Repository navigation
feat(catalog): add the current-generation models to the catalogue - #415
Merged
Merged
Conversation
6 tasks done
argszero
added a commit
that referenced
this pull request
Oct 18, 2026
Four carriers still described this project as shipping DeepSeek pricing only, with every other vendor left to the reader to configure: - README.md / README.en.md, the "transparent billing" feature line; - docs/user-stories.md, the capability list that mirrors it; - docs/plan-api-matrix.md, which said "DeepSeek pricing built in; other vendors can be configured in the same format" and listed eight provider names, two of which (`bytedance`, `aliyun`) are not the ids the config actually uses. The example config ships ten providers, sixteen plans and twenty-four models, with thirteen rows priced in CNY and eleven in USD: the four international vendors became selectable in #414, and the new-generation rows landed in #415. The old wording was accurate when written; it is incomplete now, and incomplete in the direction that undersells the feature list -- a reader of the front page is told to expect one vendor's prices and to configure the rest themselves. The fix names no counts. Those are owned by the config and by catalog_gate's MODEL_COUNT / PLAN_COUNT, and restating them in prose is the stale-copy family this repo has had to clean up before. The provider roster is spelled with the real ids and checked to be exact in both directions; the model-family roster gains the two families it was missing (Kimi, grok). Docs only: 4 files, +6/-6, no behaviour change. Co-authored-by: argszero <argszero@argszerodeMac-mini.local>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The catalogue was missing every current-generation model the vendors shipped in October 2026, so a user could not select them on this platform at all: the
[[models]]rows stopped at the previous flagships (zhipuglm-5.3, anthropicclaude-opus-5, openaigpt-5.6-sol, googlegemini-3.1-pro, aliyunqwen3.8-max, minimaxminimax-m3). This PR adds the nine missing rows, additively — no existing row is touched.New rows (prices verified against each vendor's official page on 2026-10-16; CNY per million tokens unless marked USD):
glm-5.3-flashclaude-sonnet-5.5gpt-6.1-solgpt-6-astragpt-6-lunagemini-3.8-flashgemini-4-argonqwen3.8-max-primeminimax-m2.7Decisions a reviewer should know about:
qwen3.8-max-primecache-hit price — the official pricing table gives no figure for it; its row only says the model "enjoys a context-cache discount", exactly as the siblingqwen3.8-flashdoes. Recorded as0(cache hit free — it under-collects) with a comment marking it as pending, rather than copying another model's ratio or guessing one.minimax-m2.7context window — neither the vendor's pricing page nor its model page publishes one. Recorded ascontext_length = 0with a comment; no value was invented.gemini-3.8-flash($0.75/$3.75 through 2026-12-31, then $1.50/$7.50) andgemini-4-argon($2.00/$10.00 through 2026-11-30, then $4.00/$20.00) record the current value and spell out both figures plus the switch date in the row comment, so the next refresh has a source of truth.gpt-6row records the Standard tier, with the tier note in the comment.glm-5.3-flashis markedvision = true— the vendor's page states native multimodality; every other new row isvision = falseper its vendor's "image understanding" column.Related Issue
Rant
2026-10-16T15:20:36.482297+08:00, keyword 【上架】 ("list these on the platform") — add the current-generation models to the catalogue. Its prerequisite, "make the four international vendors selectable when listing a key", landed as #414 (983111c); without it the anthropic / openai / google rows added here could not have been selected.Changes
config/config.example.toml— nine new[[models]]rows; the example file (which CI treats as the single source of truth) is updated in step with the changeui/js/data.js— the same nine models mirrored intoMODELS(USD rows go through the existingUSD()conversion)src/catalog_gate.rs—MODEL_COUNT15 → 24ui/index.html—data.js?v=cache-bust token bumpedTests
cargo test— 564 passed, 0 failedcargo fmt --check— cleancargo clippy --all-targets -- -D warnings— cleancatalog_gate's three rules (bidirectional model-set equality betweenconfig.example.tomlanddata.js, plan-id set equality,MARKET ⊆ MODELS) are exactly the tests that cover it;MODEL_COUNTis their positive control.Checklist
feat/…)