@fitlab-ai/agent-infra 0.11.4 → 0.11.6

package/templates/.agents/skills/review-plan/reference/report-template.en.md

@@ -157,16 +157,16 @@ Use this template when writing `review-plan.md` or `review-plan-r{N}.md`.
 
 ## State Check
 
-> Record the state-check command, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Record the state-check command, review scope, key result, and uncovered parts.
 > Follow `.agents/rules/evidence-reporting.md`: record review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
 ## Raw Evidence
 
-> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with an executable command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
 
 - Claim: {verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```
 

package/templates/.agents/skills/review-plan/reference/report-template.zh-CN.md

@@ -157,16 +157,16 @@
 
 ## 状态核对
 
-> 记录状态核对命令、审查范围、关键结果和未覆盖部分；每条命令以 `$ ` 开头。
+> 记录状态核对命令、审查范围、关键结果和未覆盖部分。
 > 按 `.agents/rules/evidence-reporting.md` 同时记录审查范围、关键结果和未覆盖部分；正常成功不粘贴完整 stdout。
 
 ## 证据原文
 
-> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对 `$ ` 命令和相称结果摘要；Blocker、失败、阻塞或争议必须保留可复现命令、准确位置和决定性摘录；无法复现的判断须降级或移入「自我质疑」。
+> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对可执行命令和相称结果摘要；Blocker、失败、阻塞或争议必须保留可复现命令、准确位置和决定性摘录；无法复现的判断须降级或移入「自我质疑」。
 
 - 断言：{verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```
 

package/templates/.agents/skills/review-pr/config/verify.en.json

@@ -12,8 +12,10 @@
         "State Check",
         "Evidence"
       ],
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
+      ],
       "required_patterns": [
-        "^\\$ ",
         "^- \\*\\*Reviewed Head SHA\\*\\*[:：]\\s*[0-9a-f]{40}\\s*$",
         "^- \\*\\*Review Mode\\*\\*[:：]\\s*(?:verify|audit|reconstruct)\\s*$",
         "^- \\*\\*Evidence Scenario\\*\\*[:：]\\s*S[123]\\s*$",

package/templates/.agents/skills/review-pr/config/verify.zh-CN.json

@@ -12,8 +12,10 @@
         "状态核对",
         "证据原文"
       ],
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
+      ],
       "required_patterns": [
-        "^\\$ ",
         "^- \\*\\*被审 head SHA\\*\\*[:：]\\s*[0-9a-f]{40}\\s*$",
         "^- \\*\\*审查模式\\*\\*[:：]\\s*(?:verify|audit|reconstruct)\\s*$",
         "^- \\*\\*证据场景\\*\\*[:：]\\s*S[123]\\s*$",

package/templates/.agents/skills/review-pr/reference/report-template.en.md

@@ -11,7 +11,7 @@ Use the following structure when creating `pr-review.md` or `pr-review-r{N}.md`.
 
 ## State Check
 
-> Record the state-check command, PR/head, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Record the state-check command, PR/head, review scope, key result, and uncovered parts.
 > Follow `.agents/rules/evidence-reporting.md`: record PR, head, review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
 ## Identity
@@ -77,10 +77,10 @@ Land the following in order before the line-level findings, without impersonatin
 
 ## Evidence
 
-> Follow `.agents/rules/evidence-reporting.md`: pair every assertion with a `$ ` command and proportionate result summary; formal Review, failures, blocking conditions, or disputes retain exact identity and decisive excerpts.
+> Follow `.agents/rules/evidence-reporting.md`: pair every assertion with an executable command and proportionate result summary; formal Review, failures, blocking conditions, or disputes retain exact identity and decisive excerpts.
 
 - Assertion: {verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```

package/templates/.agents/skills/review-pr/reference/report-template.zh-CN.md

@@ -11,7 +11,7 @@
 
 ## 状态核对
 
-> 记录状态核对命令、PR/head、审查范围、关键结果和未覆盖部分；每条命令以 `$ ` 开头。
+> 记录状态核对命令、PR/head、审查范围、关键结果和未覆盖部分。
 > 按 `.agents/rules/evidence-reporting.md` 同时记录 PR、head、审查范围、关键结果和未覆盖部分；正常成功不粘贴完整 stdout。
 
 ## 身份信息
@@ -77,10 +77,10 @@
 
 ## 证据原文
 
-> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对 `$ ` 命令和相称结果摘要；正式 Review、失败、阻塞或争议保留准确身份和决定性摘录。
+> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对可执行命令和相称结果摘要；正式 Review、失败、阻塞或争议保留准确身份和决定性摘录。
 
 - 断言：{verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```

package/templates/.agents/skills/run-manual-validation/config/verify.en.json

@@ -29,8 +29,8 @@
         "Remaining Coverage",
         "Raw Evidence"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     },
     "activity-log": {

package/templates/.agents/skills/run-manual-validation/config/verify.zh-CN.json

@@ -29,8 +29,8 @@
         "尚未覆盖",
         "证据原文"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     },
     "activity-log": {

package/templates/.agents/skills/run-manual-validation/reference/report-template.en.md

@@ -10,7 +10,7 @@
 ## State Check
 
 ```text
-$ agent-infra-internal task-snapshot {task-id} --format text
+agent-infra-internal task-snapshot {task-id} --format text
 {command-summary-and-key-result}
 ```
 > Follow `.agents/rules/evidence-reporting.md`: record command name, target scope, exit status, sanitized result, and coverage gap; do not paste complete argv or sensitive transcripts.
@@ -67,7 +67,7 @@ $ agent-infra-internal task-snapshot {task-id} --format text
 ## Raw Evidence
 
 ```text
-$ agent-infra-internal task-validate {task-ref} --scope {scope} --format json -- {redacted-command}
+agent-infra-internal task-validate {task-ref} --scope {scope} --format json -- {redacted-command}
 {sanitized-result}
 ```
 > Keep only the allowed public command and sanitized structured result; complete successful stdout is not default report content.

package/templates/.agents/skills/run-manual-validation/reference/report-template.zh-CN.md

@@ -10,7 +10,7 @@
 ## 状态核对
 
 ```text
-$ agent-infra-internal task-snapshot {task-id} --format text
+agent-infra-internal task-snapshot {task-id} --format text
 {command-summary-and-key-result}
 ```
 > 按 `.agents/rules/evidence-reporting.md` 记录命令名称、目标范围、退出状态、sanitized result 和覆盖缺口；不得粘贴完整 argv 或敏感 transcript。
@@ -67,7 +67,7 @@ $ agent-infra-internal task-snapshot {task-id} --format text
 ## 证据原文
 
 ```text
-$ agent-infra-internal task-validate {task-ref} --scope {scope} --format json -- {redacted-command}
+agent-infra-internal task-validate {task-ref} --scope {scope} --format json -- {redacted-command}
 {sanitized-result}
 ```
 > 仅保留允许公开的命令与脱敏结构化结果；完整成功 stdout 不属于默认报告内容。

package/dist/lib/internal/task-override.js

@@ -1,138 +0,0 @@
-import { consumeHumanOverride, diagnoseHumanOverrideForTask, issueHumanOverride } from '../task/human-override.js';
-import { resolveTaskRef } from '../task/resolve-ref.js';
-import { TaskExecutionLockError, withTaskExecutionLock } from '../task/task-execution-lock.js';
-import { ensureInternalHandlerRoute, internalHandlerRoute } from './cli-route-inventory.js';
-const USAGE = `Usage: agent-infra-internal task-override <task-ref> <diagnose|issue|consume> [options]
-
-Options: --failure-id <id> --target <target> --operator <operator> --reason <reason> --scope <scope>
-         --intent <lifecycle-intent> --alert-number <N> --issue-number <N> --staging-dir <path>
-         --expires-at <timestamp> --ticket <ticket-id> --pr-number <N>
-`;
-const FLAGS = {
-    '--failure-id': 'failureId',
-    '--target': 'target',
-    '--operator': 'operator',
-    '--reason': 'reason',
-    '--scope': 'scope',
-    '--intent': 'intent',
-    '--failure-digest': 'failureDigest',
-    '--expires-at': 'expiresAt',
-    '--ticket': 'ticketId',
-    '--facts': 'observedFacts',
-    '--alert-number': 'alertNumber',
-    '--issue-number': 'issueNumber',
-    '--pr-number': 'pullRequestNumber',
-    '--staging-dir': 'stagingDir'
-};
-function usageFailure(message) {
-    process.stdout.write(`${JSON.stringify({ status: 'failed', changed: false, error: { code: 'OVERRIDE_PAYLOAD_INVALID', message } })}\n`);
-    process.stderr.write(USAGE);
-    process.exitCode = 1;
-}
-async function taskOverride(args = []) {
-    if (!ensureInternalHandlerRoute('task-override', args))
-        return;
-    if (args[0] === '--help' || args[0] === '-h') {
-        process.stdout.write(USAGE);
-        return;
-    }
-    const [taskRef, operation] = args;
-    if (!taskRef || !operation || ![
-        internalHandlerRoute('task-override', 'diagnose', operation ?? ''),
-        internalHandlerRoute('task-override', 'issue', operation ?? ''),
-        internalHandlerRoute('task-override', 'consume', operation ?? '')
-    ].some(Boolean)) {
-        usageFailure('task ref and a valid operation are required');
-        return;
-    }
-    const values = { taskRef };
-    const seen = new Set();
-    for (let index = 2; index < args.length; index += 1) {
-        const flag = args[index];
-        const key = FLAGS[flag];
-        if (!key) {
-            usageFailure(`unknown option '${flag}'`);
-            return;
-        }
-        if (seen.has(flag)) {
-            usageFailure(`duplicate option '${flag}'`);
-            return;
-        }
-        const value = args[++index];
-        if (value === undefined || value.startsWith('--')) {
-            usageFailure(`option '${flag}' requires a value`);
-            return;
-        }
-        seen.add(flag);
-        values[key] = key === 'observedFacts' ? value.split(',').map((fact) => fact.trim()).filter(Boolean)
-            : key === 'alertNumber' || key === 'issueNumber' || key === 'pullRequestNumber' ? Number(value) : value;
-    }
-    const required = {
-        diagnose: [],
-        issue: ['failureId', 'target', 'operator', 'reason', 'scope', 'expiresAt'],
-        consume: ['failureId', 'target', 'scope', 'ticketId']
-    };
-    const missing = required[operation].find((key) => values[key] === undefined);
-    if (missing) {
-        usageFailure(`${operation} requires '--${missing.replace(/[A-Z]/g, (letter) => `-${letter.toLowerCase()}`)}'`);
-        return;
-    }
-    const resolved = resolveTaskRef(taskRef);
-    if (!resolved.ok) {
-        process.stdout.write(`${JSON.stringify({ status: 'failed', changed: false, error: { code: resolved.code, message: resolved.message } })}\n`);
-        process.exitCode = 1;
-        return;
-    }
-    let result;
-    try {
-        if (internalHandlerRoute('task-override', 'diagnose', operation)) {
-            result = await diagnoseHumanOverrideForTask(taskRef, values.failureId ? String(values.failureId) : undefined, values.target ? String(values.target) : undefined);
-        }
-        else if (internalHandlerRoute('task-override', 'issue', operation)) {
-            result = await withTaskExecutionLock(resolved.repoRoot, resolved.taskId, 'task-override.issue', async () => issueHumanOverride({
-                taskRef,
-                failureId: String(values.failureId),
-                target: String(values.target),
-                operator: String(values.operator),
-                reason: String(values.reason),
-                scope: String(values.scope),
-                expiresAt: String(values.expiresAt),
-                ...(values.intent ? { intent: String(values.intent) } : {}),
-                ...(values.alertNumber !== undefined ? { alertNumber: Number(values.alertNumber) } : {}),
-                ...(values.issueNumber !== undefined ? { issueNumber: Number(values.issueNumber) } : {}),
-                ...(values.pullRequestNumber !== undefined ? { pullRequestNumber: Number(values.pullRequestNumber) } : {}),
-                ...(values.stagingDir ? { stagingDir: String(values.stagingDir) } : {}),
-                ...(values.failureDigest ? { failureDigest: String(values.failureDigest) } : {})
-            }));
-        }
-        else {
-            result = await withTaskExecutionLock(resolved.repoRoot, resolved.taskId, 'task-override.consume', async () => consumeHumanOverride({
-                taskRef,
-                ticketId: String(values.ticketId),
-                failureId: String(values.failureId),
-                target: String(values.target),
-                scope: String(values.scope),
-                ...(values.intent ? { intent: String(values.intent) } : {}),
-                ...(values.alertNumber !== undefined ? { alertNumber: Number(values.alertNumber) } : {}),
-                ...(values.issueNumber !== undefined ? { issueNumber: Number(values.issueNumber) } : {}),
-                ...(values.pullRequestNumber !== undefined ? { pullRequestNumber: Number(values.pullRequestNumber) } : {}),
-                ...(values.stagingDir ? { stagingDir: String(values.stagingDir) } : {}),
-                ...(values.failureDigest ? { failureDigest: String(values.failureDigest) } : {}),
-                ...(values.observedFacts ? { observedFacts: values.observedFacts } : {})
-            }));
-        }
-    }
-    catch (cause) {
-        if (cause instanceof TaskExecutionLockError) {
-            process.stdout.write(`${JSON.stringify({ status: 'failed', changed: false, error: { code: cause.code, message: cause.message } })}\n`);
-            process.exitCode = 1;
-            return;
-        }
-        throw cause;
-    }
-    process.stdout.write(`${JSON.stringify(result)}\n`);
-    if (result.status === 'failed')
-        process.exitCode = 1;
-}
-export { taskOverride };
-//# sourceMappingURL=task-override.js.map