pi-commandcode-provider 0.4.2 → 0.5.0

package/src/pricing.ts

@@ -0,0 +1,226 @@
+export interface CommandCodeModelCostRates {
+  input: number
+  output: number
+  cacheRead: number
+  cacheWrite: number
+}
+
+export interface CommandCodeModelCostTier extends CommandCodeModelCostRates {
+  inputTokensAbove: number
+}
+
+export interface CommandCodeModelCost extends CommandCodeModelCostRates {
+  tiers?: readonly CommandCodeModelCostTier[]
+}
+
+export interface TemporaryPricing {
+  models: readonly string[]
+  expiresOn: string
+  description: string
+}
+
+export const PRICING_SOURCE_URL = "https://commandcode.ai/docs/resources/pricing-limits"
+export const PRICING_LAST_VERIFIED = "2026-08-04"
+
+export const ZERO_MODEL_COST: CommandCodeModelCost = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+}
+
+/**
+ * Display prices in USD per million tokens.
+ *
+ * Context-dependent rates use pi's request-wide input pricing tiers. The
+ * highest threshold exceeded by input + cache reads + cache writes applies to
+ * the full request. The Command Code usage page remains authoritative for the
+ * amount billed for an individual request.
+ */
+export const MODEL_COSTS: Readonly<Record<string, CommandCodeModelCost>> = {
+  // Free models
+  "poolside/laguna-s-2.1-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+  "inclusionai/ling-3.0-flash-free": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+
+  // Open and open-weight models
+  "tencent/hy3-paid": { input: 0.14, output: 0.58, cacheRead: 0.035, cacheWrite: 0 },
+  "moonshotai/Kimi-K3": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.7-Code": { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.7-Code-Highspeed": {
+    input: 1.9,
+    output: 8,
+    cacheRead: 0.38,
+    cacheWrite: 0,
+  },
+  "moonshotai/Kimi-K2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
+  "moonshotai/Kimi-K2.5": { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "zai-org/GLM-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "zai-org/GLM-5.2-Fast": { input: 3, output: 10.25, cacheRead: 0.5, cacheWrite: 0 },
+  "zai-org/GLM-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "zai-org/GLM-5": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M3": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "MiniMaxAI/MiniMax-M2.5": { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0 },
+  // Permanent 75% discount.
+  "deepseek/deepseek-v4-pro": {
+    input: 0.435,
+    output: 0.87,
+    cacheRead: 0.003625,
+    cacheWrite: 0,
+  },
+  "deepseek/deepseek-v4-flash": {
+    input: 0.14,
+    output: 0.28,
+    cacheRead: 0.0028,
+    cacheWrite: 0,
+  },
+  "Qwen/Qwen3.8-Max": { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 2.5 },
+  "Qwen/Qwen3.7-Max": { input: 2.5, output: 7.5, cacheRead: 0.5, cacheWrite: 3.13 },
+  "Qwen/Qwen3.7-Plus": {
+    input: 0.4,
+    output: 1.6,
+    cacheRead: 0.08,
+    cacheWrite: 0.5,
+    tiers: [
+      {
+        inputTokensAbove: 256_000,
+        input: 1.2,
+        output: 4.8,
+        cacheRead: 0.24,
+        cacheWrite: 1.5,
+      },
+    ],
+  },
+  "Qwen/Qwen3.7-Flash": {
+    input: 0.03,
+    output: 0.13,
+    cacheRead: 0.006,
+    cacheWrite: 0.038,
+    tiers: [
+      {
+        inputTokensAbove: 32_000,
+        input: 0.1,
+        output: 0.4,
+        cacheRead: 0.02,
+        cacheWrite: 0.125,
+      },
+      {
+        inputTokensAbove: 256_000,
+        input: 0.2,
+        output: 0.8,
+        cacheRead: 0.04,
+        cacheWrite: 0.25,
+      },
+    ],
+  },
+  "Qwen/Qwen3.6-Max-Preview": {
+    input: 1.3,
+    output: 7.8,
+    cacheRead: 0.26,
+    cacheWrite: 1.63,
+  },
+  "Qwen/Qwen3.6-Plus": { input: 0.5, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "stepfun/Step-3.7-Flash": { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 },
+  "stepfun/Step-3.5-Flash": { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 },
+  // Permanent discounted rates.
+  "xiaomi/mimo-v2.5-pro": { input: 0.435, output: 0.87, cacheRead: 0.0036, cacheWrite: 0 },
+  "xiaomi/mimo-v2.5": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
+  "nvidia/nemotron-3-ultra-550b-a55b": {
+    input: 0.6,
+    output: 2.4,
+    cacheRead: 0.12,
+    cacheWrite: 0,
+  },
+  "sakana/fugu-ultra": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 },
+  "thinkingmachines/inkling": { input: 1, output: 4.05, cacheRead: 0.17, cacheWrite: 0 },
+  "thinkingmachines/inkling-small": {
+    input: 0.5,
+    output: 1.2,
+    cacheRead: 0.1,
+    cacheWrite: 0,
+  },
+  "meta/muse-spark-1.1": { input: 1.25, output: 4.25, cacheRead: 0.15, cacheWrite: 0 },
+
+  // Anthropic
+  // Introductory pricing through 2026-08-31.
+  "claude-sonnet-5": { input: 2, output: 10, cacheRead: 0.2, cacheWrite: 2.5 },
+  "claude-sonnet-4-6": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 3.75 },
+  "claude-fable-5": { input: 10, output: 50, cacheRead: 1, cacheWrite: 12.5 },
+  "claude-opus-5": { input: 5, output: 25, cacheRead: 0.5, cacheWrite: 6.25 },
+  "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,
+  },
+
+  // OpenAI
+  "gpt-5.6-sol": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 6.25 },
+  // Discounted rates through 2026-08-14.
+  "gpt-5.6-terra": {
+    input: 1,
+    output: 6,
+    cacheRead: 0.1,
+    cacheWrite: 1.25,
+    tiers: [
+      {
+        inputTokensAbove: 272_000,
+        input: 2,
+        output: 9,
+        cacheRead: 0.2,
+        cacheWrite: 2.5,
+      },
+    ],
+  },
+  "gpt-5.6-luna": {
+    input: 0.1,
+    output: 0.6,
+    cacheRead: 0.01,
+    cacheWrite: 0.125,
+    tiers: [
+      {
+        inputTokensAbove: 272_000,
+        input: 0.2,
+        output: 0.9,
+        cacheRead: 0.02,
+        cacheWrite: 0.25,
+      },
+    ],
+  },
+  "gpt-5.5": { input: 5, output: 30, cacheRead: 0.5, cacheWrite: 0 },
+  "gpt-5.4": { input: 2.5, output: 15, cacheRead: 0.25, cacheWrite: 0 },
+  "gpt-5.3-codex": { input: 2, output: 8, cacheRead: 0.5, cacheWrite: 0 },
+  "gpt-5.4-mini": { input: 0.75, output: 4.5, cacheRead: 0.075, cacheWrite: 0 },
+
+  // Google and xAI
+  "google/gemini-3.6-flash": { input: 1.5, output: 7.5, cacheRead: 0.15, cacheWrite: 0 },
+  "google/gemini-3.5-flash": { input: 1.5, output: 9, cacheRead: 0.15, cacheWrite: 0 },
+  "google/gemini-3.5-flash-lite": {
+    input: 0.3,
+    output: 2.5,
+    cacheRead: 0.03,
+    cacheWrite: 0,
+  },
+  "google/gemini-3.1-flash-lite": {
+    input: 0.25,
+    output: 1.5,
+    cacheRead: 0.03,
+    cacheWrite: 0,
+  },
+  "xai/grok-4.5": { input: 2, output: 6, cacheRead: 0.5, cacheWrite: 0 },
+}
+
+export const TEMPORARY_PRICING: readonly TemporaryPricing[] = [
+  {
+    models: ["gpt-5.6-terra", "gpt-5.6-luna"],
+    expiresOn: "2026-08-14",
+    description: "50% promotional rates",
+  },
+  {
+    models: ["claude-sonnet-5"],
+    expiresOn: "2026-08-31",
+    description: "introductory pricing",
+  },
+]

package/src/runtime.ts

@@ -0,0 +1,279 @@
+import type { CommandCodeModel, LoadCommandCodeModelsResult } from "./models.ts"
+
+export interface CommandCodeUi {
+  notify(message: string, type?: "info" | "warning" | "error"): void
+}
+
+export interface CommandCodeCommandContext {
+  ui: CommandCodeUi
+  waitForIdle?: () => Promise<void>
+}
+
+export interface CommandCodeRuntimeApi<
+  TProviderConfig,
+  TContext extends CommandCodeCommandContext,
+> {
+  registerProvider(name: string, config: TProviderConfig): void
+  registerCommand(
+    name: string,
+    options: {
+      description: string
+      handler: (args: string, ctx: TContext) => Promise<void>
+    },
+  ): void
+}
+
+export interface CommandCodeRuntimeOptions<TProviderConfig> {
+  endpoint: string
+  cachePath: string
+  loadModels: () => Promise<LoadCommandCodeModelsResult>
+  createProviderConfig: (models: readonly CommandCodeModel[]) => TProviderConfig
+  now?: () => number
+  logWarning?: (message: string) => void
+}
+
+export interface CommandCodeRuntimeStatus {
+  source: LoadCommandCodeModelsResult["source"]
+  modelCount: number
+  lastSuccess?: number
+  lastAttempt?: number
+  cachePath: string
+  endpoint: string
+  warning?: string
+  refreshing: boolean
+}
+
+export interface CommandCodeRefreshResult {
+  refreshed: boolean
+  source: CommandCodeRuntimeStatus["source"]
+  modelCount: number
+  warning?: string
+}
+
+const REDACTED = "[redacted]"
+
+function errorMessage(error: unknown): string {
+  return error instanceof Error ? error.message : String(error)
+}
+
+function redactUrl(value: string): string {
+  try {
+    const url = new URL(value)
+    return `${url.protocol}//${url.host}${url.pathname}`
+  } catch {
+    return REDACTED
+  }
+}
+
+export function redactDiagnosticText(value: string): string {
+  const redactedUrls = value.replace(/https?:\/\/[^\s)]+/gi, (match) => redactUrl(match))
+  return redactedUrls
+    .replace(/\bBearer\s+[A-Za-z0-9._~+/=-]+/gi, `Bearer ${REDACTED}`)
+    .replace(/\b(?:user|cc)_[A-Za-z0-9_-]{8,}\b/gi, REDACTED)
+    .replace(/\b(?:api[-_ ]?key|token|secret|password)\s*[=:]\s*[^\s,;)]+/gi, (match) => {
+      const separator = match.match(/\s*[=:]\s*/)?.[0] ?? "="
+      return `${match.slice(0, match.indexOf(separator))}${separator}${REDACTED}`
+    })
+}
+
+export function redactEndpoint(value: string): string {
+  return redactUrl(value)
+}
+
+function formatTimestamp(timestamp: number | undefined): string {
+  return timestamp === undefined ? "never" : new Date(timestamp).toISOString()
+}
+
+export function formatCommandCodeStatus(status: CommandCodeRuntimeStatus): string {
+  const lines = [
+    `source: ${status.source}`,
+    `model count: ${status.modelCount}`,
+    `last success: ${formatTimestamp(status.lastSuccess)}`,
+    `last attempt: ${formatTimestamp(status.lastAttempt)}`,
+    `cache path: ${status.cachePath}`,
+    `endpoint: ${redactEndpoint(status.endpoint)}`,
+    `refresh: ${status.refreshing ? "in progress" : "idle"}`,
+  ]
+
+  lines.push(`warning: ${status.warning ? redactDiagnosticText(status.warning) : "none"}`)
+  return lines.join("\n")
+}
+
+export class CommandCodeRuntime<TProviderConfig, TContext extends CommandCodeCommandContext> {
+  private readonly now: () => number
+  private readonly logWarning: (message: string) => void
+  private status: CommandCodeRuntimeStatus
+  private providerRegistered = false
+  private refreshPromise: Promise<CommandCodeRefreshResult> | undefined
+
+  constructor(
+    private readonly pi: CommandCodeRuntimeApi<TProviderConfig, TContext>,
+    private readonly options: CommandCodeRuntimeOptions<TProviderConfig>,
+  ) {
+    this.now = options.now ?? Date.now
+    this.logWarning = options.logWarning ?? ((message) => console.warn(`[commandcode] ${message}`))
+    const initialStatus: CommandCodeRuntimeStatus = {
+      source: "empty",
+      modelCount: 0,
+      cachePath: options.cachePath,
+      endpoint: options.endpoint,
+      refreshing: false,
+    }
+    this.status = { ...initialStatus }
+  }
+
+  getStatus(): CommandCodeRuntimeStatus {
+    return { ...this.status }
+  }
+
+  async initialize(): Promise<void> {
+    this.registerCommands()
+    await this.refresh()
+  }
+
+  refresh(): Promise<CommandCodeRefreshResult> {
+    if (this.refreshPromise) return this.refreshPromise
+
+    const refreshPromise = this.refreshCatalog().finally(() => {
+      if (this.refreshPromise === refreshPromise) this.refreshPromise = undefined
+    })
+    this.refreshPromise = refreshPromise
+    return refreshPromise
+  }
+
+  private async refreshCatalog(): Promise<CommandCodeRefreshResult> {
+    this.status = {
+      ...this.status,
+      lastAttempt: this.now(),
+      refreshing: true,
+    }
+
+    try {
+      const loaded = await this.options.loadModels()
+      const warning = loaded.warning ? redactDiagnosticText(loaded.warning) : undefined
+
+      const shouldRegister =
+        !this.providerRegistered ||
+        loaded.source === "live" ||
+        (this.status.modelCount === 0 && loaded.models.length > 0)
+
+      if (shouldRegister) {
+        this.pi.registerProvider("commandcode", this.options.createProviderConfig(loaded.models))
+        this.providerRegistered = true
+
+        if (loaded.models.length === 0) {
+          const preservedWarning = warning ?? "Model catalog refresh returned no models"
+          this.status = {
+            ...this.status,
+            source: loaded.source,
+            modelCount: 0,
+            warning: preservedWarning,
+            refreshing: false,
+          }
+          this.warn(preservedWarning)
+          return {
+            refreshed: false,
+            source: loaded.source,
+            modelCount: 0,
+            warning: preservedWarning,
+          }
+        }
+
+        this.status = {
+          ...this.status,
+          source: loaded.source,
+          modelCount: loaded.models.length,
+          lastSuccess: this.now(),
+          warning,
+          refreshing: false,
+        }
+        if (warning) this.warn(warning)
+        return {
+          refreshed: true,
+          source: loaded.source,
+          modelCount: loaded.models.length,
+          warning,
+        }
+      }
+
+      const preservedWarning = warning ?? "Model catalog refresh returned no models"
+      this.status = {
+        ...this.status,
+        warning: preservedWarning,
+        refreshing: false,
+      }
+      this.warn(preservedWarning)
+      return {
+        refreshed: false,
+        source: this.status.source,
+        modelCount: this.status.modelCount,
+        warning: preservedWarning,
+      }
+    } catch (error) {
+      const warning = redactDiagnosticText(
+        `Could not refresh the Command Code model catalog: ${errorMessage(error)}`,
+      )
+      this.status = {
+        ...this.status,
+        warning,
+        refreshing: false,
+      }
+      this.warn(warning)
+      return {
+        refreshed: false,
+        source: this.status.source,
+        modelCount: this.status.modelCount,
+        warning,
+      }
+    }
+  }
+
+  private warn(message: string): void {
+    try {
+      this.logWarning(redactDiagnosticText(message))
+    } catch {
+      // Diagnostics must never make a catalog refresh fail.
+    }
+  }
+
+  private registerCommands(): void {
+    this.pi.registerCommand("commandcode-refresh", {
+      description: "Refresh the Command Code model catalog",
+      handler: async (_args, ctx) => {
+        await ctx.waitForIdle?.()
+        const result = await this.refresh()
+        if (result.refreshed) {
+          ctx.ui.notify(
+            `Command Code model catalog refreshed (${result.modelCount} models from ${result.source}).`,
+            "info",
+          )
+        } else {
+          ctx.ui.notify(
+            `Command Code model catalog unchanged (${result.modelCount} models remain available).${result.warning ? ` ${result.warning}` : ""}`,
+            "warning",
+          )
+        }
+      },
+    })
+
+    this.pi.registerCommand("commandcode-status", {
+      description: "Show redacted Command Code provider diagnostics",
+      handler: async (_args, ctx) => {
+        ctx.ui.notify(
+          formatCommandCodeStatus(this.status),
+          this.status.warning ? "warning" : "info",
+        )
+      },
+    })
+  }
+}
+
+export function createCommandCodeRuntime<
+  TProviderConfig,
+  TContext extends CommandCodeCommandContext,
+>(
+  pi: CommandCodeRuntimeApi<TProviderConfig, TContext>,
+  options: CommandCodeRuntimeOptions<TProviderConfig>,
+): CommandCodeRuntime<TProviderConfig, TContext> {
+  return new CommandCodeRuntime(pi, options)
+}

package/src/types.ts

@@ -15,6 +15,7 @@ export interface Usage {
   output: number
   cacheRead: number
   cacheWrite: number
+  cacheWrite1h?: number
   totalTokens: number
   cost: UsageCost
 }
@@ -50,19 +51,34 @@ export interface AssistantMessageLike {
   timestamp: number
 }
 
-export interface ModelCost {
+export interface ModelCostRates {
   input: number
   output: number
   cacheRead: number
   cacheWrite: number
 }
 
+export interface ModelCostTier extends ModelCostRates {
+  inputTokensAbove: number
+}
+
+export interface ModelCost extends ModelCostRates {
+  tiers?: readonly ModelCostTier[]
+}
+
 export interface ModelLike {
   id: string
   api: unknown
   provider: string
   maxTokens: number
   cost: ModelCost
+  reasoning?: boolean
+  thinkingLevelMap?: Partial<Record<string, string | null>>
+  thinking?: {
+    mode?: "effort"
+    effortMap?: Partial<Record<string, string>>
+    efforts?: readonly string[]
+  }
 }
 
 export interface MessageLike {
@@ -95,6 +111,8 @@ export interface StreamOptions {
   signal?: AbortSignal
   headers?: Record<string, string>
   maxTokens?: number
+  /** Resolved pi thinking level; forwarded only through the model's map. */
+  reasoning?: string
   onPayload?: (payload: unknown, model: ModelLike) => unknown | Promise<unknown>
   onResponse?: (response: ProviderResponseInfo, model: ModelLike) => void | Promise<void>
   /**