gangtise-openapi-cli 0.26.0 → 0.28.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -62,6 +62,23 @@ export function collectKeyValue(value, previous = {}) {
62
62
  export function maybeArray(value) {
63
63
  return value.length > 0 ? value : undefined;
64
64
  }
65
+ /** True when `latest` is strictly newer than `current` (numeric per-segment
66
+ * compare). Plain inequality would nag "update available" during the
67
+ * just-published window while the registry still serves the previous version. */
68
+ export function isVersionNewer(latest, current) {
69
+ const parse = (v) => v.split(".").map(Number);
70
+ const a = parse(latest);
71
+ const b = parse(current);
72
+ if (a.some(Number.isNaN) || b.some(Number.isNaN))
73
+ return false;
74
+ for (let i = 0; i < Math.max(a.length, b.length); i++) {
75
+ const x = a[i] ?? 0;
76
+ const y = b[i] ?? 0;
77
+ if (x !== y)
78
+ return x > y;
79
+ }
80
+ return false;
81
+ }
65
82
  // Whitelist for enum-valued repeatable options. Only used where the server was
66
83
  // probed NOT to reject bad values (it silently ignores the filter or returns
67
84
  // empty instead) — endpoints that answer 100003 keep server-side validation.
@@ -73,38 +90,154 @@ export function parseChoiceList(values, optionName, allowed) {
73
90
  }
74
91
  return maybeArray(values);
75
92
  }
93
+ const YYYY_MM_DD = /^\d{4}-\d{2}-\d{2}$/;
94
+ /**
95
+ * Strict `YYYY-MM-DD` guard for Quote/Fundamental date options.
96
+ *
97
+ * Beyond the documented shape the server accepts two extra year-last formats
98
+ * whose day/month order is *opposite* to each other (probed 2026-07-20 on
99
+ * quote/kline/daily and fundamental/balance-sheet; other groups sharing these
100
+ * flags were not probed, so the guard is applied uniformly as the safe default):
101
+ *
102
+ * "07/01/2026" -> 2026-01-07 slash reads DD/MM/YYYY
103
+ * "07-01-2026" -> 2026-07-01 hyphen reads MM-DD-YYYY
104
+ *
105
+ * Same three digits, six months apart, both HTTP 200, and nothing in the
106
+ * response echoes which date the server actually used. Confirmed by the
107
+ * complement: "25/12/2026" parses while "12/25/2026" errors, and the hyphen
108
+ * forms behave exactly the other way round. Since the CLI cannot know which
109
+ * reading was meant, it forwards only the unambiguous form.
110
+ *
111
+ * Other unambiguous shapes (`20260701`, `2026/07/01`) are rejected too, even
112
+ * though the server handles them — one accepted form beats a per-shape allowlist
113
+ * that has to be re-probed per endpoint group. The message says which form is
114
+ * wanted rather than claiming the input itself was ambiguous.
115
+ *
116
+ * Datetime options (`--start-time`) are guarded separately: pass-through ones by
117
+ * `parseDatetimeOption` (a timezone-free field check that returns the string as-is),
118
+ * and the two conversion endpoints (A-share announcement / knowledge-batch) by
119
+ * `parseTimestamp13`.
120
+ */
121
+ export function parseDateOption(value, optionName) {
122
+ if (!YYYY_MM_DD.test(value)) {
123
+ throw new ValidationError(`Invalid ${optionName}: expected YYYY-MM-DD, got "${value}" — only that form is forwarded; some endpoints silently misread other layouts (e.g. "07/01/2026") as a different day`);
124
+ }
125
+ // Shape alone lets 2026-02-30 / 2026-13-01 through; round-trip to reject those.
126
+ // Built from the ISO string, not Date.UTC(y,...), whose two-digit-year mapping
127
+ // would turn a valid year 0050 into 1950 and report it as a non-existent date.
128
+ const [year, month, day] = value.split("-").map(Number);
129
+ const parsed = new Date(`${value}T00:00:00Z`);
130
+ if (parsed.getUTCFullYear() !== year || parsed.getUTCMonth() !== month - 1 || parsed.getUTCDate() !== day) {
131
+ throw new ValidationError(`Invalid ${optionName}: "${value}" is not a real calendar date`);
132
+ }
133
+ return value;
134
+ }
135
+ /** Commander argParser factory — `.option("--start-date <date>", desc, dateArg("--start-date"))`. */
136
+ export function dateArg(optionName) {
137
+ return (value) => parseDateOption(value, optionName);
138
+ }
139
+ /** `yyyy-MM-dd` with an optional ` HH:mm[:ss]` / `THH:mm[:ss]` tail. Anything else
140
+ * is rejected rather than handed to `new Date()`: V8's fallback parser accepts the
141
+ * same year-last shapes the server does but reads them the OTHER way round —
142
+ * `07/01/2026` is July 1 to V8 and January 7 to the server, `25/12/2026` is invalid
143
+ * to V8 and valid to the server (both probed 2026-07-20). Since `announcement list`
144
+ * converts locally while its HK/US siblings pass the string through, an open
145
+ * fallback made the same flag mean two dates six months apart across sibling
146
+ * commands, silently and with exit 0. */
147
+ const LOCAL_DATETIME = /^(\d{4})-(\d{2})-(\d{2})(?:[ T](\d{2}):(\d{2})(?::(\d{2}))?)?$/;
148
+ /** Field-level datetime validation, timezone-free — a real calendar day plus a
149
+ * valid clock time, judged by arithmetic alone (no Date construction, so no
150
+ * dependence on the client's timezone or DST). This is what the pass-through guard
151
+ * needs: a string the CLI forwards verbatim must be judged on its fields, not on
152
+ * whether the local zone happens to contain that wall-clock instant. */
153
+ function datetimeFieldsValid(value) {
154
+ const parts = LOCAL_DATETIME.exec(value);
155
+ if (!parts)
156
+ return false;
157
+ const [, y, mo, d, hh = "0", mi = "0", ss = "0"] = parts;
158
+ const year = Number(y), month = Number(mo), day = Number(d);
159
+ if (month < 1 || month > 12)
160
+ return false;
161
+ const leap = (year % 4 === 0 && year % 100 !== 0) || year % 400 === 0;
162
+ const dim = [31, leap ? 29 : 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31][month - 1];
163
+ if (day < 1 || day > dim)
164
+ return false;
165
+ return Number(hh) <= 23 && Number(mi) <= 59 && Number(ss) <= 59;
166
+ }
167
+ /** A 10-digit seconds or 13-digit millis epoch, normalized to millis. Judged by
168
+ * digit count, NOT magnitude: a `> 1e12` test sends a real 13-digit `1000000000000`
169
+ * (which equals 1e12) down the seconds branch, and lets Number() coerce scientific
170
+ * / hex / whitespace-padded / 11–12–14-digit inputs through as a "timestamp" — all
171
+ * of which then convert wrong or get rejected by the server. Exactly 10 or 13
172
+ * digits, nothing else. */
173
+ function epochMillis(value) {
174
+ if (/^\d{13}$/.test(value))
175
+ return Number(value);
176
+ if (/^\d{10}$/.test(value))
177
+ return Number(value) * 1000;
178
+ return undefined;
179
+ }
76
180
  export function toTimestamp13(value) {
77
181
  if (value === undefined)
78
182
  return undefined;
79
- const num = Number(value);
80
- if (!Number.isNaN(num) && num > 1e12)
81
- return num;
82
- if (!Number.isNaN(num) && num > 1e9)
83
- return num * 1000;
84
- // `new Date("yyyy-MM-dd")` parses as UTC midnight while `new Date("yyyy-MM-dd HH:mm:ss")`
85
- // parses as local time — for CST users the two forms would differ by 8 hours and
86
- // silently shift the query window. Anchor date-only input to local midnight so both
87
- // forms mean the same wall-clock day.
88
- const dateOnly = /^(\d{4})-(\d{2})-(\d{2})$/.exec(value);
89
- if (dateOnly) {
90
- const d = new Date(Number(dateOnly[1]), Number(dateOnly[2]) - 1, Number(dateOnly[3]));
91
- const valid = d.getMonth() === Number(dateOnly[2]) - 1 && d.getDate() === Number(dateOnly[3]);
92
- return valid ? d.getTime() : undefined;
93
- }
94
- const ms = new Date(value).getTime();
95
- if (Number.isNaN(ms))
183
+ const ts = epochMillis(value);
184
+ if (ts !== undefined)
185
+ return ts;
186
+ if (!datetimeFieldsValid(value))
96
187
  return undefined;
97
- return ms;
188
+ // `new Date("yyyy-MM-dd")` parses as UTC midnight while `new Date("yyyy-MM-dd
189
+ // HH:mm:ss")` parses as local time — for CST users the two forms would differ by 8
190
+ // hours. Build from local components so both mean the same wall-clock day.
191
+ const parts = LOCAL_DATETIME.exec(value);
192
+ const [, y, mo, d, hh = "0", mi = "0", ss = "0"] = parts;
193
+ const year = Number(y);
194
+ const dt = new Date(year, Number(mo) - 1, Number(d), Number(hh), Number(mi), Number(ss));
195
+ // Full round-trip on every field: rejects the two inputs that cannot convert
196
+ // faithfully — the two-digit-year remap (new Date(50,…) → 1950) and a DST gap (a
197
+ // wall-clock time the local zone skips: 02:30 on a US spring-forward morning, or
198
+ // 02:15 in Lord Howe's 30-minute gap, which only a minute-level check catches).
199
+ const faithful = dt.getFullYear() === year && dt.getMonth() === Number(mo) - 1
200
+ && dt.getDate() === Number(d) && dt.getHours() === Number(hh)
201
+ && dt.getMinutes() === Number(mi) && dt.getSeconds() === Number(ss);
202
+ return faithful ? dt.getTime() : undefined;
98
203
  }
99
204
  export function parseTimestamp13(value, optionName) {
100
205
  if (value === undefined)
101
206
  return undefined;
102
207
  const parsed = toTimestamp13(value);
103
208
  if (parsed === undefined) {
104
- throw new ValidationError(`Invalid ${optionName}: expected a Unix timestamp or date string`);
209
+ throw new ValidationError(`Invalid ${optionName}: expected a Unix timestamp or "YYYY-MM-DD" optionally with " HH:mm[:ss]" (space or T separator), got "${value}" — year-last forms are refused because Node and the API read their day/month order the opposite way round`);
105
210
  }
106
211
  return parsed;
107
212
  }
213
+ /**
214
+ * Guard for datetime options forwarded to the server AS A STRING (never converted
215
+ * to a timestamp): the pass-through Insight/Vault list endpoints echo the string
216
+ * verbatim, and probing 2026-07-21 showed they misread year-last separators exactly
217
+ * like the date endpoints — `insight research list` read `07/01/2026` as 2026-01-07
218
+ * but `07-01-2026` as 2026-07-01, a half-year apart, both HTTP 200 with nothing in
219
+ * the response flagging it. Accept a finite epoch or a well-formed `YYYY-MM-DD
220
+ * [ HH:mm[:ss]]` and return the ORIGINAL string unchanged.
221
+ *
222
+ * Validated with `datetimeFieldsValid`, NOT `toTimestamp13`: the latter's local Date
223
+ * round-trip would reject a DST-gap string (e.g. `2026-03-08 02:30:00` under
224
+ * America/New_York) that the server accepts — the CLI forwards this string as-is and
225
+ * the server resolves it in its own zone, so the client's timezone must not decide
226
+ * validity. Distinct from `parseTimestamp13`, which DOES convert (A-share
227
+ * announcement / knowledge-batch want epoch millis, where an unrepresentable local
228
+ * instant genuinely cannot convert).
229
+ */
230
+ export function parseDatetimeOption(value, optionName) {
231
+ if (epochMillis(value) === undefined && !datetimeFieldsValid(value)) {
232
+ throw new ValidationError(`Invalid ${optionName}: expected a Unix timestamp or "YYYY-MM-DD" optionally with " HH:mm[:ss]" (space or T separator), got "${value}" — year-last forms are refused because the API reads their day/month order differently per separator`);
233
+ }
234
+ return value;
235
+ }
236
+ /** Commander argParser factory for pass-through datetime options — same role as
237
+ * `dateArg`, but allows an optional time part and keeps the string as-is. */
238
+ export function datetimeArg(optionName) {
239
+ return (value) => parseDatetimeOption(value, optionName);
240
+ }
108
241
  /** Machine-local calendar date as `yyyy-MM-dd`, for CLI "default: today" options.
109
242
  * `new Date().toISOString().slice(0,10)` renders the UTC day — for CST users a
110
243
  * pre-08:00 "today" resolves to yesterday. Anchoring to local components matches
@@ -1,5 +1,6 @@
1
1
  import { ApiError } from "./errors.js";
2
2
  import { printData } from "./printer.js";
3
+ import { isTransientError } from "./transport.js";
3
4
  // 14 attempts with exponential backoff (5s→30s cap) ≈ 316s total wait budget.
4
5
  export const POLL_MAX_ATTEMPTS = 14;
5
6
  const POLL_INITIAL_DELAY_MS = 5_000;
@@ -9,8 +10,35 @@ function nextDelayMs(attempt) {
9
10
  const grown = POLL_INITIAL_DELAY_MS * 1.6 ** (attempt - 1);
10
11
  return Math.min(POLL_MAX_DELAY_MS, Math.round(grown));
11
12
  }
13
+ // Probed 2026-07-20 against a real viewpoint-debate job: the async endpoints are
14
+ // still entirely on the legacy codes — 410110 "正在生成中" and 410111 "生成失败",
15
+ // both string-typed, both HTTP 400, neither carrying the new `errorType` field.
16
+ // The 2026-07-17 spec renumbers them to 140001 RESULT_GENERATING (409) and
17
+ // 140002 PROCESSING_FAILED (500); those are listed ahead of the switchover
18
+ // because the failure mode is expensive and silent — a `--wait` that does not
19
+ // recognize the pending code aborts the poll on a job already billed 50 credits.
20
+ const PENDING_CODES = new Set(["410110", "140001"]);
21
+ const FAILED_CODES = new Set(["410111", "140002"]);
12
22
  function isAsyncPending(error) {
13
- return error instanceof ApiError && error.code === "410110";
23
+ return error instanceof ApiError && error.code !== undefined && PENDING_CODES.has(error.code);
24
+ }
25
+ function isAsyncFailed(error) {
26
+ return error instanceof ApiError && error.code !== undefined && FAILED_CODES.has(error.code);
27
+ }
28
+ /** Terminal failures are swallowed here rather than rethrown, so this line is the
29
+ * user's only record of them — it has to carry what the global handler in cli.ts
30
+ * would have printed (code, msg, traceId). Without the traceId the failure is
31
+ * unreportable to Gangtise support, and README promises every error line has one. */
32
+ function terminalFailureLine(error) {
33
+ const api = error instanceof ApiError ? error : undefined;
34
+ const code = api?.code ? ` ${api.code}` : "";
35
+ const trace = api?.traceId ? ` [trace ${api.traceId}]` : "";
36
+ const detail = api?.message ? `: ${api.message}` : "";
37
+ // Name the *submit* endpoint explicitly: re-running a `*-check` is a free
38
+ // lookup, it is resubmitting the generation job that re-bills 50 credits for a
39
+ // verdict that will not change (probed 2026-07-20 on sensitive content).
40
+ return `Content generation failed (terminal${code})${trace}${detail}\n`
41
+ + "This dataId is final — re-checking it will not change. Resubmitting the generation task bills again for the same result; change the parameters first.\n";
14
42
  }
15
43
  export async function pollAsyncContent(client, getContentEndpoint, dataId, format, output) {
16
44
  for (let attempt = 1; attempt <= POLL_MAX_ATTEMPTS; attempt++) {
@@ -22,12 +50,20 @@ export async function pollAsyncContent(client, getContentEndpoint, dataId, forma
22
50
  }
23
51
  }
24
52
  catch (error) {
25
- if (error instanceof ApiError && error.code === "410111") {
26
- process.stderr.write("Content generation failed (terminal). Do not retry.\n");
53
+ if (isAsyncFailed(error)) {
54
+ process.stderr.write(terminalFailureLine(error));
27
55
  return "failed";
28
56
  }
29
- if (!isAsyncPending(error))
30
- throw error;
57
+ if (!isAsyncPending(error)) {
58
+ // AI generation windows are exactly when the server is busiest: one 5xx
59
+ // (after the client's own retries) must not void minutes of waiting —
60
+ // the dataId is still valid. Transient errors consume this attempt and
61
+ // polling continues; anything else (no credits, bad params) aborts.
62
+ if (!isTransientError(error))
63
+ throw error;
64
+ const msg = error instanceof Error ? error.message : String(error);
65
+ process.stderr.write(`Attempt ${attempt}/${POLL_MAX_ATTEMPTS}: transient error (${msg.slice(0, 80)}), continuing to wait...\n`);
66
+ }
31
67
  }
32
68
  if (attempt < POLL_MAX_ATTEMPTS) {
33
69
  const delay = nextDelayMs(attempt);
@@ -46,8 +82,8 @@ export async function checkAsyncContent(client, getContentEndpoint, dataId, form
46
82
  }
47
83
  }
48
84
  catch (error) {
49
- if (error instanceof ApiError && error.code === "410111") {
50
- process.stderr.write("Content generation failed (terminal). Do not retry.\n");
85
+ if (isAsyncFailed(error)) {
86
+ process.stderr.write(terminalFailureLine(error));
51
87
  process.exitCode = 1;
52
88
  return;
53
89
  }
@@ -4,14 +4,20 @@ import path from "node:path";
4
4
  import { pipeline } from "node:stream/promises";
5
5
  import { request } from "undici";
6
6
  import { isTokenCacheValid, normalizeToken, readTokenCache, requireAccessCredentials, writeTokenCache } from "./auth.js";
7
- import { ApiError, ValidationError } from "./errors.js";
7
+ import { ApiError, attachEnvelopeTraceId, ValidationError } from "./errors.js";
8
8
  import { ENDPOINTS, resolveTimeoutMs } from "./endpoints.js";
9
9
  import { getLookupData } from "./lookupData/index.js";
10
10
  import { decodeResponseBody, getDispatcher, isVerbose, logTiming, markRetryable, PAGE_CONCURRENCY, parseRetryAfterMs, runWithConcurrency, withRetry } from "./transport.js";
11
- // Auth errors that warrant a forced re-login + one replay. 8000014/8000015 are
12
- // AK/SK errors; 0000001008 is a server-side token invalidation (the token still
13
- // looks valid by local expiry, so only a forced refresh recovers it).
14
- const AUTH_RETRY_CODES = new Set(["8000014", "8000015", "0000001008"]);
11
+ // Auth errors that warrant a forced re-login + one replay: the token was rejected
12
+ // server-side while still looking valid by local expiry, so only a forced refresh
13
+ // recovers it. 0000001008 is the legacy code (probed 2026-07-20: still what the
14
+ // token filter emits); 999002 TOKEN_INVALID is its 2026-07-17 replacement, listed
15
+ // ahead of the rollout so self-heal does not silently die when the filter switches.
16
+ // 8000014/8000015 are the retired AK/SK codes, kept for older server builds.
17
+ // 999011 CREDENTIAL_INVALID is not here and could not act if it were — it comes from
18
+ // auth.login, which runs useAuth=false and so never reaches this check. Its "never
19
+ // replay" guarantee lives in transport's TERMINAL_API_CODES instead.
20
+ const AUTH_RETRY_CODES = new Set(["8000014", "8000015", "0000001008", "999002"]);
15
21
  export class GangtiseClient {
16
22
  config;
17
23
  refreshPromise = null;
@@ -126,17 +132,20 @@ export class GangtiseClient {
126
132
  }
127
133
  throw new ApiError(`API request failed (HTTP ${statusCode})`, undefined, statusCode, parsed, retryAfterMs);
128
134
  }
129
- unwrapEnvelope(parsed, statusCode) {
135
+ unwrapEnvelope(parsed, statusCode, retryAfterMs) {
130
136
  if (!this.isEnvelope(parsed)) {
131
137
  return parsed;
132
138
  }
133
139
  const code = parsed.code === undefined ? undefined : String(parsed.code);
134
140
  const ok = parsed.status === true || parsed.success === true || code === "000000" || code === "0";
135
141
  if (!ok) {
136
- throw new ApiError(parsed.msg || "API request failed", code, statusCode, parsed);
142
+ throw new ApiError(parsed.msg || "API request failed", code, statusCode, parsed, retryAfterMs);
137
143
  }
138
144
  if ('data' in parsed) {
139
- return parsed.data;
145
+ // Carry the envelope's traceId onto the payload: the EDE endpoints wrap a
146
+ // second envelope inside `data` and raise their own failures from it, by
147
+ // which point this is the only traceId in reach.
148
+ return attachEnvelopeTraceId(parsed.data, parsed.traceId);
140
149
  }
141
150
  return parsed;
142
151
  }
@@ -175,8 +184,14 @@ export class GangtiseClient {
175
184
  from: startFrom,
176
185
  size: firstPageSize,
177
186
  });
178
- if (!this.isPaginatedListResponse(firstPage))
187
+ if (!this.isPaginatedListResponse(firstPage)) {
188
+ // Shape drift (e.g. total arriving as a string) silently degrades fetch-all
189
+ // to a single page with no partial marker — make it visible on verbose.
190
+ if (isVerbose()) {
191
+ process.stderr.write(`[gangtise] warning: ${endpoint.key} is marked paginated but the first page has an unexpected shape (no numeric total + list); returning it as-is\n`);
192
+ }
179
193
  return firstPage;
194
+ }
180
195
  const total = firstPage.total;
181
196
  const collected = [...firstPage.list];
182
197
  const available = Math.max(total - startFrom, 0);
@@ -391,20 +406,28 @@ export class GangtiseClient {
391
406
  if (response.statusCode >= 400) {
392
407
  this.throwHttpError(parsed, response.statusCode, retryAfterMs);
393
408
  }
394
- return this.unwrapEnvelope(parsed, response.statusCode);
409
+ return this.unwrapEnvelope(parsed, response.statusCode, retryAfterMs);
395
410
  }
396
411
  catch (error) {
397
412
  await this.refreshAuthIfRecoverable(error, useAuth, authState, usedAuthorization);
398
413
  throw error;
399
414
  }
400
415
  }, {
401
- policy: endpoint.retry === "no-replay" ? "no-replay" : "default",
416
+ policy: endpoint.retry ?? "default",
402
417
  onRetry: (attempt, error, delay) => {
403
418
  if (!isVerbose())
404
419
  return;
405
420
  const msg = error instanceof Error ? error.message : String(error);
406
421
  process.stderr.write(`[gangtise] retry ${attempt} after ${delay.toFixed(0)}ms: ${msg.slice(0, 120)}\n`);
407
422
  },
423
+ }).catch((error) => {
424
+ // EDE uses 999999 for "no data for this query" (probed 2026-07-11) — the
425
+ // generic "系统错误,请稍后重试" hint would send the user retrying a query
426
+ // that will never have data. Swap in a context-specific hint.
427
+ if (endpoint.retry === 'no-999999' && error instanceof ApiError && error.code === '999999') {
428
+ throw new ApiError(error.message, error.code, error.statusCode, error.details, error.retryAfterMs, 'EDE 的 999999 多为查询无数据(节假日 / 未来日期 / 未覆盖标的)——先检查查询条件,确认应有数据再重试。');
429
+ }
430
+ throw error;
408
431
  });
409
432
  }
410
433
  async download(endpoint, query, options) {
@@ -477,7 +500,7 @@ export class GangtiseClient {
477
500
  if (response.statusCode >= 400) {
478
501
  this.throwHttpError(parsed, response.statusCode, retryAfterMs);
479
502
  }
480
- data = this.unwrapEnvelope(parsed, response.statusCode);
503
+ data = this.unwrapEnvelope(parsed, response.statusCode, retryAfterMs);
481
504
  }
482
505
  catch (error) {
483
506
  await this.refreshAuthIfRecoverable(error, true, authState, authorization);
@@ -544,6 +567,9 @@ export class GangtiseClient {
544
567
  filename,
545
568
  };
546
569
  }, {
570
+ // Download endpoints carry per-篇 billing too (summary/foreign-report/
571
+ // my-conference at 50/篇) — honor the endpoint's retry policy here as well.
572
+ policy: endpoint.retry ?? "default",
547
573
  onRetry: (attempt, error, delay) => {
548
574
  if (!isVerbose())
549
575
  return;
@@ -18,10 +18,12 @@ function truncateFilename(name, maxBytes = 200) {
18
18
  if (Buffer.byteLength(name, "utf8") <= maxBytes)
19
19
  return name;
20
20
  const ext = extname(name);
21
- let stem = name.slice(0, name.length - ext.length);
22
- while (stem.length > 1 && Buffer.byteLength(stem + ext, "utf8") > maxBytes)
23
- stem = stem.slice(0, -1);
24
- return stem + ext;
21
+ // Trim by code point, not UTF-16 unit: a cut inside a surrogate pair would put
22
+ // a lone surrogate in the name, which reaches the filesystem as U+FFFD (�).
23
+ const stem = [...name.slice(0, name.length - ext.length)];
24
+ while (stem.length > 1 && Buffer.byteLength(stem.join("") + ext, "utf8") > maxBytes)
25
+ stem.pop();
26
+ return stem.join("") + ext;
25
27
  }
26
28
  /** Pick a non-existing path by suffixing -1, -2, … before the extension, so batch
27
29
  * downloads whose titles collide ("2025年第一季度报告" from several companies) don't
@@ -137,6 +139,11 @@ async function downloadUrlTo(url, outputPath) {
137
139
  method: "GET",
138
140
  headersTimeout: timeoutMs,
139
141
  bodyTimeout: timeoutMs,
142
+ // headers/body timeouts are IDLE timeouts — a stream trickling one byte
143
+ // per interval resets them forever. A generous total deadline (10× the
144
+ // per-request timeout) bounds the whole transfer without killing large
145
+ // legitimate downloads.
146
+ signal: AbortSignal.timeout(timeoutMs * 10),
140
147
  dispatcher: getDispatcher(),
141
148
  };
142
149
  let currentUrl = url;
@@ -171,7 +178,14 @@ async function downloadUrlTo(url, outputPath) {
171
178
  }
172
179
  logTiming(`GET ${redactUrl(currentUrl)}`, Date.now() - startedAt, String(response.statusCode));
173
180
  });
174
- await fs.rename(partPath, outputPath);
181
+ try {
182
+ await fs.rename(partPath, outputPath);
183
+ }
184
+ catch (error) {
185
+ // e.g. outputPath turned out to be a directory — don't leave the .part behind.
186
+ await fs.unlink(partPath).catch(() => { });
187
+ throw error;
188
+ }
175
189
  }
176
190
  export async function saveDownloadResult(result, fallbackName, output) {
177
191
  if (!(result && typeof result === "object")) {
@@ -46,6 +46,8 @@ const ENDPOINT_DEFS = {
46
46
  path: "/application/open-insight/summary/v2/download/file",
47
47
  kind: "download",
48
48
  description: "Download summary file",
49
+ // 50/篇 — same price tier as the AI Agent calls; billing probed non-idempotent.
50
+ retry: "no-replay",
49
51
  },
50
52
  "insight.roadshow.list": {
51
53
  method: "POST",
@@ -100,6 +102,7 @@ const ENDPOINT_DEFS = {
100
102
  path: "/application/open-insight/foreign-report/download/file",
101
103
  kind: "download",
102
104
  description: "Download foreign report",
105
+ retry: "no-replay",
103
106
  },
104
107
  "insight.announcement.list": {
105
108
  method: "POST",
@@ -538,6 +541,7 @@ const ENDPOINT_DEFS = {
538
541
  path: "/application/open-vault/my-conference/download/file",
539
542
  kind: "download",
540
543
  description: "Download my conference resource",
544
+ retry: "no-replay",
541
545
  },
542
546
  "vault.wechat-message.list": {
543
547
  method: "POST",
@@ -599,18 +603,21 @@ const ENDPOINT_DEFS = {
599
603
  path: "/application/open-indicator/EDE/search",
600
604
  kind: "json",
601
605
  description: "Search data indicators by keyword (returns indicatorCode + params)",
606
+ retry: "no-999999",
602
607
  },
603
608
  "indicator.cross-section": {
604
609
  method: "POST",
605
610
  path: "/application/open-indicator/EDE/cross-section",
606
611
  kind: "json",
607
612
  description: "Get cross-section data (multi-indicator x multi-security, single date)",
613
+ retry: "no-999999",
608
614
  },
609
615
  "indicator.time-series": {
610
616
  method: "POST",
611
617
  path: "/application/open-indicator/EDE/time-series",
612
618
  kind: "json",
613
619
  description: "Get time-series data (multi-indicator x single-security OR single-indicator x multi-security)",
620
+ retry: "no-999999",
614
621
  },
615
622
  };
616
623
  export const ENDPOINTS = Object.fromEntries(Object.entries(ENDPOINT_DEFS).map(([key, def]) => [key, { key, ...def }]));