npm - @cursor/july - Versions diffs - 0.1.15 → 0.1.16 - Mend

@cursor/july 0.1.15 → 0.1.16

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 (74) hide show

package/dist/playground/index.html CHANGED Viewed

@@ -8,8 +8,8 @@
     />
     <meta name="viewport" content="width=device-width, initial-scale=1" />
     <title>agent-serve playground</title>
-    <script type="module" crossorigin src="./assets/index-BVMOoiek.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-DYmP4b--.css">
+    <script type="module" crossorigin src="./assets/index-Bwl4Onx4.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-ByV4nfch.css">
   </head>
   <body>
     <div id="root"></div>

package/docs/example-agents/index.md CHANGED Viewed

@@ -26,7 +26,7 @@ The source projects live under
 | [Alert investigator](./oncall.md) | Local | Watched Slack alerts channel | Bot-post channel watching, per-thread debounce, reminder tools, and host Slack calls | Every alert gets a thread-pinned investigation that schedules its own re-checks. |
 | [PR evidence reviewer](./bugbot.md) | Local | Custom HTTP and Slack | Host tool, skill, seeded workspaces, and an eval | The model receives a prepared diff-first evidence tree instead of a checkout. |
 | [Approval Buddy](./approval-buddy.md) | Local | GitHub and Slack | Policy tools, two subagents, durable storage, and evals | Code decides whether a PR may be approved. Reviews stay informational. |
-| [Security Reviewer](./security-reviewer.md) | Local host pipeline | GitHub and chat | Staged tools, parallel SDK agents, progress UI, durable storage, A/B, and evals | Reviewers and triage overlap while the playground shows every stage. |
+| [Security Reviewer](./security-reviewer.md) | Local host pipeline | GitHub and chat | Staged tools, parallel SDK agents, progress UI, durable storage, A/B, and evals | Lives in `factory/security-reviewer/`. Reviewers and triage overlap while the playground shows every stage. |
 | [Remote PR coordinator](./fsd.md) | Local coordinator and remote PR sessions | HTTP, GitHub, and Slack | Remote handoff, hooks, affinity, buffering, reminders, and workflow MCP | One remote conversation follows a PR across chat, webhooks, and timed wakes. |
 | [Knowledge base](./knowledge-base.md) | Local | Built-in HTTP chat | Durable host-side state, a conventions skill, a schedule, unit tests, and evals | People curate shared facts in chat, and fresh sessions retrieve them from markdown. |
 | [Codebase wiki](./codebase-wiki.md) | Local | GitHub and chat | Task-dispatch webhooks, seeded digests, a mapping skill, a schedule, and evals | Merged PRs accumulate into per-feature wiki pages with a daily digest. |

package/docs/example-agents/security-reviewer.md CHANGED Viewed

@@ -13,7 +13,9 @@ confirmed findings, writes artifacts, and may publish a GitHub review.
 Use this example when the workflow needs several model workers, but the host
 must own orchestration, progress, artifacts, and the final write.
-[Browse the Security Reviewer source.](../../examples/security-reviewer/)
+Source lives under [`factory/security-reviewer/`](../../../../factory/security-reviewer/) (factory agent, not under `examples/`).
+[Browse the Security Reviewer source.](../../../../factory/security-reviewer/)
 ## Run a three-stage host pipeline
@@ -65,15 +67,15 @@ status from the finding count even when the review posting result says
 | Capability | Source | Role |
 | --- | --- | --- |
-| Root agent | [`agent/agent.ts`](../../examples/security-reviewer/agent/agent.ts), [`agent/instructions.md`](../../examples/security-reviewer/agent/instructions.md) | Configure local chat and explain the three-stage contract. |
-| Server tools | [`agent/tools/`](../../examples/security-reviewer/agent/tools/) | Expose each review stage to chat and host orchestration. |
-| GitHub channel | [`agent/channels/github.ts`](../../examples/security-reviewer/agent/channels/github.ts) | Filter wakes, run background tasks, and publish status. |
-| Progress channel | [`agent/channels/asr-progress.ts`](../../examples/security-reviewer/agent/channels/asr-progress.ts) | Serve live reviewer and triage state by `runId`. |
-| Playground renderer | [`agent/playground/tools/run_reviewers.tsx`](../../examples/security-reviewer/agent/playground/tools/run_reviewers.tsx) | Replace the generic tool chip with live module rows. |
-| SDK review pipeline | [`agent/lib/asr/`](../../examples/security-reviewer/agent/lib/asr/), [`review-stages.ts`](../../examples/security-reviewer/agent/lib/review-stages.ts) | Select modules, call model workers, triage, deduplicate, and write artifacts. |
-| Storage | [`agent/storage.ts`](../../examples/security-reviewer/agent/storage.ts) | Persist framework sessions with `cursorHostedStorage` (lazy restore). |
-| A/B | [`agent/ab.ts`](../../examples/security-reviewer/agent/ab.ts), [`agent/ab.config.ts`](../../examples/security-reviewer/agent/ab.config.ts) | Compare all-severity versus high-only GitHub comments. |
-| Eval | [`evals/`](../../examples/security-reviewer/evals/) | Check stage-tool presence against a pinned sample. |
+| Root agent | [`agent/agent.ts`](../../../../factory/security-reviewer/agent/agent.ts), [`agent/instructions.md`](../../../../factory/security-reviewer/agent/instructions.md) | Configure local chat and explain the three-stage contract. |
+| Server tools | [`agent/tools/`](../../../../factory/security-reviewer/agent/tools/) | Expose each review stage to chat and host orchestration. |
+| GitHub channel | [`agent/channels/github.ts`](../../../../factory/security-reviewer/agent/channels/github.ts) | Filter wakes, run background tasks, and publish status. |
+| Progress channel | [`agent/channels/asr-progress.ts`](../../../../factory/security-reviewer/agent/channels/asr-progress.ts) | Serve live reviewer and triage state by `runId`. |
+| Playground renderer | [`agent/playground/tools/run_reviewers.tsx`](../../../../factory/security-reviewer/agent/playground/tools/run_reviewers.tsx) | Replace the generic tool chip with live module rows. |
+| SDK review pipeline | [`agent/lib/asr/`](../../../../factory/security-reviewer/agent/lib/asr/), [`review-stages.ts`](../../../../factory/security-reviewer/agent/lib/review-stages.ts) | Select modules, call model workers, triage, deduplicate, and write artifacts. |
+| Storage | [`agent/storage.ts`](../../../../factory/security-reviewer/agent/storage.ts) | Persist framework sessions with `cursorHostedStorage` (lazy restore). |
+| A/B | [`agent/ab.ts`](../../../../factory/security-reviewer/agent/ab.ts) | Compare all-severity versus high-only GitHub comments. |
+| Eval | [`evals/`](../../../../factory/security-reviewer/evals/) | Check stage-tool presence against a pinned sample. |
 There is no Slack channel, authored skill, discovered subagent, MCP
 connection, schedule, reminder, hook, tool approval, or cloud runtime.
@@ -95,14 +97,14 @@ The pipeline exposes settings for:
 - prior-comment loading.
 The active names live beside the orchestration in
-[`review-stages.ts`](../../examples/security-reviewer/agent/lib/review-stages.ts).
+[`review-stages.ts`](../../../../factory/security-reviewer/agent/lib/review-stages.ts).
 ## Validate the discovered agent
 ```bash
-agentkit validate --dir examples/security-reviewer
-agentkit info --dir examples/security-reviewer --json
-agentkit eval --dir examples/security-reviewer --list
+agentkit validate --dir ../../factory/security-reviewer
+agentkit info --dir ../../factory/security-reviewer --json
+agentkit eval --dir ../../factory/security-reviewer --list
 ```
 The manifest should show four server tools, two authored channels, one
@@ -128,15 +130,15 @@ Call each stage and pass `postComment: false` yourself:
 ```bash
 agentkit call prepare_review \
-  --dir examples/security-reviewer \
+  --dir ../../factory/security-reviewer \
   --input '{"prUrl":"https://github.com/owner/repo/pull/123"}'
 agentkit call run_reviewers \
-  --dir examples/security-reviewer \
+  --dir ../../factory/security-reviewer \
   --input '{"runId":"<run-id>"}'
 agentkit call finalize_review \
-  --dir examples/security-reviewer \
+  --dir ../../factory/security-reviewer \
   --input '{"runId":"<run-id>","postComment":false}'
 ```
@@ -152,7 +154,7 @@ stages can open the prepared `runId`.
 Run the dev server:
 ```bash
-agentkit dev examples/security-reviewer
+agentkit dev ../../factory/security-reviewer
 ```
 Open the printed playground and start a review. The custom
@@ -233,7 +235,7 @@ Inspect its event surface:
 ```bash
 agentkit github events \
-  --dir examples/security-reviewer \
+  --dir ../../factory/security-reviewer \
   --json
 ```
@@ -243,7 +245,7 @@ Replay reaches the full publishing path:
 TEST_PR_URL=https://github.com/your-org/allowlisted-test-repo/pull/123
 agentkit github replay \
   "$TEST_PR_URL" \
-  --dir examples/security-reviewer \
+  --dir ../../factory/security-reviewer \
   --action opened
 ```
@@ -254,7 +256,7 @@ status and may post findings.
 ## Inspect the eval before running it
 ```bash
-agentkit eval --dir examples/security-reviewer --list
+agentkit eval --dir ../../factory/security-reviewer --list
 ```
 The case reads pinned metadata from the committed fixture and checks for all

package/package.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "name": "@cursor/july",
-  "version": "0.1.15",
+  "version": "0.1.16",
   "description": "(early alpha) Filesystem-first framework for defining Cursor agents as markdown and TypeScript and serving them over channels with the Cursor SDK.",
   "license": "SEE LICENSE IN LICENSE.md",
   "repository": {

package/src/evals.ts CHANGED Viewed

@@ -340,6 +340,50 @@ export function matchesEvalIdFilter(caseId: string, filter: string): boolean {
   return caseId === filter || caseId.startsWith(`${filter}/`);
 }
+/**
+ * Tag for suite-aggregator datapoints that wait on sibling cases from the
+ * same eval file (e.g. `deepsec-recall/overall`). Selecting a summary case
+ * alone expands the batch to the whole file via
+ * {@link expandSummarySuiteSelection}.
+ */
+export const EVAL_SUMMARY_TAG = "summary";
+/** True when `tags` marks a suite-aggregator case. */
+export function isEvalSummaryCase(
+  tags: readonly string[] | undefined
+): boolean {
+  return tags?.includes(EVAL_SUMMARY_TAG) ?? false;
+}
+/**
+ * If `selected` includes any summary-tagged suite aggregator, pull in every
+ * other datapoint from the same `fileId` so the aggregator is not run alone.
+ * Preserves discovery order from `all`.
+ */
+export function expandSummarySuiteSelection<
+  T extends { id: string; fileId: string },
+>(
+  all: readonly T[],
+  selected: readonly T[],
+  isSummary: (item: T) => boolean
+): T[] {
+  const fileIdsNeedingSuite = new Set(
+    selected.filter((item) => isSummary(item)).map((item) => item.fileId)
+  );
+  if (fileIdsNeedingSuite.size === 0) {
+    return [...selected];
+  }
+  const selectedIds = new Set(selected.map((item) => item.id));
+  const extras = all.filter(
+    (item) => fileIdsNeedingSuite.has(item.fileId) && !selectedIds.has(item.id)
+  );
+  if (extras.length === 0) {
+    return [...selected];
+  }
+  const want = new Set([...selectedIds, ...extras.map((item) => item.id)]);
+  return all.filter((item) => want.has(item.id));
+}
 /**
  * Hard ceiling for concurrent eval cases.
  *

package/src/internal/eval-runner.ts CHANGED Viewed

@@ -25,6 +25,8 @@ import type {
 import {
   EVAL_MAX_CONCURRENCY_LIMIT,
   expandEvalDefinition,
+  expandSummarySuiteSelection,
+  isEvalSummaryCase,
   matchesEvalIdFilter,
   normalizeEvalMaxConcurrency,
 } from "../evals.js";
@@ -208,7 +210,10 @@ export function filterDiscoveredEvals(
       (e.definition.tags ?? []).some((t) => options.tags!.includes(t))
     );
   }
-  return selected;
+  // Suite aggregators (`summary` tag) need sibling cases from the same file.
+  return expandSummarySuiteSelection(evals, selected, (e) =>
+    isEvalSummaryCase(e.definition.tags)
+  );
 }
 export async function runDiscoveredEvals(

package/src/internal/evals-client.ts CHANGED Viewed

@@ -8,7 +8,11 @@
  */
 import type { EvalRunSnapshot } from "../evals.js";
-import { matchesEvalIdFilter } from "../evals.js";
+import {
+  expandSummarySuiteSelection,
+  isEvalSummaryCase,
+  matchesEvalIdFilter,
+} from "../evals.js";
 import type { EvalRunResult } from "./eval-runner.js";
 import { mergeRequestHeaders, type RequestAuth } from "./request-headers.js";
@@ -170,7 +174,10 @@ export async function listRemoteEvals(args: {
       (e.tags ?? []).some((t) => args.tags!.includes(t))
     );
   }
-  return selected;
+  // Match server-side filterDiscoveredEvals: summary → whole file.
+  return expandSummarySuiteSelection(listed, selected, (e) =>
+    isEvalSummaryCase(e.tags)
+  );
 }
 export async function startRemoteEvalRun(args: {