cat-shark
5947e133de
Replace the previous implementation with one that registers the Provider API catalog through pi's own provider layer instead of shipping a custom transport, cache file, and hand-maintained pricing table. - models: derive the catalog from the published command-code CLI package (context windows, reasoning efforts, image input, output limits, rates) and keep it as the offline baseline; scripts/sync-catalog.mjs regenerates it and supports --check - refresh: use refreshModels plus context.publish so pi persists the live /provider/v1/models listing in models-store.json and restores it offline - auth: /login browser transfer through a localhost callback server with a pasted-key fallback; $COMMAND_CODE_API_KEY, --api-key and auth.json keep working - streaming: pi's native openai-completions and anthropic-messages adapters; the generate-transport fallback and Oh My Pi branches are gone - keep the context-overflow rewrite that enables pi's compaction retry and the /commandcode-quota command - tests: 51 cases under tests/<module>/ covering models, catalog sync, auth, the callback server, overflow handling, quota, and the extension factory Verified against the live API: chat, tool round trip, image input and --thinking max on deepseek/deepseek-v4.1-flash, quota output, and catalog persistence in an interactive session.
70 lines
2.5 KiB
TypeScript
70 lines
2.5 KiB
TypeScript
import assert from "node:assert/strict"
|
|
import { test } from "node:test"
|
|
|
|
import {
|
|
normalizeCommandCodeErrorMessage,
|
|
normalizeCommandCodeMessage,
|
|
redactCommandCodeErrorText,
|
|
} from "../../src/overflow.ts"
|
|
|
|
test("provider overflow wording is rewritten to pi's generic prefix", () => {
|
|
const cases = [
|
|
"This model's maximum context length is 1000000 tokens, however you requested 1200000 tokens",
|
|
"prompt is too long: 210000 tokens > 200000 maximum",
|
|
"Input tokens exceed the context window",
|
|
"Request exceeds the maximum allowed input tokens",
|
|
]
|
|
|
|
for (const message of cases) {
|
|
assert.match(normalizeCommandCodeErrorMessage(message) ?? "", /^context_length_exceeded: /, message)
|
|
}
|
|
})
|
|
|
|
test("retryable and quota errors are never treated as overflow", () => {
|
|
const cases = [
|
|
"rate limit exceeded, please retry",
|
|
"429 Too Many Requests",
|
|
"status: 429",
|
|
"Service temporarily unavailable",
|
|
"quota exceeded for this billing period",
|
|
]
|
|
|
|
for (const message of cases) {
|
|
assert.equal(normalizeCommandCodeErrorMessage(message), undefined, message)
|
|
}
|
|
})
|
|
|
|
test("already-normalized and unrelated errors are left alone", () => {
|
|
assert.equal(normalizeCommandCodeErrorMessage("context_length_exceeded: prompt too long"), undefined)
|
|
assert.equal(normalizeCommandCodeErrorMessage("invalid api key"), undefined)
|
|
assert.equal(normalizeCommandCodeErrorMessage(undefined), undefined)
|
|
})
|
|
|
|
test("message rewriting only applies to Command Code assistant errors", () => {
|
|
const message = {
|
|
role: "assistant",
|
|
provider: "commandcode",
|
|
stopReason: "error",
|
|
errorMessage: "prompt is too long",
|
|
}
|
|
|
|
assert.deepEqual(normalizeCommandCodeMessage(message), {
|
|
message: { ...message, errorMessage: "context_length_exceeded: prompt is too long" },
|
|
})
|
|
assert.equal(normalizeCommandCodeMessage({ ...message, stopReason: "stop" }), undefined)
|
|
assert.equal(normalizeCommandCodeMessage({ ...message, role: "user" }), undefined)
|
|
assert.equal(normalizeCommandCodeMessage({ ...message, provider: "anthropic" }), undefined)
|
|
// pi asks the model's provider when the message provider differs.
|
|
assert.ok(normalizeCommandCodeMessage({ ...message, provider: "other" }, "commandcode"))
|
|
})
|
|
|
|
test("error text never leaks API keys", () => {
|
|
const redacted = redactCommandCodeErrorText(
|
|
"failed with Authorization: Bearer user_abcdefgh12345678 and apiKey=user_secret_value",
|
|
)
|
|
|
|
assert.ok(!redacted.includes("user_abcdefgh12345678"))
|
|
assert.ok(!redacted.includes("user_secret_value"))
|
|
assert.match(redacted, /Bearer \[redacted\]/)
|
|
})
|