliance (#3952). Users
who upgraded through that version still have type:"oauth" entries under
`anthropic` in auth.json which cannot resolve to a valid API key.
stale entry, so hasAuth("anthropic") kept reporting true and masked the
claude-code fallback path. Users had to hand-edit auth.json to recover.
Self-heal instead:
- AuthStorage.removeLegacyOAuthCredential(provider) strips only
type:"oauth" entries and preserves any api_key credentials.
- sdk.ts getApiKey() calls it when the legacy-OAuth branch triggers,
logs a one-line warning, and throws a message pointing the user at
the "claude-code" provider when the `claude` binary is in PATH, or
at ANTHROPIC_API_KEY otherwise.
Closes#4399
(cherry picked from commit b8ef6604617fda239a037cf5d5e6020b168d2e62)
ChatGPT-backed Codex sign-in no longer exposes the removed 5.1/5.2 Codex variants. Filter those models from openai-codex OAuth so GSD stops surfacing selections that immediately fail while leaving API-key-backed OpenAI models available.
(cherry picked from commit 1aedba583916826fc5c6129037f61e9802010e46)
