mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
* chore(release): open v3.8.21 development cycle
* fix: pass through valid max_tokens-truncated responses instead of fake 502 (#3572) (#3595)
* fix: /v1/completions returns legacy text-completion format, not chat (#3571) (#3596)
* fix: z.ai/GLM coding plan no longer shows Monthly 0% when no monthly cap (#3580) (#3597)
* docs: mark DISCOVERY_TOOL_DESIGN endpoints as Phase-2 not-yet-implemented (#3498) (#3599)
* fix(agent-bridge): add validate-only upstream-ca/test route (#3488) (#3600)
* fix(gamification): add level/badges/badges-earned profile routes (#3484)
* security(oauth): migrate 5 public client_ids to resolvePublicCred (#3493)
* fix(mcp): ship MCP server source closure in npm files + coverage gate (#3578)
* fix: add reasoning token buffer for combo routing (fixes #3587) (#3588)
Integrated into release/v3.8.21
* Refactor: Extract chatCore phases into modular files (#3598)
Integrated into release/v3.8.21 — chatCore phase modularization. Adjusted: re-derive idempotencyKey for the save path after the check moved into the module (co-authored). Thanks @oyi77!
* docs(changelog): credit #3598 (chatCore modularization) + #3588 (combo reasoning buffer)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(api): implement GET /api/guardrails + POST /api/guardrails/test, drop shadow/guardrails doc-fiction (#3496) (#3602)
Integrated into release/v3.8.21 — implements GET /api/guardrails + POST /api/guardrails/test, removes shadow/guardrails doc-fiction. TDD-validated (5/5) + check-docs-symbols/typecheck/eslint green.
* fix(gemini): isolate textual reasoning wrappers (#3605)
Split-out PR C from #3584. Isolates textual reasoning wrappers (<think>/<thinking>/<thought>/<internal_thought>, including malformed/open tags) into reasoning_content across both the non-streaming sanitizer and the Gemini streaming translator, with split-chunk buffering. Additive to the existing textual tool-call pipeline; does not touch the #3569 native functionResponse path. Integrated into release/v3.8.21. Thanks @dhaern!
* fix(antigravity): normalize Gemini 3.5 Flash tier IDs (#3603)
Split-out PR A from #3584. Normalizes the Antigravity/agy Gemini 3.5 Flash tier IDs to clean public names (gemini-3.5-flash-low/medium/high), maps them to the live upstream IDs at the executor boundary, and removes Antigravity from the global model resolver so the executor owns wire normalization. Maintainer follow-up: kept gemini-3.5-flash-preview as a hidden backward-compat alias routing to the High tier (so saved combos/configs keep working). Live-validated the tier set via the agy CLI catalog. Integrated into release/v3.8.21. Thanks @dhaern!
* fix(agent-bridge): surface real MITM startup-failure cause, not always port 443 (#3606) (#3608)
Integrated into release/v3.8.21 (#3606)
* fix(oauth): surface real Kiro import-token failure cause, not a bare 500 (#3589) (#3609)
Integrated into release/v3.8.21 (#3589)
* docs(opencode-provider): soft-deprecate in favor of @omniroute/opencode-plugin (#3419) (#3613)
Integrated into release/v3.8.21 (#3419)
* fix(usage): normalize Antigravity and agy provider quotas (#3604)
Split-out PR B from #3584. Normalizes Antigravity/agy provider quotas: prefers retrieveUserQuota for live consumption, falls back to fetchAvailableModels and local usage_history, sanitizes cached Provider Limits so retired upstream IDs are not re-exposed, and schedules a deduplicated post-usage refresh. Maintainer follow-up: decoupled the post-usage refresh via a lightweight usageEvents bus (usageHistory no longer dynamic-imports providerLimits) so it does not pull the executors/translator graph into the typecheck-core surface — typecheck:core stays at 0. Integrated into release/v3.8.21. Thanks @dhaern!
* feat(cli): add autostart on/off/toggle shorthand for headless serve mode (#3331) (#3614)
Integrated into release/v3.8.21 (#3331)
* docs(changelog): credit #3603 (Flash tier IDs) + #3604 (provider quotas) + #3605 (reasoning wrappers)
Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
* fix(review): resolve findings from /review-reviews battery (v3.8.21 hardening) (#3618)
Pre-release hardening from the /review-reviews battery — 15 findings resolved (L1-L13,L15) + L14 live-verified WONTFIX, convergence re-review clean. lint/typecheck:core/test:vitest(146)/build green; zero new test:unit failures vs baseline 797de433f.
* chore(release): v3.8.21 CHANGELOG + i18n + env-doc sync
---------
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Raxxoor <manker_lol@hotmail.com>
158 lines
4.4 KiB
TypeScript
158 lines
4.4 KiB
TypeScript
// Antigravity CLI (`agy`) model catalog.
|
|
//
|
|
// These models are pinned from the live `:fetchAvailableModels` endpoint
|
|
// (https://daily-cloudcode-pa.googleapis.com/v1internal:fetchAvailableModels) using a
|
|
// real `agy` consumer-OAuth token. The public catalog exposes the same clean Gemini
|
|
// 3.5 Flash tier names as the Antigravity IDE provider; the shared Antigravity executor
|
|
// maps those names to the legacy upstream IDs immediately before dispatch.
|
|
//
|
|
// The `agy` provider reuses the `antigravity` executor/translator (identical backend),
|
|
// but ships its OWN catalog so it can expose models the `antigravity` provider's static
|
|
// list omits — notably the Claude models (`claude-opus-4-6-thinking`, `claude-sonnet-4-6`),
|
|
// which `:fetchAvailableModels` reports as user-callable with quota even though the
|
|
// `antigravity` catalog comment assumes they 404. Tab-completion models
|
|
// (`tab_flash_lite_preview`, `tab_jump_flash_lite_preview`) are intentionally excluded —
|
|
// they are not chat-callable.
|
|
|
|
export const AGY_PUBLIC_MODELS = Object.freeze([
|
|
// Claude (Antigravity backend) — the headline differentiator for this provider.
|
|
{
|
|
id: "claude-opus-4-6-thinking",
|
|
name: "Claude Opus 4.6 (Thinking)",
|
|
contextLength: 200000,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "claude-sonnet-4-6",
|
|
name: "Claude Sonnet 4.6 (Thinking)",
|
|
contextLength: 200000,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
// Gemini 3.x
|
|
{
|
|
id: "gemini-3.1-pro-high",
|
|
name: "Gemini 3.1 Pro (High)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-3.1-pro-low",
|
|
name: "Gemini 3.1 Pro (Low)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-pro-agent",
|
|
name: "Gemini 3.1 Pro (Agent)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-3.5-flash-low",
|
|
name: "Gemini 3.5 Flash (Low)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65536,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-3.5-flash-medium",
|
|
name: "Gemini 3.5 Flash (Medium)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-3.5-flash-high",
|
|
name: "Gemini 3.5 Flash (High)",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65536,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-3.1-flash-lite",
|
|
name: "Gemini 3.1 Flash Lite",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
toolCalling: true,
|
|
},
|
|
{ id: "gemini-3.1-flash-image", name: "Gemini 3.1 Flash Image" },
|
|
// Gemini 2.5
|
|
{
|
|
id: "gemini-2.5-pro",
|
|
name: "Gemini 2.5 Pro",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
supportsReasoning: true,
|
|
supportsVision: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-2.5-flash",
|
|
name: "Gemini 2.5 Flash",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-2.5-flash-thinking",
|
|
name: "Gemini 2.5 Flash Thinking",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
supportsReasoning: true,
|
|
toolCalling: true,
|
|
},
|
|
{
|
|
id: "gemini-2.5-flash-lite",
|
|
name: "Gemini 2.5 Flash Lite",
|
|
contextLength: 1048576,
|
|
maxOutputTokens: 65535,
|
|
toolCalling: true,
|
|
},
|
|
// GPT-OSS
|
|
{
|
|
id: "gpt-oss-120b-medium",
|
|
name: "GPT-OSS 120B (Medium)",
|
|
contextLength: 131072,
|
|
maxOutputTokens: 32768,
|
|
supportsReasoning: true,
|
|
toolCalling: true,
|
|
},
|
|
]);
|
|
|
|
const AGY_PUBLIC_MODEL_IDS = new Set(AGY_PUBLIC_MODELS.map((model) => model.id));
|
|
|
|
const AGY_CLIENT_VISIBLE_MODEL_NAMES = Object.freeze(
|
|
AGY_PUBLIC_MODELS.reduce<Record<string, string>>((acc, model) => {
|
|
acc[model.id] = model.name;
|
|
return acc;
|
|
}, {})
|
|
);
|
|
|
|
export function getClientVisibleAgyModelName(modelId: string, fallbackName?: string): string {
|
|
return AGY_CLIENT_VISIBLE_MODEL_NAMES[modelId] || fallbackName || modelId;
|
|
}
|
|
|
|
export function isUserCallableAgyModelId(modelId: string): boolean {
|
|
return !!modelId && AGY_PUBLIC_MODEL_IDS.has(modelId);
|
|
}
|