Every number the counts gate checks inside the README SVGs (providers, MCP tools, routing
strategies, pools, free-forever providers, catalog entries, CLI integrations, scoring factors,
the free-tier budget card) comes from docs/reference/derived-facts.json through
scripts/docs/readmeFacts.mjs instead of a literal kept by hand in each generator. Curated copy
(150+, 15-95%, $0) stays literal. Each generator still produces the committed SVG byte for byte.
The base added the expiry-first strategy (#17829) and the
CODE_ASSIST_INELIGIBLE_ONBOARD_LEGACY_TIER flag (#18060), so both sides
had moved the same counts.
- Strategies: the code registry now has 22 public strategies (expiry-first
and jev). AGENTS.md, open-sse/services/AGENTS.md, the bs AGENTS mirror,
AUTO-COMBO.md (table now has both rows), RESILIENCE_GUIDE.md and llm.txt
state 22. The other docs the expiry-first PR bumped to 21 now say 22
(README, CONTRIBUTING, ARCHITECTURE, FEATURES, OPEN_SSE_ARCHITECTURE,
REPOSITORY_MAP, CODEBASE_DOCUMENTATION, comparison, diagrams README,
request-pipeline, QUOTA_SHARE, RELEASE_CHECKLIST, tier-flow images).
README's strategy table gets a jev row. The README SVGs were regenerated
from their generators (comparison table, hero, tier cascade, strategies
grid).
- Flags: both sides' flags are kept (catalog total 125, Runtime 62).
featureFlagDefinitions.ts stays under the 1440-line cap: the System One
spread loses its comment and two blank lines are dropped.
- llm.txt i18n mirrors: same five count lines as the root (docs-sync).
- stryker.conf.json: list boundary-engine-seams.test.ts, which now covers
auth.ts and autoStrategy.ts (check:mutation-test-coverage --strict).
- strategy-registry test: CANONICAL is 22 public + quota-share = 23.
- connectionAwareExpansion.ts, check-fabricated-docs.mjs, stryker.conf.json:
both sides kept.
Brings the recut of #17920 up to release/v3.8.54 at 2f2c1957. The base
added Hetzner, Grokified, Replicate and Cerebrium (#19206) and moved the
canonical provider count 388 -> 393 on the same lines this branch bumps.
The 93 conflicted files were count-only (verified by masking digits). Each
conflict hunk keeps the release side; the merged tree then has 394
canonical providers (check:provider-consistency), so the provider total
was replayed 393 -> 394 on the lines check:docs-counts flags, the matching
llm.txt mirrors, the tier-flow SVGs and the README diagram generators.
Digit-only edits. PROVIDER_REFERENCE.md was regenerated with
gen:provider-reference and the README diagrams with docs:readme-diagrams.
The "Catalog-Marked Free" figure (153) and the README locale mirrors
(389) are left as the base has them; neither is gated and both were
already behind the code before this merge.
Co-authored-by: Ilya Bogin <246701201+ilya-bogin-keenable@users.noreply.github.com>
Validated in the full merge-train on the .113 (lot 6, 2026-11-13): typecheck, static gates and the full unit suite. Every failure from that run was re-run in isolation, both on the merged tree and on the train base. They come from the .113 root environment, load-sensitive timing, or known flakes. None trace back to this change.
Co-authored-by: Bob.Hou <houminxi@gmail.com>
Co-authored-by: Minxi Hou <houminxi@gmail.com>
Validated in the full merge-train on the .113 (lot 6, 2026-11-13): typecheck, static gates and the full unit suite. Every failure from that run was re-run in isolation, both on the merged tree and on the train base. They come from the .113 root environment, load-sensitive timing, or known flakes. None trace back to this change.
Co-authored-by: Rafa Martins <rafacpti23@users.noreply.github.com>
Validated in the full merge-train on the .113 (lot 5, 2026-11-12): typecheck, static gates and the full unit suite. Every failure from that run was re-run in isolation, both on the merged tree and on the train base. They come from the .113 root environment, load-sensitive timing, or known flakes. None trace back to this change.
Co-authored-by: Jowimila <127446097+jowimila@users.noreply.github.com>
Validated in the full merge-train on the .113 (lot 3c, 2026-11-11): typecheck, static gates and the full unit suite. Every failure from that run was re-run in isolation, both on the merged tree and on the train base. They come from the .113 root environment, load-sensitive timing, or known flakes. None trace back to this change.
Co-authored-by: Cristiano M Bergamo <cmbergamo@outlook.com>
Both this branch (keenable-search) and release/v3.8.54 (#15201, chatgpt)
moved the canonical provider count 387 -> 388 on the same lines, so the merge
kept 388. The merged tree has 389 canonical providers
(check:provider-consistency). Digit-only edits on those lines (AGENTS.md,
llm.txt + mirrors, README + mirrors, skills, package.json, docs, generator
constants); PROVIDER_REFERENCE.md and the README diagrams regenerated with
gen:provider-reference and docs:readme-diagrams.
Adds ChatGPT as its own OAuth provider through OpenAI's official Sign in with ChatGPT (SIWC) token-sharing flow and the public Responses API: a recognizable sign-in button, OpenAI's consent screen, an account-specific live model catalog, public Responses inference and usage management, without a separately created OpenAI API key or client secret.
Provider-count train, step 6: the branch was merged with the release tip after Codex Web Search (#17933). Both sides had raised the count from 386 to 387, so git kept identical lines; every count line was recounted to 388 (`gen:provider-reference`: 388 unique IDs, oauth=31): README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills, docs, `package.json` and the SVG generators. PROVIDER_REFERENCE and the README diagrams were regenerated. RESERVED_PREFIX_COUNT is 444 (443 on the base plus `chatgpt`). The `QuotaCard` conflict keeps the ChatGPT local-usage branch and the base's Cursor per-model usage. The PKCE challenge and the test owner fingerprints now go through `generateCodeChallenge` and `opaqueTokenFingerprint`, byte-identical to the inline SHA-256 they replace. Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (388), the focused SIWC, usage UI, golden and count tests, lint and the full fast gates.
Both this branch (keenable-search) and release/v3.8.54 (#17933, codex-search)
bumped the canonical provider count 386 -> 387 on the same lines, so the merge
kept 387. The merged tree has 388 canonical providers
(check:provider-consistency). Digit-only edits on the lines either side bumped,
plus PROVIDER_REFERENCE.md regenerated with gen:provider-reference.
Adds `codex-search` (alias `codex_search`), a fallback-only `/v1/search` provider that uses the built-in `web_search` tool through connected OpenAI Codex (ChatGPT) accounts, so no separate search-service key is needed. Normalizes observed sources and citations into standard search rows, bounds the stream to 4 MiB with cancellation, keeps search failures in a search-specific in-memory lock so they never touch the shared Codex connection's health, and records upstream token usage in call logs. `CODEX_SEARCH_AUTO_FALLBACK_ENABLED` (default off) controls whether automatic searches may use a Codex account. Closes#17925.
Provider-count train, step 5 of 5: the branch was merged with the release tip after deAPI (#19319), ParalonCloud (#18356), MegaBrain (#18129) and RenderHour (#18103). Count-only conflicts took the base text and were recounted to 387 (`gen:provider-reference`: 387 unique IDs, search=20): README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills, docs, `package.json`, the SVG generators and the tier-flow SVGs. PROVIDER_REFERENCE and the README diagrams were regenerated. The feature-flag count is 121 on the merged tree. Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (387), the focused search, flag, golden and count tests, lint and the full fast gates.
Brings the recut of #17920 up to release/v3.8.54 at 8943ca61, which added
RenderHour (#18103) and moved the provider count 385 -> 386 in the same
count-only files this PR bumps. For those 93 files the release side was kept
and the PR's own +1 provider / +1 hasFree was replayed on top (387 providers,
154 hasFree, 20 search providers). PROVIDER_REFERENCE.md and the four README
diagrams were regenerated. Protected files change in digits only.
Co-authored-by: Ilya Bogin <246701201+ilya-bogin-keenable@users.noreply.github.com>
Adds RenderHour (`renderhour`) as one dual-auth media provider for images, video and speech: subscription sign-in (authorization code + PKCE with the public client via `resolvePublicCred`, rotating refresh tokens) or an `rh_…` API key, both validated with `GET /v1/balance`. One shared client runs RenderHour's async job API (upload, `POST /v1/generations` with an Idempotency-Key, polling with back-off), with thin image, video and TTS handlers on top.
Provider-count train, step 4 of 5: the branch was merged with the release tip after deAPI (#19319), ParalonCloud (#18356) and MegaBrain (#18129). Count-only conflicts took the base text and were recounted to 386 (`gen:provider-reference`: 386 unique IDs): README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills, docs, `package.json`, the SVG generators and the tier-flow SVGs. PROVIDER_REFERENCE and the README diagrams were regenerated. The OAuth test-config and provider-list conflicts keep both MegaBrain and RenderHour. Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (386), the focused provider, OAuth, refresh, public-creds, golden and count tests, lint and the full fast gates.
Brings the recut of #17920 up to release/v3.8.54 at 8e72dbf5. The base added
MegaBrain (#18129), which moved the provider count 384 -> 385 in the same
count-only files this PR bumps. For those 93 files the release side was kept
and the PR's own +1 provider / +1 hasFree was replayed on top (386 providers,
154 hasFree, 20 search providers). PROVIDER_REFERENCE.md and the four README
diagrams were regenerated. Protected files change in digits only.
Co-authored-by: Ilya Bogin <246701201+ilya-bogin-keenable@users.noreply.github.com>
Adds MegaBrain (`megabrain`, alias `mb`) as one dual-auth chat provider wired like `kilocode`: subscription sign-in through Kilo's device-auth flow on api.getmegabrain.com, or an `mb-v1-…` API key. Requests carry `X-KILOCODE-FEATURE: omniroute` so they count against the plan limits. Includes live model discovery, connection test and key validation via `/api/profile/limits`, Provider Limits (session and weekly quotas), and an error-classifier branch that locks the model instead of banning the connection on MegaBrain's `plan_tier_required` / `extra_usage_off` 403s.
Provider-count train, step 3 of 5: the branch was merged with the release tip after deAPI (#19319) and ParalonCloud (#18356). Count-only conflicts took the base text and were recounted to 385 (`gen:provider-reference`: 385 unique IDs, oauth=29, apikey=258): README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills, docs, `package.json`, the SVG generators and the tier-flow SVGs. PROVIDER_REFERENCE and the README diagrams were regenerated. The registry conflict keeps both providers with megabrain still last, and RESERVED_PREFIX_COUNT is 443 (paraloncloud/paralon plus megabrain/mb). Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (385), the focused provider, OAuth, golden and count tests, lint and the full fast gates.
Keep the release side for the count lines and re-apply this PR's +1
(Keenable Search) on top of ParalonCloud: 384 -> 385 providers,
153 -> 154 hasFree; regenerated PROVIDER_REFERENCE.md and README SVGs.
Adds ParalonCloud (`paraloncloud`, alias `paralon`) as a built-in API-key provider: OpenAI-compatible chat and embeddings, with key validation and live model discovery through `GET /v1/models`. Original implementation by @robertjitaru.
Provider-count train, step 2 of 5: the branch was merged with the release tip after deAPI (#19319). Both sides had raised the count from 382 to 383, so git kept identical lines; every count line was recounted to 384 (`gen:provider-reference`: 384 unique IDs, apikey=258): README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills, docs, `package.json` and the SVG generators. PROVIDER_REFERENCE and the README diagrams were regenerated. The APIKEY_PROVIDER_COUNT conflict keeps both entries (deAPI 256, EmpirioLabs 257, ParalonCloud 258), and RESERVED_PREFIX_COUNT stays 441. Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (384), the focused provider, golden and count tests, lint and the full fast gates.
Co-authored-by: robertjitaru <42837438+robertjitaru@users.noreply.github.com>
Resolve the provider-count conflicts by keeping the release side and
re-applying this PR's +1 (Keenable Search): 383 -> 384 providers,
153 -> 154 hasFree, regenerated PROVIDER_REFERENCE.md and README SVGs.
Adds deAPI (`deapi`) as an API-key media provider on its OpenAI-compatible gateway: image, TTS, STT, embeddings and async video (new `deapi-video-job` preset). This carries #18593 by @Pietrus-914 with a maintainer repair.
Provider-count train, step 1 of 5: the branch was merged with the current release tip (clean merge). The merged tree has 383 providers (`gen:provider-reference`: 383 unique IDs, apikey=257). PROVIDER_REFERENCE and the README diagrams regenerate byte-identical, and every count claim already reads 383: README and its 66 mirrors (Persian digits in `fa`), `llm.txt` and its 66 mirrors, AGENTS.md, skills and docs. Protected files differ from the tip only in digits. Validated with check:docs-counts, check:provider-consistency (383), the focused provider and count tests, lint, typecheck:core, check:open-sse-typecheck and the full fast gates.
Co-authored-by: Pietrus-914 <107179363+Pietrus-914@users.noreply.github.com>
This PR carries #17209 by @Adam-Dalloul, plus a maintainer repair. The contributor's fork rejected our push to `feat/empiriolabs-provider`, so the repaired branch lives here instead. Adam Dalloul's three commits keep his authorship. #17209 stays open and will be closed when this PR merges.
Original PR: #17209
## What the maintainer repair changed
One merge commit, `528c929f`, brings `release/v3.8.54` into the contributor's head (`0fbaab41`). It is a merge, not a rebase. The release had reached 380 providers and had added providers (gisoo among them) on the same lines, so 92 files conflicted. No provider code needed a fix.
- `src/shared/constants/config.ts`: `PROVIDER_ENDPOINTS` keeps gisoo from the release and adds empiriolabs.
- `tests/unit/provider-node-reserved-prefix.test.ts`: keeps every release comment and assertion, raises `RESERVED_PREFIX_COUNT` from 436 to 437 and adds a `has("empiriolabs")` check.
- `tests/unit/providers-constants-split.test.ts`: keeps the release history and sets `APIKEY_PROVIDER_COUNT` to 256 (255 plus empiriolabs).
- 89 count-only files (README, docs, SVGs, `llm.txt` and its 66 mirrors, AGENTS.md, `skills/README.md`, two `SKILL.md` files, `agentSkills.ts`, `package.json`): resolved to the release side, then recounted on the merged tree to 381. In the protected files (AGENTS.md, `llm.txt`, the 66 `llm.txt` mirrors, `skills/**/SKILL.md`) the removed and added lines are identical once digits are masked.
- `docs/reference/PROVIDER_REFERENCE.md`:
Editions became the dashboard's default palette (#18901), so the eight
header shields move from the Classic lime-on-ink to Editions copper on ink:
color=e5ac82 (--ci-color-accent) and labelColor=20211c (--ci-color-heading),
from the light block of packages/ui-kit/src/ci-editions.css. shields.io
draws the message text dark on the copper and white on the ink.
apply-readme-badge-colors.mjs carries the same values and was run over
README.md and the 66 mirrors: 528 lines, URL query strings only. The PR-scoped
i18n drift gate reports 0 drift introduced (README.md and its 66 mirrors are
already drifted on release/v3.8.54).
## Why
MiniMax Code accounts need an OpenAI-compatible route that returns native tool calls to agent clients using the subscription gateway.
## What changed
- Register `minimax-code` (`mmcode`) and add dashboard device-code sign-in.
- Translate chat, tool-call, and streaming gateway responses; preserve request-scoped size refusals and upstream error semantics.
- Read and refresh credentials from the local MiniMax Code profile. OmniRoute does not persist a separate provider credential in its connection database.
## Verification
- Focused MiniMax Code unit tests: 73/73 passed.
- `npm run check:docs-all`: passed; `npx eslint open-sse/executors/minimax-code.ts`: passed.
- API Route Typecheck and Semgrep are queued for this head.
## Notes
The managed gateway is an undocumented MiniMax subscription endpoint. Maintainer approval and a live `mcode` run remain outstanding; no live account result is claimed here. The ACP transport is not in this diff: #18119 was closed as a duplicate, and its implementation remains on `rebuild/minimax-code-provider-acp` pending a decision on its destination. Base-red issue #17219 is inherited.
Thanks @megamen32.
Complements the System One design from #17994 with pieces from open PRs, each
behind a default-off feature flag so nothing changes for current users:
- ollama-local/<model> on POST /v1/systemone, served by the ollama-local
connection's base URL with Ollama's own body limits checked before any
upstream call (from #14667; SYSTEMONE_OLLAMA_LOCAL_BACKEND_ENABLED).
- getExecutor refuses chat on the decisions-only typesafe provider instead of
letting the default executor post the TypeSafe key to the OpenAI fallback
(from #14498; SYSTEMONE_CHAT_GUARD_ENABLED).
- the jev combo strategy: one TypeSafe System One choice call admits the
targets, failover keeps the operator's order (from #15279). The TypeSafe
call needs COMBO_JEV_STRATEGY_ENABLED; a stored key alone never sends
traffic, and with the flag off a jev combo keeps its preference order.
Strategy count 20 -> 21 where the docs-counts gate and the
routing-strategy-docs-sync test pin it (digits and the jev name only).
Co-authored-by: PixmaNTS <maxime@maxime-pointet.fr>
Co-authored-by: Sean P. Ford <sean@seanford.com>
Co-authored-by: Miguel Enes <1568086+miguelenes@users.noreply.github.com>
## Problem and resulting behavior
Free-only imports could accept paid or ineligible models through optimistic catalog entries and badges. Compatible-node imports require affirmative payload evidence; explicit paid evidence takes precedence through discovery, cache and sync. Client-restricted offers do not grant generic proxy eligibility. Normal imports remain available.
Refs #17028. Keep this issue open for the remaining evidence, validation, integration and acceptance.
## Scope
- Preserve the original OpenAI-/Anthropic-compatible-node option, persisted setting and translated hint in 67 measured locale files. Claude Code-compatible nodes remain excluded because they expose no model listing.
- Preserve paid-price and explicit-paid vetoes through classification, badges, discovery, cache and sync. Missing prices are not invented. Successful cache refresh requires `source: api` and persisted metadata; cached HTTP 200 with a warning is insufficient.
- Preserve the seven previously audited conditional offers and their account, region and Requesty training restrictions.
- Remove unconditional Ollama grants whose official offers ended or became paid, including the preceding Gemma correction. The latest increment removes [deepseek-v4-flash](https://ollama.com/library/deepseek-v4-flash), [glm-5.1](https://ollama.com/library/glm-5.1), and [Tencent hunyuan-pro](https://cloud.tencent.com/document/product/1729/131925), using explicit retirement notices, not absence from a model listing
Merged as part of the v3.8.53 fix sweep (author @alirezariahi).
Co-authored-by: Alireza <ali.r.riahi@gmail.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
* chore(dashboard): sync the vendored CI UI Kit to 0.0.88
packages/ui-kit moves from upstream 681cdb1 to f7c79d0 (0.0.88) through scripts/dev/sync-ui-kit.sh.
* fix(dashboard): drop the light Editions warning override now that the kit ships AA
Kit 0.0.88 (upstream #155) darkens the light Editions --ci-color-warning to #8c5a1b, the value #18919 had hard-coded in globals.css. --color-warning-ink stays as the alias that badges, warning buttons and text-warning read, now plainly the kit token, and the light-only override plus its prefers-color-scheme fallback are gone. The contrast test reads the kit value instead, checks that no hard-coded or theme-specific override comes back, and still fails if the kit's light Editions warning drops below 4.5:1 (checked by restoring #99631f).
* test(docs): keep the README diagrams' warning override while the kit misses AA on surfaceMuted
The diagram theme test asserted the kit's light Editions warning was #99631f and below AA, so kit 0.0.88 (upstream #155, #8c5a1b) made it fail on purpose. The new kit value clears AA on the canvas, the surface and warnBg but is 4.46:1 on surfaceMuted, which the README diagrams also draw warn text on, so they keep #8a591c. The test now pins the kit value, keeps the override only while some diagram surface still misses AA, and requires 4.5:1 for the diagram value on all five light surfaces. No SVG changes.
* test(docs): check the diagrams' warning override is darker than the kit's
The previous commit consolidated the diagram-theme warning test and dropped one assertion (86 -> 85), which check:test-masking flags. This adds a real one back: on surfaceMuted, the surface that still needs the override, the diagram warn must have more contrast than the kit warning, so the override can never turn into a lighter or unrelated colour.
* chore(dashboard): sync the vendored CI UI Kit to 0.0.89 and read its warning in the README diagrams
Kit 0.0.89 (upstream #157) keeps light warning text at AA on every content surface: Classic #a05600, Editions #8a591c. That is the value the README diagrams carried as a local override, so the diagram theme now reads the kit's warning as is in both schemes; the diagram-theme test pins it to ci-editions.css and still requires 4.5:1 on all five light surfaces. No SVG changes, since the colour is the same. The 0.0.88 changelog fragment becomes the 0.0.89 one.
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Lime on ink (d8ff00 on 040d10) for the eight shields.io badges of the header group. The star
counter moves from style=social, which ignores both colors, to style=flat with its logo and
label spelled out, so it keeps the same text and mark.
scripts/docs/apply-readme-badge-colors.mjs applies the same URL change and is idempotent; it
is meant to be run over docs/i18n/*/README.md after the translation wave lands.