v3.8.21

### ✨ Added

- **feat(cli):** `omniroute autostart` now accepts the shorthand the headless / `omniroute serve` path was missing — `omniroute autostart on` / `... true` (aliases of `enable`), `... off` / `... false` (aliases of `disable`), a new `... toggle`, and a default `... status` (bare `omniroute autostart` is a safe read-only). Previously autostart could only be toggled from the tray (`serve --tray`) or the Electron Appearance tab, so a plain `omniroute serve` user had no way to enable it. (The cross-platform launchd/systemd/registry logic is unchanged — this only wires the ergonomic CLI surface.) ([#3331](https://github.com/diegosouzapw/OmniRoute/issues/3331) — thanks @uniQta)

### ♻️ Code Quality

- **refactor(chatCore):** extract the chatCore request phases — idempotency check, semantic cache check, common request sanitization, and memory/skills injection — into dedicated `open-sse/handlers/chatCore/` modules (`idempotency.ts`, `semanticCache.ts`, `sanitization.ts`, `memorySkillsInjection.ts`), slimming the monolithic handler with no behavior change. (Maintainer follow-up: re-derive `idempotencyKey` at the Phase 9.2 save site after the check moved into the module, fixing a `ReferenceError` on successful non-cached responses.) ([#3598](https://github.com/diegosouzapw/OmniRoute/pull/3598) — thanks @oyi77)
- **docs(opencode-provider):** soft-deprecate `@omniroute/opencode-provider` in favour of `@omniroute/opencode-plugin`. The provider package writes a **static** model list to `opencode.json` that drifts behind the live OmniRoute catalog, whereas the plugin fetches `/v1/models` at OpenCode startup. The package keeps working (no code/behavior change), but its npm description and README now carry a deprecation banner with the one-line migration, and a guard test pins the notice. ([#3419](https://github.com/diegosouzapw/OmniRoute/issues/3419) — thanks @herjarsa)
- **chore(review):** pre-release hardening from a multi-reviewer `/review-reviews` battery over the v3.8.21 diff (7 Opus reviewers; zero blocker/high). Resolved findings: npm tarball no longer ships co-located test files (`files[]` negations + reconciled `.npmignore`; the #3578 closure gate now asserts the real `npm pack` output in both directions); `getSanitizedCachedProviderLimitsMap` scopes its connection scan to antigravity/agy instead of decrypting every active connection on each dashboard poll; the Antigravity quota-tier remap (`toClientAntigravityQuotaModelId`) is centralized in `antigravityModelAliases.ts` (was an inline if-ladder in `usage.ts`); the chatCore idempotency check returns its resolved key so the save site reuses a single derivation; and new tests pin the chatCore extracted modules, the Antigravity `usage_history` fallback contract, the reasoning-wrapper prefix-preservation heuristic, the Antigravity SSE `markdown` branch, and the upstream-ca/test no-persist guarantee. (Live-verified that agy consumer tokens are accepted by the non-daily `cloudcode-pa` host used by `retrieveUserQuota`, so #3604 is not agy-host-limited.)

### 🔧 Bug Fixes

- **fix(routing):** reasoning models (deepseek-v4-flash, nemotron, etc.) no longer return empty content in combo routing when they spend all of `max_tokens` on reasoning — `validateResponseQuality` now rejects an empty-content-but-`reasoning_content` response when reasoning consumed ≥90% of completion tokens (so the combo loop retries/falls back), and reasoning models receive a `max_tokens` buffer (+50%, +1000 floor) so reasoning and content both fit. (Maintainer follow-up: the round-robin buffer is applied to a per-attempt copy so it does not compound across models/retries — `4096 → 6144 → 9216 → …`.) ([#3588](https://github.com/diegosouzapw/OmniRoute/pull/3588) — thanks @herjarsa)
- **fix(routing):** a valid `max_tokens`-truncated upstream response is no longer misclassified as empty content and rewritten into a fake 502 — `isEmptyContentResponse()` flagged any Claude `content:[]` / OpenAI empty-choice payload regardless of `stop_reason`/`finish_reason`, so a Claude Code `max_tokens: 1` connectivity ping (HTTP 200, `stop_reason:"max_tokens"`, empty content) became a synthetic `502 "Provider returned empty content"` and triggered a needless family fallback. The guard now treats a terminal truncation/tool signal (Claude `stop_reason` `max_tokens`/`tool_use`, OpenAI `finish_reason` `length`/`tool_calls`) as a legitimate completion; genuinely empty responses (no terminal reason, or `stop`/`end_turn` with empty content) are still caught. ([#3572](https://github.com/diegosouzapw/OmniRoute/issues/3572))
- **fix(api):** `/v1/completions` now returns the legacy OpenAI Completions shape (`object:"text_completion"`, `choices[].text`) instead of chat payloads (`choices[].message|delta.content`) — the endpoint routes internally through the chat pipeline, so legacy Completion clients like TabbyML's `openai/completion` backend crashed with `missing field "text"`. The response (both non-streaming JSON and the SSE stream) is now translated back to the text-completion shape; `[DONE]` and error bodies pass through unchanged. ([#3571](https://github.com/diegosouzapw/OmniRoute/issues/3571))
- **fix(usage):** the z.ai/GLM coding-plan quota card no longer shows "Monthly 0%" — coding plans have no monthly cap (only 5-hour windows), so the quota API reports the `TIME_LIMIT` ("Monthly") entry with `total=0`, and the `total>0 ? … : 0` fallback rendered a misleading 0% remaining (which can skew downstream model-choice). With no absolute cap the remaining percentage now falls back to the percentage-derived value (full/100% when 0% used). ([#3580](https://github.com/diegosouzapw/OmniRoute/issues/3580))
- **docs(discovery):** mark `DISCOVERY_TOOL_DESIGN.md`'s API Endpoints table with an explicit "⚠️ Not yet implemented — Phase 2" banner — the discovery routes are a design proposal (Phase-1 stub only), and the banner makes clear the `KNOWN_STALE_DOC_REFS` gate suppression is intentional, not stale drift. ([#3498](https://github.com/diegosouzapw/OmniRoute/issues/3498))
- **fix(agent-bridge):** add the missing `POST /api/tools/agent-bridge/upstream-ca/test` route — the UpstreamCaField "Test" button POSTed to it but it didn't exist (404). The new validate-only route checks the CA file exists and is a parseable PEM certificate (returns the subject/expiry) **without** persisting the path or activating it; it inherits the `/api/tools/agent-bridge/` LOCAL_ONLY classification. ([#3488](https://github.com/diegosouzapw/OmniRoute/issues/3488))
- **fix(gamification):** the dashboard Profile page no longer hits three 404s — added the missing `GET /api/gamification/{level,badges,badges/earned}` routes (management-scoped). The page is operator-wide (no `apiKeyId`), so `level`/`badges/earned` aggregate across all keys (with an optional `?apiKeyId` for a single key), and `badges` seeds the built-in catalog first (idempotent) so the grid is populated even on installs that never seeded it (see #3472). ([#3484](https://github.com/diegosouzapw/OmniRoute/issues/3484))
- **security(oauth):** migrate the five public OAuth client_ids (Claude, Codex, Qwen, Kimi, GitHub Copilot — 9 server-side call-sites in `providerRegistry.ts` + `oauth.ts`) from string literals to `resolvePublicCred()` (Hard Rule #11), matching the existing Gemini/Antigravity pattern. The values decode byte-for-byte to the same public client_ids (env overrides still win), so OAuth flows are unchanged; the `check-public-creds` allowlist is now empty. The browser-bundled `codexDeviceFlow.ts` copy stays a literal by necessity (it cannot import `open-sse`). ([#3493](https://github.com/diegosouzapw/OmniRoute/issues/3493))
- **fix(mcp):** `omniroute --mcp` no longer crashes on npm installs with `ERR_MODULE_NOT_FOUND` (e.g. `src/lib/combos/steps.ts`) — the MCP server runs from raw TypeScript and imports across `src/` + `open-sse/`, but the published `files` allowlist only shipped a handful of cherry-picked paths, so the transitive closure (~400 files) was absent from the tarball. `files` now ships the backend source the MCP server needs (`open-sse/` + `src/{domain,lib,mitm,server,shared,sse,types}/`, excluding the `src/app` UI), and a new regression test computes the MCP import closure and fails if any reachable source file is not covered by `files`. ([#3578](https://github.com/diegosouzapw/OmniRoute/issues/3578))
- **fix(api):** `API_REFERENCE.md` no longer documents a non-existent `/api/guardrails*` / `/api/shadow*` surface (doc-fiction flagged by `check-docs-symbols`, frozen in `KNOWN_STALE_DOC_REFS`). The guardrail pipeline is real (`src/lib/guardrails`), so the two routes that map to actual behavior are now implemented — `GET /api/guardrails` (list the registered guardrails + status) and `POST /api/guardrails/test` (dry-run the pre-call pipeline over a sample input), both management-scoped — while the fictional `enable`/`disable`/`logs` rows and the entire `/api/shadow*` table (shadow A-B comparison is combo-config + `/api/combos/metrics`) were removed from the doc and dropped from the allowlist. ([#3496](https://github.com/diegosouzapw/OmniRoute/issues/3496))
- **fix(agent-bridge):** the MITM "Start" button no longer reports a misleading "port 443 may be in use" for every failure cause — `startMitm()` only matched the EADDRINUSE stderr line and always threw the port-443 message, so a missing `ROUTER_API_KEY` or an `EACCES` permission error sent users debugging the wrong thing. The startup watcher now buffers the MITM child's stderr and `interpretMitmStartupError()` maps the real `server.cjs` `❌` cause (port-in-use / permission-denied / missing API key / any other diagnostic line) into the surfaced error; with no captured output it stays generic instead of guessing port 443. ([#3606](https://github.com/diegosouzapw/OmniRoute/issues/3606))
- **fix(oauth):** Kiro "Import Token" no longer reports a bare `Internal server error` that hides the real cause — the import validates/refreshes the pasted refresh token against AWS, and the catch returned a generic 500 string, so an `invalid_grant`, an expired token, or a region mismatch all surfaced identically in the dashboard. The import error now carries the sanitized upstream cause via `sanitizeErrorMessage()` (Hard Rule #12 — no stack, no secrets), keeping the same `{ error: <string> }` response shape, and still falls back to the generic message when there is nothing to report. ([#3589](https://github.com/diegosouzapw/OmniRoute/issues/3589))
- **fix(antigravity):** the Antigravity/agy Gemini 3.5 Flash catalog now exposes clean public tier IDs (`gemini-3.5-flash-low`/`-medium`/`-high`, matching Antigravity 2.0.4's Low/Medium/High selector) and maps them to the live upstream IDs at the executor boundary, instead of the old confusing `-preview`/`-agent` names. Antigravity model-id normalization moved out of the global model resolver into the executor so client-visible IDs are no longer rewritten before account/credential routing and logging. (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.) ([#3603](https://github.com/diegosouzapw/OmniRoute/pull/3603) — thanks @dhaern)
- **fix(usage):** Antigravity/agy Provider Limits now report accurate consumption — `retrieveUserQuota` (live usage) is preferred over the `fetchAvailableModels` catalog view (which keeps reporting full buckets after real usage), with a local `usage_history` fallback for buckets that are only catalog-visible; cached entries are sanitized so retired upstream IDs are not re-exposed, and a deduplicated post-usage refresh keeps the dashboard fresh after each request. (Maintainer follow-up: the post-usage refresh is decoupled through a lightweight `usageEvents` bus so `usageHistory` no longer imports `providerLimits`/the executors graph, keeping the `typecheck:core` surface stable.) ([#3604](https://github.com/diegosouzapw/OmniRoute/pull/3604) — thanks @dhaern)
- **fix(gemini):** textual reasoning wrappers emitted as assistant prose (`<think>`/`<thinking>`/`<thought>`/`<internal_thought>`, including malformed/open tags like `<thought\n…` before a tool call) are now routed to `reasoning_content` instead of leaking into visible `content`, in both the non-streaming sanitizer and the Gemini streaming translator (with split-chunk buffering so a tag fragmented across SSE chunks stays hidden). Structured tool calls and the existing textual tool-call conversion are preserved. ([#3605](https://github.com/diegosouzapw/OmniRoute/pull/3605) — thanks @dhaern)
- **fix(gemini):** a signed native `functionCall` arriving while a textual reasoning wrapper opened in an earlier streaming chunk is still buffered now flushes that buffered reasoning to `reasoning_content` before the tool call, instead of silently discarding it. (Pre-release `/review-reviews` finding.)
- **fix(api):** `/v1/completions` now drops a stale upstream `content-length` on the SSE branch too (the JSON branch already did) — re-serialization changes the byte length, so a buffered SSE body could otherwise advertise the pre-rewrite length and truncate/hang the client. (Pre-release `/review-reviews` finding.)


---

### 🙌 Contributors

Thanks to all who contributed to this release:
@uniQta · @herjarsa · @oyi77 · @dhaern · @diegosouzapw


## What's Changed
* fix: add reasoning token buffer for combo routing (fixes #3587) by @herjarsa in https://github.com/diegosouzapw/OmniRoute/pull/3588
* Release v3.8.21 by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3593


**Full Changelog**: https://github.com/diegosouzapw/OmniRoute/compare/v3.8.20...v3.8.21

## What's Changed
* fix: pass through valid max_tokens-truncated responses instead of fake 502 (#3572) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3595
* fix: /v1/completions returns legacy text-completion format, not chat (#3571) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3596
* fix: z.ai/GLM coding plan no longer shows Monthly 0% when no monthly cap (#3580) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3597
* docs: mark DISCOVERY_TOOL_DESIGN endpoints as Phase-2 not-yet-implemented (#3498) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3599
* fix(agent-bridge): add validate-only upstream-ca/test route (#3488) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3600
* Refactor: Extract chatCore phases into modular files by @oyi77 in https://github.com/diegosouzapw/OmniRoute/pull/3598
* fix(api): implement GET /api/guardrails + POST /api/guardrails/test, drop shadow/guardrails doc-fiction (#3496) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3602
* fix(gemini): isolate textual reasoning wrappers by @dhaern in https://github.com/diegosouzapw/OmniRoute/pull/3605
* fix(antigravity): normalize Gemini 3.5 Flash tier IDs by @dhaern in https://github.com/diegosouzapw/OmniRoute/pull/3603
* fix(agent-bridge): surface real MITM startup-failure cause, not always port 443 (#3606) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3608
* fix(oauth): surface real Kiro import-token failure cause, not a bare 500 (#3589) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3609
* docs(opencode-provider): soft-deprecate in favor of @omniroute/opencode-plugin (#3419) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3613
* fix(usage): normalize Antigravity and agy provider quotas by @dhaern in https://github.com/diegosouzapw/OmniRoute/pull/3604
* feat(cli): add autostart on/off/toggle shorthand for headless serve mode (#3331) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3614
* fix(review): resolve findings from /review-reviews battery (v3.8.21 hardening) by @diegosouzapw in https://github.com/diegosouzapw/OmniRoute/pull/3618


**Full Changelog**: https://github.com/diegosouzapw/OmniRoute/compare/v3.8.20...v3.8.21