allow external_directory reads — not a security boundary

Made-with: Cursor

agents/opentoad.ts

@@ -52,7 +52,7 @@ function buildSecurityConfig(ctx: AgentRunContext, model: string | undefined): s
       edit: "allow",
       read: "allow",
       webfetch: "allow",
-      external_directory: "deny",
+      external_directory: "allow",
       skill: "allow",
     },
     mcp: {

entry

@@ -148198,7 +148198,8 @@ ${learningsStep(6)}`,
 
 6. Submit:
    - **actionable issues found**: call \`${ghPullfrogMcpName}/create_pull_request_review\` with \`approved: false\`, all comments, and an **empty body** \u2014 inline comments speak for themselves, and a top-level body clutters the PR conversation on every re-review cycle. Then call \`report_progress\` with a 1-sentence summary.
-   - **no actionable issues found**: do NOT submit a review. Call \`${ghPullfrogMcpName}/report_progress\` with a brief note (e.g., "Re-reviewed \u2014 no new issues found.").`,
+   - **no actionable issues, but substantive changes or prior fixes confirmed**: post a brief comment (1-3 sentences) via \`${ghPullfrogMcpName}/create_issue_comment\` confirming the review happened and listing which prior review issues were resolved. Substantive = new functionality, behavior changes, architectural changes, or fixes to previously flagged issues.
+   - **no actionable issues, non-substantive changes only** (e.g., trivial formatting, import reordering, comment tweaks with no functional impact): do NOT submit a review. Call \`${ghPullfrogMcpName}/report_progress\` with a brief note (e.g., "Re-reviewed \u2014 no new issues found.").`,
   Plan: `### Checklist
 
 1. Analyze the task and gather context:
@@ -149048,7 +149049,8 @@ ${permalinkTip}
 
 7. **SUBMIT** \u2014 Determine whether to submit a review:
    - **Issues found**: Submit via ${ghPullfrogMcpName}/create_pull_request_review with \`approved: false\`, the inline comments from step 6, and an **empty body** \u2014 inline comments speak for themselves, and a top-level body clutters the PR conversation on every re-review cycle. Then call \`report_progress\` with a 1-sentence summary (e.g., "Re-reviewed \u2014 found 2 issues in the new commits.").
-   - **No issues found**: Do NOT submit a review. Call \`report_progress\` with a brief note (e.g., "Re-reviewed \u2014 no new issues found.").
+   - **No issues, but substantive changes or prior fixes confirmed**: Post a brief comment (1-3 sentences) via ${ghPullfrogMcpName}/create_issue_comment confirming the review happened and listing which prior review issues were resolved. Substantive = new functionality, behavior changes, architectural changes, or fixes to previously flagged issues.
+   - **No issues, non-substantive changes only** (e.g., trivial formatting, import reordering, comment tweaks with no functional impact): Do NOT submit a review. Call \`report_progress\` with a brief note (e.g., "Re-reviewed \u2014 no new issues found.").
 
 ${permalinkTip}
 `
@@ -149376,7 +149378,7 @@ function buildSecurityConfig(ctx, model) {
       edit: "allow",
       read: "allow",
       webfetch: "allow",
-      external_directory: "deny",
+      external_directory: "allow",
       skill: "allow"
     },
     mcp: {

mcp/selectMode.ts

@@ -135,7 +135,8 @@ ${learningsStep(6)}`,
 
 6. Submit:
    - **actionable issues found**: call \`${ghPullfrogMcpName}/create_pull_request_review\` with \`approved: false\`, all comments, and an **empty body** — inline comments speak for themselves, and a top-level body clutters the PR conversation on every re-review cycle. Then call \`report_progress\` with a 1-sentence summary.
-   - **no actionable issues found**: do NOT submit a review. Call \`${ghPullfrogMcpName}/report_progress\` with a brief note (e.g., "Re-reviewed — no new issues found.").`,
+   - **no actionable issues, but substantive changes or prior fixes confirmed**: post a brief comment (1-3 sentences) via \`${ghPullfrogMcpName}/create_issue_comment\` confirming the review happened and listing which prior review issues were resolved. Substantive = new functionality, behavior changes, architectural changes, or fixes to previously flagged issues.
+   - **no actionable issues, non-substantive changes only** (e.g., trivial formatting, import reordering, comment tweaks with no functional impact): do NOT submit a review. Call \`${ghPullfrogMcpName}/report_progress\` with a brief note (e.g., "Re-reviewed — no new issues found.").`,
 
   Plan: `### Checklist
 

modes.ts

@@ -154,7 +154,8 @@ ${permalinkTip}
 
 7. **SUBMIT** — Determine whether to submit a review:
    - **Issues found**: Submit via ${ghPullfrogMcpName}/create_pull_request_review with \`approved: false\`, the inline comments from step 6, and an **empty body** — inline comments speak for themselves, and a top-level body clutters the PR conversation on every re-review cycle. Then call \`report_progress\` with a 1-sentence summary (e.g., "Re-reviewed — found 2 issues in the new commits.").
-   - **No issues found**: Do NOT submit a review. Call \`report_progress\` with a brief note (e.g., "Re-reviewed — no new issues found.").
+   - **No issues, but substantive changes or prior fixes confirmed**: Post a brief comment (1-3 sentences) via ${ghPullfrogMcpName}/create_issue_comment confirming the review happened and listing which prior review issues were resolved. Substantive = new functionality, behavior changes, architectural changes, or fixes to previously flagged issues.
+   - **No issues, non-substantive changes only** (e.g., trivial formatting, import reordering, comment tweaks with no functional impact): Do NOT submit a review. Call \`report_progress\` with a brief note (e.g., "Re-reviewed — no new issues found.").
 
 ${permalinkTip}
 `,

test/__snapshots__/models.test.ts.snap

@@ -23,8 +23,8 @@ exports[`latest model per provider snapshot > matches snapshot 1`] = `
     "releaseDate": "2026-03-17",
   },
   "opencode": {
-    "modelId": "mimo-v2-pro-free",
+    "modelId": "qwen3.6-plus-free",
-    "releaseDate": "2026-03-18",
+    "releaseDate": "2026-03-30",
   },
   "openrouter": {
     "modelId": "xiaomi/mimo-v2-pro",