opencode-cmd-provider 1.6.4 → 1.7.0

package/CHANGELOG.md

@@ -1,3 +1,62 @@
+## 1.7.0 - 2026-09-06
+
+### Model catalog: models.md-primary with enrichment that never blocks shipping
+
+The Model catalog's membership authority flipped: the npm `command-code`
+package's bundled models.md table is now the sole authority — every row
+ships in the Snapshot on the next refresh, even when the provider listing
+API lags (day-1 models like `gpt-6-astra` appear immediately). The listing
+API is demoted to a pure divergence reporter (annotate-only, zero gating
+power, zero field writes), and every other source — RSC slug records, the
+CLI bundle, the Command Code models page — is enrichment that fills gaps
+but never decides membership, never wins a ship-bar field, and never gates
+the refresh (see ADR-0008 and the rewritten glossary in `CONTEXT.md`).
+
+- **Ship-bar parsing** — `scripts/parse-facts.mjs` converts coarse Context
+  tokens through a pinned decimal table; a missing Context cell ships as
+  `null` (pending, resolved by the fallback ladder), a missing price cell
+  ships cost-less (never zero-filled, missing never reads as free), and
+  unparseable cells fail loudly. `facts.ts` is now a re-export shim over
+  the snapshot rows, keeping the consumer contract stable.
+- **Enrichment fallback ladders** — context resolves models.md → RSC
+  `contextWindow` → CLI bundle → carried-forward last-known-good (each
+  step annotated, provenance recorded on the row); costs resolve models
+  page index → model detail page → RSC rates (never carried forward, so a
+  model going free is never billed at its old rate); modalities fall back
+  CLI bundle → models page Caps Vision bit → text-only. Total absence of
+  context or cost is a loud failure (unshippable ship-bar row) — one of
+  the two surviving loud failure classes.
+- **Sparse classification** — reasoning derives any-true-wins across
+  models.md efforts, the RSC `reasoning` flag, and the models page Caps
+  Reasoning bit; models with no evidence anywhere ship in a visible
+  pending bucket and behave as non-reasoning until evidence arrives.
+- **Models page index** — `scripts/parse-models-page.mjs` parses display
+  rates, Context strings, and Caps bits from the Command Code models page
+  (shape-strict rows, pinned Caps labels, footnote/banded-pricing notes),
+  with a pinned 68-entry slug-to-id join map and a re-captured
+  `tests/fixtures/models-page.html`.
+- **Richer refresh diffs** — a package-table row removal prunes the
+  Snapshot immediately with a loud Removed-models section; the Model
+  catalog diff gains five enrichment subsections (pending enrichment per
+  model, carried-forward context, cost-fallback provenance, API
+  divergence, banded-pricing notes); identical catalogs still
+  short-circuit to No changes.
+- **Catalog refresh** — snapshot refreshed to `command-code@1.49.1` (68
+  models); classification 68 entries, deals 71 entries, coverage gate OK.
+- **Fixes** — facts rows filtered to snapshot ids (an ahead-of-API
+  models.md row broke the cron's stale-entry check); RSC fixture
+  assertions tolerate docs-ahead-of-API records.
+
+### Follow-ups
+
+- Open issues carried forward: #136 (reasoning text rendered as normal
+  output), #102 (TUI/server init via npm package name), #90 (expired-deal
+  filtering).
+
+## 1.6.5 - 2026-09-04
+
+Automated catalog refresh.
+
 ## 1.6.4 - 2026-09-03
 
 ### Model catalog

package/README.md

@@ -13,12 +13,17 @@ A provider and plugin for [OpenCode](https://opencode.ai) that connects to the [
 opencode plugin opencode-cmd-provider
 ```
 
-Update an existing install:
+Update an existing install — OpenCode caches the plugin package and reuses it
+on every startup without checking for a newer version, so updating means
+deleting the cache:
 
 ```sh
-opencode plugin opencode-cmd-provider --force
+rm -rf ~/.cache/opencode/packages/opencode-cmd-provider*
 ```
 
+Restart OpenCode afterwards. The plugin is re-downloaded, so that first launch
+takes a little longer than usual; subsequent startups are fast again.
+
 Install globally (available in every project):
 
 ```sh
@@ -117,7 +122,9 @@ Delivery is zero-step: the package exports both a `server` and a `tui` target
 opencode-cmd-provider` writes both `opencode.json(c)` and `tui.json` from one
 spec. The sidebar is a TUI plugin loaded from `tui.json` — which is why
 installs made before the `./tui` export only wrote the server target and never
-showed a sidebar. Re-run with `--force` to add `tui.json`.
+showed a sidebar. Re-run `opencode plugin opencode-cmd-provider --force` to add
+`tui.json` (this only rewrites the config entry — see
+[Update and remove](#update-and-remove) for refreshing the cached package).
 
 When the Deals catalog is empty (the upstream fetch failed or the RSC shape
 changed), the feature degrades visibly rather than silently: the sidebar shows
@@ -135,7 +142,9 @@ paid model (e.g. the MiniMax M3 free tier) get a `(free)` suffix —
 `[CMD] MiniMax M3 (free)` — so the two are distinguishable in the model
 picker. The suffix is derived from the bundled pricing table: a model is
 labeled free only when the catalog carries an explicit zero-cost entry. Model
-availability changes when the package is updated. You can still declare your
+availability changes when the package is updated — but note that OpenCode's
+plugin cache can hold a stale copy after a release if new models don't appear
+(see [Update and remove](#update-and-remove)). You can still declare your
 own `provider.commandcode` entry; your declarations always win and the
 snapshot fills in only what's missing (`whitelist`/`blacklist` on a declared
 entry filter the auto-registered models too).
@@ -184,7 +193,9 @@ Actions cron
 (`.github/workflows/catalog-refresh.yml`, 06:00 UTC, also manually
 triggerable via `workflow_dispatch`) runs the same pipeline: when upstream
 moved it opens a `chore: catalog refresh` PR whose body is the human-readable
-diff from `scripts/diff-catalog.mjs` — model catalog, reasoning
+diff from `scripts/diff-catalog.mjs` — model catalog (change table plus
+removed-models, pending-enrichment, carried-forward-context, cost-fallback,
+API-divergence, and banded-pricing subsections), reasoning
 classification (flips, new reasoning models, retirements, active overrides),
 and deals sections; when nothing meaningful drifted it exits silently (a
 run whose only change is the refreshed-date stamps opens no PR).
@@ -232,7 +243,37 @@ Models missing from that table display zero cost in OpenCode. This does **not**
 
 ## Update and remove
 
-Update the installed package, or remove it from the `plugin` array in your `opencode.json` (the auto-registered `provider.commandcode` entry is injected by the plugin, so there is no config block to remove). The npm package is cached under OpenCode's plugin cache (`~/.cache/opencode/packages/`); remove the cached directory to fully uninstall.
+### Updating
+
+OpenCode caches the plugin package (`~/.cache/opencode/packages/`) and reuses
+the cached copy on every startup without checking for a newer version — so a
+new release won't appear until you delete the cache:
+
+```sh
+rm -rf ~/.cache/opencode/packages/opencode-cmd-provider*
+```
+
+Then restart OpenCode. The plugin is re-downloaded, so that first launch takes
+a little longer than usual; subsequent startups are fast again. If new Command
+Code models stop appearing in `/models` after a release, a stale cache entry is
+the most likely cause.
+
+- **OpenChamber users:** click **Reload OpenCode** in OpenChamber's settings
+  instead of restarting manually — the running OpenCode server keeps the old
+  plugin loaded until it is restarted.
+- **No re-authentication needed.** Your API key is stored by OpenCode's
+  `/connect` flow in OpenCode's auth store (and mirrored to
+  `~/.commandcode/auth.json`), not inside the plugin package — the plugin reads
+  it from there (or the `COMMANDCODE_API_KEY` env var) at request time, so
+  deleting the plugin cache does not affect your login.
+
+### Removing
+
+Remove it from the `plugin` array in your `opencode.json` (the auto-registered
+`provider.commandcode` entry is injected by the plugin, so there is no config
+block to remove). The npm package is cached under OpenCode's plugin cache
+(`~/.cache/opencode/packages/`); remove the cached directory to fully
+uninstall.
 
 ## Development
 

package/dist/src/catalog/classification.d.ts

@@ -1,7 +1,8 @@
 export declare const CLASSIFICATION_SOURCE_URLS: ReadonlyArray<string>;
-export declare const CLASSIFICATION_LAST_REFRESHED = "2026-09-03";
+export declare const CLASSIFICATION_LAST_REFRESHED = "2026-09-06";
 export declare const CLASSIFICATION_OVERRIDES: Readonly<Record<string, {
     capability: boolean;
     justification: string;
 }>>;
+export declare const MODEL_REASONING_PENDING: ReadonlyArray<string>;
 export declare const MODEL_REASONING_CAPABILITY: Readonly<Record<string, boolean>>;

package/dist/src/catalog/classification.js

@@ -1,9 +1,14 @@
 // src/catalog/classification.ts — GENERATED by scripts/refresh-classification.mjs. Do not edit.
 //
-// Per-model reasoning capability, derived from the `reasoning` flag on
-// the Command Code docs' RSC slug records (plans/goat + plans/pro,
-// slug-id aliasing applied, keyed by snapshot id) — the same
-// snapshot-keyed records the Deals catalog consumes. Classification is
+// Per-model reasoning capability, derived any-true-wins across the
+// models.md efforts entries, the `reasoning` flag on the Command Code
+// docs' RSC slug records (plans/goat + plans/pro, slug-id aliasing
+// applied, keyed by snapshot id), and the models page Caps Reasoning
+// bit (issue #132). The map is sparse: only models with evidence get an
+// entry (true = any channel fires; false = checked evidence is
+// all-negative). Models with NO evidence anywhere ship in
+// MODEL_REASONING_PENDING — they behave as non-reasoning at runtime and
+// flip with zero code when evidence arrives. Classification is
 // upstream-managed and derived, never hand-maintained; the only human
 // seam is CLASSIFICATION_OVERRIDES, whose entries each carry a written
 // justification naming the upstream disagreement (see ADR-0006).
@@ -13,11 +18,16 @@ export const CLASSIFICATION_SOURCE_URLS = [
     "https://commandcode.ai/docs/plans/goat",
     "https://commandcode.ai/docs/plans/pro",
 ];
-export const CLASSIFICATION_LAST_REFRESHED = "2026-09-03";
+export const CLASSIFICATION_LAST_REFRESHED = "2026-09-06";
 // Active capability overrides. Empty = upstream data is truth.
 // Every entry requires a written justification naming the upstream
 // disagreement; entries are rendered into the refresh PR body.
 export const CLASSIFICATION_OVERRIDES = {};
+// Snapshot models with no capability evidence anywhere (no RSC record,
+// no models.md efforts, no models page Reasoning bit). They behave as
+// non-reasoning and land in this bucket until evidence arrives — the
+// next refresh moves them into MODEL_REASONING_CAPABILITY with zero code.
+export const MODEL_REASONING_PENDING = [];
 export const MODEL_REASONING_CAPABILITY = {
     "claude-fable-5": true,
     "claude-fable-5-1": true,
@@ -44,6 +54,7 @@ export const MODEL_REASONING_CAPABILITY = {
     "gpt-5.6-luna": true,
     "gpt-5.6-sol": true,
     "gpt-5.6-terra": true,
+    "gpt-6-astra": true,
     "meituan/LongCat-2.0:free": true,
     "meta/muse-spark-1.1": true,
     "meta/muse-spark-1.2": true,

package/dist/src/catalog/facts.d.ts

@@ -1,7 +1,7 @@
-export declare const FACTS_SOURCE_URL = "https://unpkg.com/command-code@1.46.0/dist/bundled/command-code-knowledge/reference/models.md";
-export declare const MODALITIES_SOURCE_URL = "https://unpkg.com/command-code@1.46.0/dist/cli.mjs";
-export declare const FACTS_PACKAGE_VERSION = "1.46.0";
-export declare const FACTS_LAST_REFRESHED = "2026-09-03";
+export declare const FACTS_SOURCE_URL = "https://unpkg.com/command-code@1.49.1/dist/bundled/command-code-knowledge/reference/models.md";
+export declare const MODALITIES_SOURCE_URL = "https://unpkg.com/command-code@1.49.1/dist/cli.mjs";
+export declare const FACTS_PACKAGE_VERSION = "1.49.1";
+export declare const FACTS_LAST_REFRESHED = "2026-09-06";
 export declare const MODEL_EFFORTS: Readonly<Record<string, readonly string[]>>;
 export declare const MODEL_COSTS: Readonly<Record<string, {
     input: number;

package/dist/src/catalog/facts.js

@@ -1,13 +1,14 @@
 // src/catalog/facts.ts — GENERATED by scripts/refresh-snapshot.mjs. Do not edit.
 //
-// Capability facts (reasoning efforts + per-1M-token rates) parsed from the
-// command-code npm package's bundled model catalog (models.md), plus input
-// modalities parsed from its CLI bundle (dist/cli.mjs). Regenerate
-// with `npm run refresh:snapshot`.
-export const FACTS_SOURCE_URL = "https://unpkg.com/command-code@1.46.0/dist/bundled/command-code-knowledge/reference/models.md";
-export const MODALITIES_SOURCE_URL = "https://unpkg.com/command-code@1.46.0/dist/cli.mjs";
-export const FACTS_PACKAGE_VERSION = "1.46.0";
-export const FACTS_LAST_REFRESHED = "2026-09-03";
+// Capability facts derived from the models.md-primary Snapshot rows in
+// src/catalog/snapshot.ts (issue #130): reasoning efforts + rates parse
+// from the package table (never from the listing API). Input modalities
+// parse from the CLI bundle (dist/cli.mjs). Regenerate with
+// `npm run refresh:snapshot`.
+export const FACTS_SOURCE_URL = "https://unpkg.com/command-code@1.49.1/dist/bundled/command-code-knowledge/reference/models.md";
+export const MODALITIES_SOURCE_URL = "https://unpkg.com/command-code@1.49.1/dist/cli.mjs";
+export const FACTS_PACKAGE_VERSION = "1.49.1";
+export const FACTS_LAST_REFRESHED = "2026-09-06";
 export const MODEL_EFFORTS = {
     "deepseek/deepseek-v4-pro": ["high", "max"],
     "deepseek/deepseek-v4-flash": ["high", "max"],
@@ -29,6 +30,7 @@ export const MODEL_EFFORTS = {
     "claude-opus-5": ["low", "medium", "high", "xhigh", "max"],
     "claude-opus-4-8": ["low", "medium", "high", "xhigh", "max"],
     "claude-opus-4-7": ["low", "medium", "high", "xhigh", "max"],
+    "gpt-6-astra": ["low", "medium", "high", "xhigh", "max"],
     "gpt-5.6-sol": ["low", "medium", "high", "xhigh", "max"],
     "gpt-5.6-terra": ["low", "medium", "high", "xhigh", "max"],
     "gpt-5.6-luna": ["low", "medium", "high", "xhigh", "max"],
@@ -46,7 +48,7 @@ export const MODEL_EFFORTS = {
     "meta/muse-spark-1.1": ["low", "medium", "high", "xhigh"],
     "meta/muse-spark-1.2": ["low", "medium", "high", "xhigh"],
     "meta/muse-spark-1.2-contributor": ["low", "medium", "high", "xhigh"],
-    "meta/muse-spark-1.3": ["low", "medium", "high", "xhigh"],
+    "meta/muse-spark-1.3": ["low", "medium", "high", "xhigh", "max"],
     "meta/muse-spark-1.3-contributor": ["low", "medium", "high", "xhigh"],
     "xai/grok-4.5": ["low", "medium", "high"],
     "xai/grok-4.6": ["low", "medium", "high", "xhigh"],
@@ -98,6 +100,7 @@ export const MODEL_COSTS = {
     "claude-opus-4-8": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
     "claude-opus-4-7": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
     "claude-haiku-4-5-20251001": { input: 1, output: 5, cacheRead: 0.1, cacheWrite: 1.25 },
+    "gpt-6-astra": { input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 },
     "gpt-5.6-sol": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 6.25 },
     "gpt-5.6-terra": { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 2.5 },
     "gpt-5.6-luna": { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite: 0.25 },
@@ -151,6 +154,7 @@ export const MODEL_INPUT_MODALITIES = {
     "gpt-5.6-luna": ["text", "image"],
     "gpt-5.6-sol": ["text", "image"],
     "gpt-5.6-terra": ["text", "image"],
+    "gpt-6-astra": ["text", "image"],
     "meta/muse-spark-1.1": ["text", "image"],
     "meta/muse-spark-1.2": ["text", "image"],
     "meta/muse-spark-1.2-contributor": ["text", "image"],
@@ -166,6 +170,7 @@ export const MODEL_INPUT_MODALITIES = {
     "thinkingmachines/inkling": ["text", "image"],
     "thinkingmachines/inkling-small": ["text", "image"],
     "xai/grok-4.5": ["text", "image"],
+    "xai/grok-4.6": ["text", "image"],
     "xiaomi/mimo-v2.5": ["text", "image"],
     "z-ai/glm-5.3-flash": ["text", "image"],
 };

package/dist/src/catalog/snapshot.d.ts

@@ -1,6 +1,17 @@
 export interface CatalogModel {
     readonly id: string;
     readonly name: string;
-    readonly contextLength: number;
+    readonly contextLength: number | null;
+    /** "models.md" when the package cell parsed; else the ladder step that resolved it. */
+    readonly contextSource: "models.md" | "rsc" | "cli" | "carried-forward";
+    readonly efforts: readonly string[] | null;
+    readonly cost: {
+        readonly input: number;
+        readonly output: number;
+        readonly cacheRead: number;
+        readonly cacheWrite: number;
+    } | null;
+    /** "models.md" when the package cell parsed; else the ladder step that resolved it. */
+    readonly costSource: "models.md" | "models-page" | "detail" | "rsc";
 }
 export declare const MODEL_SNAPSHOT: readonly CatalogModel[];

package/dist/src/catalog/snapshot.js

@@ -1,74 +1,83 @@
 // src/catalog/snapshot.ts — GENERATED by scripts/refresh-snapshot.mjs. Do not edit.
 //
-// A copy of the Command Code model catalog (id, name, context length) bundled
-// in the package so the plugin can auto-register every model without network
-// access at runtime. Regenerate with `npm run refresh:snapshot`.
+// A copy of the Command Code model catalog bundled in the package so the
+// plugin can auto-register every model without network access at runtime.
+// Since issue #130 the npm package models.md table is the sole membership
+// authority: every models.md row ships here with its ship-bar fields
+// (id, name, context length parsed from the coarse Context column, costs,
+// efforts). Since issue #132 a blank models.md cell is resolved through
+// the ordered enrichment ladders (context: RSC contextWindow → CLI
+// contextWindow → carried-forward; cost: models page index → detail page
+// → RSC rates — costs never carry forward), and each row carries its
+// `contextSource` / `costSource` provenance. The listing API decides
+// nothing and wins no field. Regenerate with `npm run refresh:snapshot`.
 export const MODEL_SNAPSHOT = [
-    { id: "claude-sonnet-5", name: "Claude Sonnet 5", contextLength: 1000000 },
-    { id: "claude-sonnet-4-6", name: "Claude Sonnet 4.6", contextLength: 1000000 },
-    { id: "claude-fable-5-1", name: "Claude Fable 5.1", contextLength: 1000000 },
-    { id: "claude-fable-5", name: "Claude Fable 5", contextLength: 1000000 },
-    { id: "claude-opus-5", name: "Claude Opus 5", contextLength: 1000000 },
-    { id: "claude-opus-4-8", name: "Claude Opus 4.8", contextLength: 1000000 },
-    { id: "claude-opus-4-7", name: "Claude Opus 4.7", contextLength: 1000000 },
-    { id: "claude-haiku-4-5-20251001", name: "Claude Haiku 4.5", contextLength: 200000 },
-    { id: "gpt-5.6-sol", name: "GPT-5.6 Sol", contextLength: 1050000 },
-    { id: "gpt-5.6-terra", name: "GPT-5.6 Terra", contextLength: 1050000 },
-    { id: "gpt-5.6-luna", name: "GPT-5.6 Luna", contextLength: 1050000 },
-    { id: "gpt-5.5", name: "GPT-5.5", contextLength: 400000 },
-    { id: "gpt-5.4", name: "GPT-5.4", contextLength: 400000 },
-    { id: "gpt-5.3-codex", name: "GPT-5.3 Codex", contextLength: 400000 },
-    { id: "gpt-5.4-mini", name: "GPT-5.4 Mini", contextLength: 400000 },
-    { id: "deepseek/deepseek-v4-pro", name: "DeepSeek V4 Pro (latest)", contextLength: 1000000 },
-    { id: "deepseek/deepseek-v4-flash", name: "DeepSeek V4 Flash (latest)", contextLength: 1000000 },
-    { id: "deepseek/deepseek-v4-flash-vision-exp", name: "DeepSeek V4 Flash Vision (exp)", contextLength: 1000000 },
-    { id: "deepseek/deepseek-v4-flash-fast", name: "DeepSeek V4 Flash Fast", contextLength: 1000000 },
-    { id: "moonshotai/Kimi-K3", name: "Kimi K3", contextLength: 1000000 },
-    { id: "moonshotai/Kimi-K2.7-Code", name: "Kimi K2.7 Code", contextLength: 256000 },
-    { id: "moonshotai/Kimi-K2.7-Code-Highspeed", name: "Kimi K2.7 Code HighSpeed", contextLength: 262000 },
-    { id: "moonshotai/Kimi-K2.6", name: "Kimi K2.6", contextLength: 256000 },
-    { id: "moonshotai/Kimi-K2.5", name: "Kimi K2.5", contextLength: 256000 },
-    { id: "z-ai/glm-5.3-flash", name: "GLM-5.3 Flash", contextLength: 1048576 },
-    { id: "zai-org/GLM-5.3", name: "GLM-5.3", contextLength: 1000000 },
-    { id: "zai-org/GLM-5.2", name: "GLM-5.2", contextLength: 1000000 },
-    { id: "zai-org/GLM-5.2-Fast", name: "GLM-5.2 Fast", contextLength: 1000000 },
-    { id: "zai-org/GLM-5.1", name: "GLM-5.1", contextLength: 200000 },
-    { id: "zai-org/GLM-5", name: "GLM-5", contextLength: 200000 },
-    { id: "MiniMaxAI/MiniMax-M3", name: "MiniMax M3", contextLength: 1000000 },
-    { id: "MiniMaxAI/MiniMax-M2.7", name: "MiniMax M2.7", contextLength: 200000 },
-    { id: "MiniMaxAI/MiniMax-M2.5", name: "MiniMax M2.5", contextLength: 200000 },
-    { id: "xiaomi/mimo-v2.5-pro", name: "MiMo V2.5 Pro", contextLength: 1000000 },
-    { id: "xiaomi/mimo-v2.5", name: "MiMo V2.5", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.8-Max-0902", name: "Qwen 3.8 Max 0902", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.8-Max", name: "Qwen 3.8 Max", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.8-27B", name: "Qwen 3.8 27B", contextLength: 262144 },
-    { id: "Qwen/Qwen3.8-Flash", name: "Qwen 3.8 Flash", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.7-Max", name: "Qwen 3.7 Max", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.7-Plus", name: "Qwen 3.7 Plus", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.7-Flash", name: "Qwen 3.7 Flash", contextLength: 1000000 },
-    { id: "Qwen/Qwen3.6-Max-Preview", name: "Qwen 3.6 Max Preview", contextLength: 200000 },
-    { id: "Qwen/Qwen3.6-Plus", name: "Qwen 3.6 Plus", contextLength: 200000 },
-    { id: "meituan/LongCat-2.0:free", name: "LongCat 2.0", contextLength: 1048576 },
-    { id: "stepfun/Step-3.7-Flash", name: "Step 3.7 Flash", contextLength: 256000 },
-    { id: "stepfun/Step-3.5-Flash", name: "Step 3.5 Flash", contextLength: 1000000 },
-    { id: "tencent/hy3-paid", name: "Tencent Hy3", contextLength: 262144 },
-    { id: "tencent/hy4-preview", name: "Tencent Hy4 Preview", contextLength: 1048576 },
-    { id: "google/gemini-3.8-flash", name: "Gemini 3.8 Flash", contextLength: 1000000 },
-    { id: "google/gemini-3.7-flash", name: "Gemini 3.7 Flash", contextLength: 1048576 },
-    { id: "google/gemini-3.6-flash", name: "Gemini 3.6 Flash", contextLength: 1000000 },
-    { id: "google/gemini-3.5-flash", name: "Gemini 3.5 Flash", contextLength: 1000000 },
-    { id: "google/gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite", contextLength: 1000000 },
-    { id: "google/gemini-3.1-flash-lite", name: "Gemini 3.1 Flash Lite", contextLength: 1000000 },
-    { id: "sakana/fugu-ultra", name: "Fugu Ultra", contextLength: 1000000 },
-    { id: "nvidia/nemotron-3-ultra-550b-a55b", name: "Nemotron 3 Ultra", contextLength: 1000000 },
-    { id: "thinkingmachines/inkling", name: "Inkling", contextLength: 256000 },
-    { id: "thinkingmachines/inkling-small", name: "Inkling Small", contextLength: 1000000 },
-    { id: "poolside/laguna-s-2.1-free", name: "Laguna S 2.1", contextLength: 256000 },
-    { id: "meta/muse-spark-1.1", name: "Muse Spark 1.1", contextLength: 1048576 },
-    { id: "meta/muse-spark-1.2", name: "Muse Spark 1.2", contextLength: 1048576 },
-    { id: "meta/muse-spark-1.2-contributor", name: "Muse Spark 1.2 Contributor", contextLength: 1048576 },
-    { id: "meta/muse-spark-1.3", name: "Muse Spark 1.3", contextLength: 1048576 },
-    { id: "meta/muse-spark-1.3-contributor", name: "Muse Spark 1.3 Contributor", contextLength: 1048576 },
-    { id: "xai/grok-4.5", name: "Grok 4.5", contextLength: 500000 },
-    { id: "xai/grok-4.6", name: "Grok 4.6", contextLength: 500000 },
+    { id: "deepseek/deepseek-v4-pro", name: "DeepSeek V4 Pro (latest)", contextLength: 1000000, contextSource: "models.md", efforts: ["high", "max"], cost: { input: 0.66, output: 1.98, cacheRead: 0.022, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "deepseek/deepseek-v4-flash", name: "DeepSeek V4 Flash (latest)", contextLength: 1000000, contextSource: "models.md", efforts: ["high", "max"], cost: { input: 0.22, output: 0.66, cacheRead: 0.007, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "deepseek/deepseek-v4-flash-vision-exp", name: "DeepSeek V4 Flash Vision (exp)", contextLength: 1000000, contextSource: "models.md", efforts: ["high", "max"], cost: { input: 0.22, output: 0.66, cacheRead: 0.007, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "deepseek/deepseek-v4-flash-fast", name: "DeepSeek V4 Flash Fast", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "high", "max"], cost: { input: 0.28, output: 0.56, cacheRead: 0.07, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "moonshotai/Kimi-K3", name: "Kimi K3", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "high", "max"], cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "moonshotai/Kimi-K2.7-Code", name: "Kimi K2.7 Code", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "moonshotai/Kimi-K2.7-Code-Highspeed", name: "Kimi K2.7 Code HighSpeed", contextLength: 262000, contextSource: "models.md", efforts: null, cost: { input: 1.9, output: 8, cacheRead: 0.38, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "moonshotai/Kimi-K2.6", name: "Kimi K2.6", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "moonshotai/Kimi-K2.5", name: "Kimi K2.5", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "z-ai/glm-5.3-flash", name: "GLM-5.3 Flash", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "high", "max"], cost: { input: 0.15, output: 0.5, cacheRead: 0.03, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "zai-org/GLM-5.3", name: "GLM-5.3", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "high", "max"], cost: { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "zai-org/GLM-5.2", name: "GLM-5.2", contextLength: 1000000, contextSource: "models.md", efforts: ["high", "max"], cost: { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "zai-org/GLM-5.2-Fast", name: "GLM-5.2 Fast", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 3, output: 10.25, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "zai-org/GLM-5.1", name: "GLM-5.1", contextLength: 200000, contextSource: "rsc", efforts: null, cost: { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "zai-org/GLM-5", name: "GLM-5", contextLength: 200000, contextSource: "models.md", efforts: null, cost: { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "MiniMaxAI/MiniMax-M3", name: "MiniMax M3", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "MiniMaxAI/MiniMax-M2.7", name: "MiniMax M2.7", contextLength: 200000, contextSource: "rsc", efforts: null, cost: { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "MiniMaxAI/MiniMax-M2.5", name: "MiniMax M2.5", contextLength: 200000, contextSource: "models.md", efforts: null, cost: { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "xiaomi/mimo-v2.5-pro", name: "MiMo V2.5 Pro", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.435, output: 0.87, cacheRead: 0.0036, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "xiaomi/mimo-v2.5", name: "MiMo V2.5", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.8-Max-0902", name: "Qwen 3.8 Max 0902", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "xhigh"], cost: { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.8-Max", name: "Qwen 3.8 Max", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "xhigh"], cost: { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 2.5 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.8-27B", name: "Qwen 3.8 27B", contextLength: 262000, contextSource: "models.md", efforts: ["low", "medium", "xhigh"], cost: { input: 0.4, output: 3, cacheRead: 0.04, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.8-Flash", name: "Qwen 3.8 Flash", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "xhigh"], cost: { input: 0.16, output: 0.47, cacheRead: 0.016, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.7-Max", name: "Qwen 3.7 Max", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 2.5, output: 7.5, cacheRead: 0.5, cacheWrite: 3.13 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.7-Plus", name: "Qwen 3.7 Plus", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.4, output: 1.6, cacheRead: 0.08, cacheWrite: 0.5 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.7-Flash", name: "Qwen 3.7 Flash", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.03, output: 0.13, cacheRead: 0.006, cacheWrite: 0.038 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.6-Max-Preview", name: "Qwen 3.6 Max Preview", contextLength: 200000, contextSource: "rsc", efforts: null, cost: { input: 1.3, output: 7.8, cacheRead: 0.26, cacheWrite: 1.63 }, costSource: "models.md" },
+    { id: "Qwen/Qwen3.6-Plus", name: "Qwen 3.6 Plus", contextLength: 200000, contextSource: "rsc", efforts: null, cost: { input: 0.5, output: 3, cacheRead: 0.1, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meituan/LongCat-2.0:free", name: "LongCat 2.0", contextLength: 1050000, contextSource: "models.md", efforts: null, cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "stepfun/Step-3.7-Flash", name: "Step 3.7 Flash", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "stepfun/Step-3.5-Flash", name: "Step 3.5 Flash", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "tencent/hy3-paid", name: "Tencent Hy3", contextLength: 262000, contextSource: "models.md", efforts: null, cost: { input: 0.14, output: 0.58, cacheRead: 0.035, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "tencent/hy4-preview", name: "Tencent Hy4 Preview", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 0.834, output: 2.501, cacheRead: 0.042, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "nvidia/nemotron-3-ultra-550b-a55b", name: "Nemotron 3 Ultra", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "thinkingmachines/inkling", name: "Inkling", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 1, output: 4.05, cacheRead: 0.17, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "thinkingmachines/inkling-small", name: "Inkling Small", contextLength: 1000000, contextSource: "models.md", efforts: null, cost: { input: 0.5, output: 1.2, cacheRead: 0.1, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "poolside/laguna-s-2.1-free", name: "Laguna S 2.1", contextLength: 256000, contextSource: "models.md", efforts: null, cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "claude-sonnet-5", name: "Claude Sonnet 5", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 2, output: 10, cacheRead: 0.2, cacheWrite: 2.5 }, costSource: "models.md" },
+    { id: "claude-sonnet-4-6", name: "Claude Sonnet 4.6", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 }, costSource: "models.md" },
+    { id: "claude-fable-5-1", name: "Claude Fable 5.1", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 10, output: 50, cacheRead: 0.25, cacheWrite: 12.5 }, costSource: "models.md" },
+    { id: "claude-fable-5", name: "Claude Fable 5", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 }, costSource: "models.md" },
+    { id: "claude-opus-5", name: "Claude Opus 5", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 }, costSource: "models.md" },
+    { id: "claude-opus-4-8", name: "Claude Opus 4.8", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 }, costSource: "models.md" },
+    { id: "claude-opus-4-7", name: "Claude Opus 4.7", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 }, costSource: "models.md" },
+    { id: "claude-haiku-4-5-20251001", name: "Claude Haiku 4.5", contextLength: 200000, contextSource: "models.md", efforts: null, cost: { input: 1, output: 5, cacheRead: 0.1, cacheWrite: 1.25 }, costSource: "models.md" },
+    { id: "gpt-6-astra", name: "GPT-6 Astra", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 }, costSource: "models.md" },
+    { id: "gpt-5.6-sol", name: "GPT-5.6 Sol", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 6.25 }, costSource: "models.md" },
+    { id: "gpt-5.6-terra", name: "GPT-5.6 Terra", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 2.5 }, costSource: "models.md" },
+    { id: "gpt-5.6-luna", name: "GPT-5.6 Luna", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite: 0.25 }, costSource: "models.md" },
+    { id: "gpt-5.5", name: "GPT-5.5", contextLength: 400000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "gpt-5.4", name: "GPT-5.4", contextLength: 400000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "gpt-5.3-codex", name: "GPT-5.3 Codex", contextLength: 400000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 2, output: 8, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "gpt-5.4-mini", name: "GPT-5.4 Mini", contextLength: 400000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 0.75, output: 4.5, cacheRead: 0.075, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "google/gemini-3.8-flash", name: "Gemini 3.8 Flash", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 1.5, output: 7.5, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "google/gemini-3.7-flash", name: "Gemini 3.7 Flash", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 1.5, output: 7.5, cacheRead: 0.15, cacheWrite: 0.08334 }, costSource: "models.md" },
+    { id: "google/gemini-3.6-flash", name: "Gemini 3.6 Flash", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 1.5, output: 7.5, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "google/gemini-3.5-flash", name: "Gemini 3.5 Flash", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 1.5, output: 9, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "google/gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 0.3, output: 2.5, cacheRead: 0.03, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "google/gemini-3.1-flash-lite", name: "Gemini 3.1 Flash Lite", contextLength: 1000000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 0.25, output: 1.5, cacheRead: 0.03, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "sakana/fugu-ultra", name: "Fugu Ultra", contextLength: 1000000, contextSource: "models.md", efforts: ["high", "xhigh"], cost: { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meta/muse-spark-1.1", name: "Muse Spark 1.1", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meta/muse-spark-1.2", name: "Muse Spark 1.2", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meta/muse-spark-1.2-contributor", name: "Muse Spark 1.2 Contributor", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 0.1, output: 0.2, cacheRead: 0.002, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meta/muse-spark-1.3", name: "Muse Spark 1.3", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh", "max"], cost: { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "meta/muse-spark-1.3-contributor", name: "Muse Spark 1.3 Contributor", contextLength: 1050000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 0.1, output: 0.2, cacheRead: 0.002, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "xai/grok-4.5", name: "Grok 4.5", contextLength: 500000, contextSource: "models.md", efforts: ["low", "medium", "high"], cost: { input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
+    { id: "xai/grok-4.6", name: "Grok 4.6", contextLength: 500000, contextSource: "models.md", efforts: ["low", "medium", "high", "xhigh"], cost: { input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0 }, costSource: "models.md" },
 ];

package/dist/src/deals/catalog.d.ts

@@ -51,5 +51,5 @@ export interface ModelDeals {
 export declare const MODEL_DEALS: Readonly<Record<string, ModelDeals>>;
 export declare const PLAN_CATALOG: Readonly<Record<PlanId, PlanInfo>>;
 export declare const DEAL_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits";
-export declare const DEAL_LAST_REFRESHED = "2026-09-03";
+export declare const DEAL_LAST_REFRESHED = "2026-09-06";
 export declare const DEAL_PACKAGE_VERSION = "docs";

package/dist/src/deals/catalog.js

@@ -30,6 +30,7 @@ export const MODEL_DEALS = {
     "gpt-5.6-luna": { tier: "opensource", benchmark: { "intelligence": 52.3, "tokPerSec": 124.1 }, overContext: { "input": 0.4, "output": 1.8, "cacheRead": 0.04, "cacheWrite": 0.5 }, free: false, allowance: { "goat": 20, "pro": 30 } },
     "gpt-5.6-sol": { tier: "opensource", benchmark: { "intelligence": 60.9, "tokPerSec": 69.6 }, overContext: { "input": 10, "output": 45, "cacheRead": 1, "cacheWrite": 12.5 }, free: false, allowance: { "goat": 70, "pro": 80 } },
     "gpt-5.6-terra": { tier: "premium", benchmark: { "intelligence": 56.6, "tokPerSec": 112.8 }, overContext: { "input": 4, "output": 18, "cacheRead": 0.4, "cacheWrite": 5 }, free: false, allowance: { "goat": 20, "pro": 20 } },
+    "gpt-6-astra": { tier: "premium", overContext: { "input": 20, "output": 75, "cacheRead": 2, "cacheWrite": 25 }, free: false, allowance: { "goat": 20, "pro": 20 } },
     "meituan/LongCat-2.0:free": { tier: "opensource", free: true },
     "meta/muse-spark-1.1": { tier: "premium", benchmark: { "intelligence": 53.2 }, free: false, allowance: { "goat": 20, "pro": 20 } },
     "meta/muse-spark-1.2": { tier: "opensource", benchmark: { "intelligence": 56.8 }, free: false, allowance: { "goat": 20, "pro": 30 } },
@@ -83,5 +84,5 @@ export const PLAN_CATALOG = {
     provider: { price: 15, credits: 0, window5h: 0, windowWeek: 0, display: "Provider" },
 };
 export const DEAL_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits";
-export const DEAL_LAST_REFRESHED = "2026-09-03";
+export const DEAL_LAST_REFRESHED = "2026-09-06";
 export const DEAL_PACKAGE_VERSION = "docs";

package/dist/src/plugin/models.js

@@ -1,8 +1,16 @@
-import { MODEL_COSTS, ZERO_MODEL_COST, isFreeModelCost, } from "../provider/pricing.js";
+import { isFreeModelCost } from "../provider/pricing.js";
 import { reasoningVariantsForModel, isReasoningModel } from "../provider/reasoning.js";
 import { inputModalitiesForModel } from "../provider/modalities.js";
 const DEFAULT_MAX_OUTPUT_TOKENS = 65_536;
 export const DEFAULT_DISPLAY_PREFIX = "[CMD] ";
+// Context advertised for a snapshot row whose models.md Context cell is
+// missing ("—"): the row ships as pending-context (issue #130) and the
+// fallback ladder lands in #132. OpenCode requires a numeric limit, so a
+// conservative placeholder keeps the model usable — it is deliberately
+// NOT the listing API's value (the API wins no ship-bar field) and NOT
+// any carried-forward number: a reviewer sees the real gap in the
+// refresh log's "context pending" note and the #132 ladder resolves it.
+const PENDING_CONTEXT_LENGTH = 128_000;
 /**
  * Resolves the auto-registration display-name prefix from the user-declared
  * `provider.commandcode.options.display_prefix` key. A string value is used
@@ -91,21 +99,34 @@ export function augmentConfigCommandCodeModels(config) {
  * prefixed display name, context/output limits with output capped at
  * 65_536, and metadata enriched from the reasoning, modality, and pricing
  * tables.
+ *
+ * Ship-bar fields come from the snapshot row itself (issue #130: the
+ * models.md row is the authority; the listing API wins no field):
+ *  - contextLength null (the models.md Context cell was "—") falls back to
+ *    the OpenCode default context — never 0, never a fabricated API value;
+ *  - cost null (the price cell was "—") advertises NO cost entry — missing
+ *    never zero-fills (only an explicit all-zero cell means free).
  */
 function configModelFor(model, prefix = DEFAULT_DISPLAY_PREFIX) {
     const variants = reasoningVariantsForModel(model.id);
-    const costs = MODEL_COSTS[model.id] ?? ZERO_MODEL_COST;
-    // Upstream names the paid and free MiniMax variants identically
-    // (`MiniMax M3` / `MiniMax M2.7`); append `(free)` to the picker entry so
-    // users can tell them apart. Data-driven from the zero cost table — a model
-    // is only "free" when the catalog has an actual zero-cost entry (an absent
-    // entry falls back to ZERO_MODEL_COST and is NOT free).
-    const freeSuffix = MODEL_COSTS[model.id] !== undefined && isFreeModelCost(costs) ? " (free)" : "";
+    // The row's own parsed price is the ship-bar authority. A null cost
+    // (missing models.md price cell) advertises no cost entry — the
+    // zero-cost defensive fallback (ZERO_MODEL_COST) is deliberately not
+    // used here: a missing price must never read as a $0 model (the parent
+    // spec's "missing never zero-fills").
+    const rowCost = model.cost;
+    const freeSuffix = rowCost !== null && isFreeModelCost(rowCost) ? " (free)" : "";
+    // OpenCode requires a numeric context limit. A package row whose Context
+    // cell is missing ships as pending-context (issue #130) and must not read
+    // as 0 — that would advertise a broken model. PENDING_CONTEXT_LENGTH is
+    // a conservative placeholder for such a row until the ladder (issue
+    // #132) resolves it.
+    const contextLength = model.contextLength ?? PENDING_CONTEXT_LENGTH;
     return {
         name: `${prefix}${model.name}${freeSuffix}`,
         limit: {
-            context: model.contextLength,
-            output: Math.min(model.contextLength, DEFAULT_MAX_OUTPUT_TOKENS),
+            context: contextLength,
+            output: Math.min(contextLength, DEFAULT_MAX_OUTPUT_TOKENS),
         },
         reasoning: isReasoningModel(model.id) ? true : undefined,
         variants: variants,
@@ -118,12 +139,16 @@ function configModelFor(model, prefix = DEFAULT_DISPLAY_PREFIX) {
         modalities: {
             input: [...inputModalitiesForModel(model.id)],
         },
-        cost: {
-            input: costs.input,
-            output: costs.output,
-            cache_read: costs.cacheRead,
-            cache_write: costs.cacheWrite,
-        },
+        ...(rowCost !== null
+            ? {
+                cost: {
+                    input: rowCost.input,
+                    output: rowCost.output,
+                    cache_read: rowCost.cacheRead,
+                    cache_write: rowCost.cacheWrite,
+                },
+            }
+            : {}),
         status: "active",
     };
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-cmd-provider",
-  "version": "1.6.4",
+  "version": "1.7.0",
   "description": "Command Code provider + plugin for opencode",
   "type": "module",
   "main": "./dist/index.js",
@@ -23,7 +23,7 @@
     "refresh:classification": "node scripts/refresh-classification.mjs",
     "refresh": "npm run refresh:snapshot && npm run refresh:fixtures && npm run refresh:classification -- --fixtures && npm run refresh:deals -- --fixtures",
     "test": "npm run typecheck && npm run test:unit && npm run test:integration && npm run test:contract && npm run format:check",
-    "test:unit": "tsx tests/env.test.ts && tsx tests/auth-key.test.ts && tsx tests/converters.test.ts && tsx tests/stream.test.ts && tsx tests/provider-codecs.test.ts && tsx tests/provider-transport.test.ts && tsx tests/provider-parity.test.ts && tsx tests/provider-upgrade-fallback.test.ts && tsx tests/provider-zdr.test.ts && tsx tests/redact.test.ts && tsx tests/cost.test.ts && tsx tests/retry.test.ts && tsx tests/reasoning.test.ts && tsx tests/modalities.test.ts && tsx tests/snapshot.test.ts && tsx tests/refresh-snapshot.test.ts && tsx tests/oauth.test.ts && tsx tests/auth-mirror.test.ts && tsx tests/parse-facts.test.ts && tsx tests/parse-modalities.test.ts && tsx tests/catalog-metadata.test.ts && tsx tests/plugin-models.test.ts && tsx tests/vendor.test.ts && tsx tests/deals-enrichment.test.ts && tsx tests/deals-coverage.test.ts && tsx tests/plan-summary.test.ts && tsx tests/html-tables.test.ts && tsx tests/parse-docs.test.ts && tsx tests/parse-rsc.test.ts && tsx tests/rsc-source.test.ts && tsx tests/classification-overrides.test.ts && tsx tests/refresh-classification.test.ts && tsx tests/classification.test.ts && tsx tests/no-upstream-value-pins.test.ts && tsx tests/mock-cc-rsc.test.ts && tsx tests/capture-rsc-fixtures.test.ts && tsx tests/refresh-deals.test.ts && tsx tests/refresh-deals-rsc.test.ts && tsx tests/tier-overrides.test.ts && tsx tests/tui-deals-panel.test.ts && tsx tests/diff-catalog.test.ts && tsx tests/catalog-refresh-extract.test.ts && tsx tests/catalog-refresh-drift.test.ts && tsx tests/catalog-refresh-push.test.ts && tsx tests/auto-release.test.ts && tsx tests/replay-verification.test.ts && tsx tests/plugin-install.test.ts",
+    "test:unit": "tsx tests/env.test.ts && tsx tests/auth-key.test.ts && tsx tests/converters.test.ts && tsx tests/stream.test.ts && tsx tests/provider-codecs.test.ts && tsx tests/provider-transport.test.ts && tsx tests/provider-parity.test.ts && tsx tests/provider-upgrade-fallback.test.ts && tsx tests/provider-zdr.test.ts && tsx tests/redact.test.ts && tsx tests/cost.test.ts && tsx tests/retry.test.ts && tsx tests/reasoning.test.ts && tsx tests/modalities.test.ts && tsx tests/snapshot.test.ts && tsx tests/refresh-snapshot.test.ts && tsx tests/api-demotion.test.ts && tsx tests/ladders.test.ts && tsx tests/retire-prune.test.ts && tsx tests/enrichment-sections.test.ts && tsx tests/oauth.test.ts && tsx tests/auth-mirror.test.ts && tsx tests/parse-facts.test.ts && tsx tests/parse-modalities.test.ts && tsx tests/catalog-metadata.test.ts && tsx tests/plugin-models.test.ts && tsx tests/vendor.test.ts && tsx tests/deals-enrichment.test.ts && tsx tests/deals-coverage.test.ts && tsx tests/plan-summary.test.ts && tsx tests/html-tables.test.ts && tsx tests/parse-docs.test.ts && tsx tests/parse-rsc.test.ts && tsx tests/parse-models-page.test.ts && tsx tests/rsc-source.test.ts && tsx tests/classification-overrides.test.ts && tsx tests/refresh-classification.test.ts && tsx tests/classification.test.ts && tsx tests/no-upstream-value-pins.test.ts && tsx tests/mock-cc-rsc.test.ts && tsx tests/capture-rsc-fixtures.test.ts && tsx tests/refresh-deals.test.ts && tsx tests/refresh-deals-rsc.test.ts && tsx tests/tier-overrides.test.ts && tsx tests/tui-deals-panel.test.ts && tsx tests/diff-catalog.test.ts && tsx tests/catalog-refresh-extract.test.ts && tsx tests/catalog-refresh-drift.test.ts && tsx tests/catalog-refresh-push.test.ts && tsx tests/auto-release.test.ts && tsx tests/replay-verification.test.ts && tsx tests/plugin-install.test.ts",
     "test:integration": "tsx tests/integration-do-stream.test.ts && tsx tests/integration-do-generate.test.ts",
     "test:contract": "tsx tests/contract.test.ts",
     "test:e2e": "node tests/e2e-opencode.mjs",