bitfab-cli 0.2.383 → 0.2.384

package/dist/index.js

@@ -23854,7 +23854,7 @@ var labelEvidenceShape = external_exports.preprocess(parseJsonString, external_e
 var saveAgentLabels = {
   name: "save_agent_labels",
   title: "Save Agent Labels",
-  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). Add `evidence` as `{ spanId, text }` entries to ground that reasoning in spans on the evaluated trace. 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 `experimentId` 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. Before judging a replay, call get_trace_assertions on the original trace ids: an assertion says what the user asked this specific case to do, so the verdict is measured against that rather than a guess. When an assertion's target cannot be found on the trace you are judging, the check never ran, so pass `skip: true` for that trace rather than recording a FAIL. Pass `assertionId` to score ONE assertion on the trace (the `[ID: ...]` get_trace_assertions prints), one entry per assertion, all in the same call. Omit it for the trace's single whole-trace verdict. get_trace_labels reads these back one line per assertion, keyed by the same assertionId, so a per-assertion write is verifiable per assertion.",
+  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). Add `evidence` as `{ spanId, text }` entries to ground that reasoning in spans on the evaluated trace. 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. That records an explicit skip so coverage checks know you intentionally did not verdict it, and `annotation` still applies: pass it to say why the verdict was withheld (the check never ran, the tape was punctured, the run never terminated), which is the only place a reader learns that. A skip with no annotation clears the note the previous verdict carried, so a stale reason never sits under a withheld verdict. 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 `experimentId` 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. Before judging a replay, call get_trace_assertions on the original trace ids: an assertion says what the user asked this specific case to do, so the verdict is measured against that rather than a guess. When an assertion's target cannot be found on the trace you are judging, the check never ran, so pass `skip: true` for that trace rather than recording a FAIL. Pass `assertionId` to score ONE assertion on the trace (the `[ID: ...]` get_trace_assertions prints), one entry per assertion, all in the same call. Omit it for the trace's single whole-trace verdict. get_trace_labels reads these back one line per assertion, keyed by the same assertionId, so a per-assertion write is verifiable per assertion.",
   inputSchema: {
     experimentId: external_exports.uuid().optional().describe("The experiment ID. Required when any label targets a trace by originalTraceId (replay verdicts); ignored otherwise."),
     labels: external_exports.preprocess(parseJsonString, external_exports.array(external_exports.object({
@@ -23864,9 +23864,9 @@ var saveAgentLabels = {
       sourceTraceId: external_exports.uuid().optional().meta({ deprecated: true }).describe("Deprecated alias for originalTraceId. Prefer originalTraceId; accepted for back-compat."),
       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."),
       archive: external_exports.boolean().optional().describe("If true, archive the existing agent label for this trace and ignore label/annotation/skip/confidence. Default false."),
-      skip: external_exports.boolean().optional().describe("If true, record an explicit skip (cannot judge) and ignore label/annotation/confidence. Default false."),
+      skip: external_exports.boolean().optional().describe("If true, record an explicit skip (cannot judge) and ignore label/confidence. Pass `annotation` alongside it to record why the verdict was withheld. Default false."),
       label: external_exports.boolean().optional().describe("true for PASS, false for FAIL. Required when archive and skip are both false/omitted."),
-      annotation: external_exports.string().min(1).optional().describe("Your reasoning for the verdict - shown to the human reviewer in the labeling UI. Required when archive and skip are both false/omitted."),
+      annotation: external_exports.string().min(1).optional().describe("Your reasoning, shown to the human reviewer in the labeling UI. Required when archive and skip are both false/omitted. Optional alongside `skip: true`, where it says why the verdict was withheld."),
       confidence: external_exports.enum(["VeryLow", "Low", "Medium", "High", "VeryHigh"]).optional().describe("How confident you are in this verdict: VeryLow / Low / Medium / High / VeryHigh. Surfaced as a chip in the labeling UI; low-confidence labels are prioritized for human review. Optional; only meaningful when paired with a label."),
       evidence: labelEvidenceShape.nullable().optional().describe("Span-by-span evidence for this verdict. Omit it to preserve existing evidence. Pass null to clear existing evidence.")
     })).min(1).max(200)).describe("One entry per assertion on traces that have assertions, otherwise one whole-trace entry (1-200)")
@@ -24917,10 +24917,10 @@ var semver3 = __toESM(require_semver2(), 1);
 
 // ../bitfab-plugin-lib/dist/bakedSdkVersions.js
 var BAKED_SDK_VERSIONS = {
-  typescript: "0.60.0",
-  python: "0.60.0",
-  ruby: "0.60.0",
-  go: "0.60.0"
+  typescript: "0.60.1",
+  python: "0.60.1",
+  ruby: "0.60.1",
+  go: "0.60.1"
 };
 
 // ../bitfab-plugin-lib/dist/installedSdk.js

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bitfab-cli",
-  "version": "0.2.383",
+  "version": "0.2.384",
   "description": "Install and configure the Bitfab plugin in Claude Code, Codex, or Cursor, or the Bitfab skill pack in Amp (Alpha).",
   "type": "module",
   "main": "dist/index.js",