bitfab-cli 0.2.298 → 0.2.300

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.
Files changed (2) hide show
  1. package/dist/index.js +5 -4
  2. package/package.json +1 -1
package/dist/index.js CHANGED
@@ -11548,9 +11548,9 @@ var semver3 = __toESM(require_semver2(), 1);
11548
11548
 
11549
11549
  // ../bitfab-plugin-lib/dist/bakedSdkVersions.js
11550
11550
  var BAKED_SDK_VERSIONS = {
11551
- typescript: "0.41.0",
11552
- python: "0.41.0",
11553
- ruby: "0.41.0",
11551
+ typescript: "0.42.0",
11552
+ python: "0.42.1",
11553
+ ruby: "0.42.0",
11554
11554
  go: "0.41.0"
11555
11555
  };
11556
11556
 
@@ -45952,13 +45952,14 @@ var getSpanField = {
45952
45952
  var saveAgentLabels = {
45953
45953
  name: "save_agent_labels",
45954
45954
  title: "Save Agent Labels",
45955
- description: "Set, skip, or archive the agent's pass/fail verdict on one or more traces (`labelSource=\"agent\"`). Use this AFTER you have read the traces with get_traces and decided yourself whether each one looks like a pass, a fail, or genuinely cannot be judged. To set a verdict, pass `label` (true=PASS, false=FAIL) and `annotation` (your reasoning, shown to the human reviewer in the labeling UI). Optionally pass `confidence` (`VeryLow|Low|Medium|High|VeryHigh`) to record how confident you are - surfaced in the labeling UI so reviewers can prioritize low-confidence verdicts. To explicitly skip a trace you cannot decide on (instead of leaving it unlabeled), pass `skip: true` and omit label/annotation - this records an explicit skip so coverage checks know you intentionally did not verdict it. To clear a previously-set agent verdict (e.g., you changed your mind or labeled the wrong trace), pass `archive: true` and omit label/annotation. New verdicts start unapproved (`approvedAt=null`); once a human approves one, it joins the validated dataset (queryable via `search_traces` with `validated: true`). Archiving is non-destructive - the row is hidden from all reads but kept for audit, and you can immediately re-label the trace from scratch. For replay results, key each label by the replay item's `originalTraceId` (the original trace it was replayed from; `sourceTraceId` is accepted as a deprecated alias) plus the top-level `testRunId` instead of a `traceId`: the server resolves it to the replay trace via lineage, so you never need a server-generated replay trace id. Returns an agent-readable summary with one parseable effective label line per updated trace, keyed by the id you supplied (`originalTraceId` for replay verdicts, otherwise `traceId`), so command callers can verify persistence.",
45955
+ description: "Set, skip, or archive the agent's pass/fail verdict on one or more traces (`labelSource=\"agent\"`). Use this AFTER you have read the traces with get_traces and decided yourself whether each one looks like a pass, a fail, or genuinely cannot be judged. To set a verdict, pass `label` (true=PASS, false=FAIL) and `annotation` (your reasoning, shown to the human reviewer in the labeling UI). Optionally pass `confidence` (`VeryLow|Low|Medium|High|VeryHigh`) to record how confident you are - surfaced in the labeling UI so reviewers can prioritize low-confidence verdicts. To explicitly skip a trace you cannot decide on (instead of leaving it unlabeled), pass `skip: true` and omit label/annotation - this records an explicit skip so coverage checks know you intentionally did not verdict it. To clear a previously-set agent verdict (e.g., you changed your mind or labeled the wrong trace), pass `archive: true` and omit label/annotation. New verdicts start unapproved (`approvedAt=null`); once a human approves one, it joins the validated dataset (queryable via `search_traces` with `validated: true`). Archiving is non-destructive - the row is hidden from all reads but kept for audit, and you can immediately re-label the trace from scratch. For replay results, key each label by the replay item's `originalTraceId` (the original trace it was replayed from; `sourceTraceId` is accepted as a deprecated alias) plus the top-level `testRunId` instead of a `traceId`: the server resolves it to the replay trace via lineage, so you never need a server-generated replay trace id. When the experiment ran each trace more than once, also pass the item's `attempt` so each attempt gets its own verdict. Returns an agent-readable summary with one parseable effective label line per updated trace, keyed by the id you supplied (`originalTraceId` for replay verdicts, otherwise `traceId`), so command callers can verify persistence.",
45956
45956
  inputSchema: {
45957
45957
  testRunId: external_exports.uuid().optional().describe("The replay test run id. Required when any label targets a trace by originalTraceId (replay verdicts); ignored otherwise."),
45958
45958
  labels: external_exports.preprocess(parseJsonString, external_exports.array(external_exports.object({
45959
45959
  traceId: external_exports.uuid().optional().describe("The trace ID to update. Provide this OR originalTraceId, not both."),
45960
45960
  originalTraceId: external_exports.uuid().optional().describe("For replay verdicts: the original trace ID the replay item was replayed from (the replay item's originalTraceId). The server resolves it to the replay trace via lineage, so you never need a server replay trace id. Requires the top-level testRunId. Provide this OR traceId, not both."),
45961
45961
  sourceTraceId: external_exports.uuid().optional().meta({ deprecated: true }).describe("Deprecated alias for originalTraceId. Prefer originalTraceId; accepted for back-compat."),
45962
+ attempt: external_exports.number().int().min(0).optional().describe("For replay verdicts on an experiment that ran each trace more than once: which attempt of originalTraceId this verdict is for (0-based, the replay item's attempt). Defaults to 0, so single-attempt callers never need it."),
45962
45963
  archive: external_exports.boolean().optional().describe("If true, archive the existing agent label for this trace and ignore label/annotation/skip/confidence. Default false."),
45963
45964
  skip: external_exports.boolean().optional().describe("If true, record an explicit skip (cannot judge) and ignore label/annotation/confidence. Default false."),
45964
45965
  label: external_exports.boolean().optional().describe("true for PASS, false for FAIL. Required when archive and skip are both false/omitted."),
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "bitfab-cli",
3
- "version": "0.2.298",
3
+ "version": "0.2.300",
4
4
  "description": "Install and configure the Bitfab plugin in Claude Code, Codex, or Cursor.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",