bitfab-cli 0.2.379 → 0.2.380

package/dist/index.js

@@ -23942,10 +23942,11 @@ var deleteAssertionCategory = {
 var generateTraceAssertions = {
   name: "generate_trace_assertions",
   title: "Generate Trace Assertions",
-  description: "Generate review-ready assertion drafts from what one original trace actually did. Call this when the user asks Bitfab to generate assertions, infer expected behavior from a trace, or turn a known root cause into regression checks. Bitfab reads the organization's existing assertion categories, selects the categories supported by trace evidence, and generates assertions one category at a time. The generated assertions are saved awaiting human review, so they are not checked on replays until a person approves them. The call is idempotent by default and returns the assertions from the existing generation run instead of spending model calls again. Set regenerate to true to archive the prior generated drafts and replace them. Human-authored assertions are never replaced. Pass rootCause when the user knows why the trace was wrong; it narrows the evidence and produces smaller assertions. A replay trace id is refused because assertions belong to the original trace.",
+  description: "Generate review-ready assertion drafts from what one original trace actually did. Call this when the user asks Bitfab to generate assertions, infer expected behavior from a trace, or turn a known root cause into regression checks. Bitfab reads the organization's existing assertion categories, selects the categories supported by trace evidence, and generates assertions one category at a time. The generated assertions are saved awaiting human review, so they are not checked on replays until a person approves them. Generation runs on Bitfab and this call waits up to four minutes for it. If it is still running after that, the result says so, and calling again with the same traceId and without regenerate checks on it. A trace has one generation at a time, so a repeat call joins the running or finished generation instead of spending model calls again, and regenerate while one is running joins that one too. Set regenerate to true after it finishes to archive the prior generated drafts and replace them. A failed generation is returned as an error with its reason. Human-authored assertions are never replaced. Pass guidance when the user knows what the assertions should be about, most often a root cause analysis of why the trace was wrong; it narrows the evidence and produces smaller assertions. Pass categoryIds to limit generation to those assertion categories. A replay trace id is refused because assertions belong to the original trace.",
   inputSchema: {
     traceId: external_exports.uuid().describe("The ORIGINAL trace to generate assertions for. A replay trace id is refused, and the error names the original to retry with."),
-    rootCause: external_exports.string().trim().min(1).max(1e4).optional().describe("Optional known cause of the bad behavior. Use it to focus generation on the smallest assertions that would catch this failure."),
+    guidance: external_exports.string().trim().min(1).max(1e4).optional().describe("Optional assertion guidance, such as a root cause analysis of why the trace went wrong. Use it to focus generation on the smallest assertions that would catch this failure."),
+    categoryIds: external_exports.preprocess(parseJsonString, external_exports.array(external_exports.uuid()).min(1)).optional().describe("Optional assertion category ids from list_assertion_categories. Limits generation to these categories. Omit to let Bitfab choose from every category in the organization. An id outside the organization fails the call before any work starts."),
     regenerate: external_exports.preprocess(parseJsonString, external_exports.boolean()).optional().describe("Set true to rerun generation and replace prior generated drafts. Omit or set false to reuse the existing generation result.")
   }
 };
@@ -23973,7 +23974,7 @@ var saveTraceAssertions = {
 var getTraceAssertions = {
   name: "get_trace_assertions",
   title: "Get Trace Assertions",
-  description: `Read what SHOULD happen when one or more traces are replayed: each trace's approved assertions, their pass/fail criteria, people-only human note, who is assigned to review each one, and what part of the evaluated trace each one checks. Only assertions a person has approved are returned, because only those are checked on a replay; a trace whose assertions are all still awaiting review reads the same as one with none. Categorized assertions include category_assertion_id and the category's id, title, and description. A human note is returned so it can be read and edited, but it is never assessment evidence: judge only from the assertion, pass/fail criteria, and evaluated trace. Call this before judging a replay so the verdict is measured against what the user actually asked for rather than a guess, and before save_trace_assertions to find the assertion to edit or to avoid creating a duplicate. No span content is loaded, so one call accepts up to ${GET_TRACE_ASSERTIONS_MAX_IDS} ids. Accepts original trace ids and replay trace ids alike: a replay with no assertions of its own reads its original's, and the response says which original they came from. An assertion whose target cannot be found on the trace being evaluated is errored, never passed, so record it with save_agent_labels \`skip\` rather than a FAIL.`,
+  description: `Read what SHOULD happen when one or more traces are replayed: each trace's approved assertions, their pass/fail criteria, people-only human note, who is assigned to review each one, and what part of the evaluated trace each one checks. Only assertions a person has approved are returned, because only those are checked on a replay; a trace whose assertions are all still awaiting review reads the same as one with none. Each trace also reports its assertion generation, if one ran: running, completed with how many drafts it saved for review, or failed with the reason. Categorized assertions include category_assertion_id and the category's id, title, and description. A human note is returned so it can be read and edited, but it is never assessment evidence: judge only from the assertion, pass/fail criteria, and evaluated trace. Call this before judging a replay so the verdict is measured against what the user actually asked for rather than a guess, and before save_trace_assertions to find the assertion to edit or to avoid creating a duplicate. No span content is loaded, so one call accepts up to ${GET_TRACE_ASSERTIONS_MAX_IDS} ids. Accepts original trace ids and replay trace ids alike: a replay with no assertions of its own reads its original's, and the response says which original they came from. An assertion whose target cannot be found on the trace being evaluated is errored, never passed, so record it with save_agent_labels \`skip\` rather than a FAIL.`,
   inputSchema: {
     traceIds: external_exports.preprocess(parseJsonString, external_exports.array(external_exports.uuid()).min(1).max(GET_TRACE_ASSERTIONS_MAX_IDS)).describe(`Original trace IDs to read assertions for (1-${GET_TRACE_ASSERTIONS_MAX_IDS})`)
   }
@@ -24906,10 +24907,10 @@ var semver3 = __toESM(require_semver2(), 1);
 
 // ../bitfab-plugin-lib/dist/bakedSdkVersions.js
 var BAKED_SDK_VERSIONS = {
-  typescript: "0.58.5",
-  python: "0.58.5",
-  ruby: "0.58.4",
-  go: "0.58.4"
+  typescript: "0.59.0",
+  python: "0.59.0",
+  ruby: "0.59.0",
+  go: "0.59.0"
 };
 
 // ../bitfab-plugin-lib/dist/installedSdk.js

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bitfab-cli",
-  "version": "0.2.379",
+  "version": "0.2.380",
   "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",