@peterxiaoyang/superspec 0.1.4 → 0.1.6

package/adapters/codex/agents/verifier.toml

@@ -3,117 +3,11 @@ name = "verifier"
 description = "Completion evidence, claim validation, test adequacy"
 model_reasoning_effort = "xhigh"
 developer_instructions = """
-<identity>
-You are Verifier. Prove or disprove completion with direct evidence.
-</identity>
+Role: Verifier. Prove or disprove completion claims with reproducible evidence; missing evidence is not a pass.
 
-<goal>
-Turn claims into reproducible proof or proof gaps by checking code, diffs, commands, diagnostics, tests, artifacts, and acceptance criteria. Missing evidence is a gap, not a pass, and the main thread remains responsible for final adjudication.
-</goal>
+Prompt binding: load `.codex/prompts/verifier.md` first, then read the provided `review-packet`, `apply-verify-packet`, or `prompt_ref`. The packet's refs, output kind, contract fields, review scope, evidence/report refs, freshness fingerprints, and stop conditions override static prompt memory.
 
-<constraints>
-<scope_guard>
-- Verify claims against observable evidence; do not trust implementation summaries.
-- Distinguish failed behavior from unavailable or missing proof.
-- Prefer fresh command output when available.
-</scope_guard>
+Boundary: read-only. Check commands, test output, diff, artifacts, evidence refs, acceptance criteria, and freshness without editing files, writing evidence, marking tasks complete, or replacing main-thread workflow decisions.
 
-<ask_gate>
-<!-- OMX:GUIDANCE:VERIFIER:CONSTRAINTS:START -->
-- Default reports to outcome-first, evidence-dense verdicts: name the claim, success criteria, validation evidence, gaps, and stop condition before adding process detail.
-- Keep collaboration style direct and concise; do not expand verification scope beyond what materially proves or disproves the claim.
-- For multi-step verification, start with a concise preamble that names the first check; keep intermediate updates brief and evidence-based.
-- AUTO-CONTINUE for clear, already-requested, low-risk, reversible, local inspect-test-verify work; keep inspecting, testing, and verifying without permission handoff.
-- ASK only for destructive, irreversible, credential-gated, external-production, or materially scope-changing actions, or when missing authority blocks progress.
-- On AUTO-CONTINUE branches, do not use permission-handoff phrasing; state the next verification action or evidence-backed verdict.
-- Use absolute language only for true invariants: safety, security, side-effect boundaries, required output fields, workflow state transitions, and product contracts.
-- Keep gathering evidence until the verdict is grounded or blocked by a missing acceptance target or unavailable proof source.
-- If correctness depends on additional tests, diagnostics, or inspection, keep using those tools until the verdict is grounded; stop once enough evidence proves the core claim.
-- More verification effort does not mean unrelated tool churn; gather the proof that matters, not every possible artifact.
-<!-- OMX:GUIDANCE:VERIFIER:CONSTRAINTS:END -->
-- Ask only when the acceptance target is materially unclear and cannot be derived from repo or task history.
-</ask_gate>
-</constraints>
-
-<execution_loop>
-1. State what must be proven.
-2. Inspect relevant files, diffs, outputs, and artifacts.
-3. Run or review the commands that directly prove the claim.
-4. Report proof status, evidence, gaps, risks, and any blocked proof source.
-</execution_loop>
-
-<success_criteria>
-- Acceptance criteria are checked directly.
-- Evidence is concrete and reproducible.
-- Missing proof is called out explicitly.
-- The verdict is grounded and actionable.
-</success_criteria>
-
-<verification_loop>
-<!-- OMX:GUIDANCE:VERIFIER:INVESTIGATION:START -->
-5) If a newer user instruction only changes the current verification target or report shape, apply that override locally without discarding earlier non-conflicting acceptance criteria; preserve traceability from each claim to evidence, validation command, or explicit proof gap.
-<!-- OMX:GUIDANCE:VERIFIER:INVESTIGATION:END -->
-Keep gathering the required evidence until the verdict is grounded or the proof source is unavailable.
-</verification_loop>
-
-<tools>
-Use Read/Grep/Glob for evidence, diagnostics/test/build commands for behavior, and diff/history inspection when scope depends on recent changes.
-</tools>
-
-<style>
-<output_contract>
-## Verdict
-- PASS / FAIL / PARTIAL
-
-## Evidence
-- `command or artifact` — result
-
-## Gaps
-- Missing or inconclusive proof
-
-## Risks
-- Remaining uncertainty or follow-up needed
-</output_contract>
-
-<scenario_handling>
-- If the user says `continue`, keep gathering the required evidence instead of restating a partial verdict.
-- If the user says `merge if CI green`, check relevant statuses, confirm they are green, and report the gate outcome.
-</scenario_handling>
-
-<stop_rules>
-Stop only when the verdict is evidence-backed or the needed proof source/authority is unavailable.
-</stop_rules>
-</style>
-
-<posture_overlay>
-
-You are operating in the frontier-orchestrator posture.
-- Prioritize intent classification before implementation.
-- Default to delegation and orchestration when specialists exist.
-- Treat the first decision as a routing problem: research vs planning vs implementation vs verification.
-- Challenge flawed user assumptions concisely before execution when the design is likely to cause avoidable problems.
-- Preserve explicit executor handoff boundaries: do not absorb deep implementation work when a specialized executor is more appropriate.
-
-</posture_overlay>
-
-<model_class_guidance>
-
-This role is tuned for standard-capability models.
-- Balance autonomy with clear boundaries.
-- Prefer explicit verification and narrow scope control over speculative reasoning.
-
-</model_class_guidance>
-
-<native_subagent_leaf_guard>
-
-Leaf native subagent: do not call Task, spawn_agent, or native child agents.
-Use local tools; report missing specialist coverage to the leader.
-
-</native_subagent_leaf_guard>
-
-## OMX Agent Metadata
-- role: verifier
-- posture: frontier-orchestrator
-- model_class: standard
-- routing_role: leader
+Output: concise Simplified Chinese. State pass, fail, partial, or evidence gap first; list evidence, gaps, residual risk, and stop conditions.
 """

package/adapters/codex/install-map.json

@@ -42,6 +42,16 @@
       "source": "templates/workflow/prompts/critic.md",
       "target": ".codex/prompts/critic.md"
     },
+    {
+      "kind": "prompt",
+      "source": "templates/workflow/prompts/executor.md",
+      "target": ".codex/prompts/executor.md"
+    },
+    {
+      "kind": "prompt",
+      "source": "templates/workflow/prompts/test-runner.md",
+      "target": ".codex/prompts/test-runner.md"
+    },
     {
       "kind": "prompt",
       "source": "templates/workflow/prompts/test-engineer.md",
@@ -67,6 +77,16 @@
       "source": "adapters/codex/agents/critic.toml",
       "target": ".codex/agents/critic.toml"
     },
+    {
+      "kind": "agent",
+      "source": "adapters/codex/agents/executor.toml",
+      "target": ".codex/agents/executor.toml"
+    },
+    {
+      "kind": "agent",
+      "source": "adapters/codex/agents/test-runner.toml",
+      "target": ".codex/agents/test-runner.toml"
+    },
     {
       "kind": "agent",
       "source": "adapters/codex/agents/test-engineer.toml",

package/dist/src/apply_worker_chain.d.ts

@@ -0,0 +1,57 @@
+import type { JsonMap, Reason } from "./util.ts";
+export type ArtifactRefExpected = {
+    kind?: string;
+    role?: string;
+    taskId?: string;
+    chainId?: string | null;
+};
+export type ApplyWorkerArtifactMaterializeInput = {
+    taskId: string;
+    kind: "worker_report" | "raw_transcript" | "diff_transcript" | "status_report";
+    role: "test-runner" | "executor" | "code-reviewer" | "verifier";
+    content: string | Buffer | JsonMap;
+    path?: string;
+    refPath?: string;
+    filename?: string;
+    workerChainContext?: "none" | "executor_worker";
+    applyWorkerChainId?: string;
+    originPacketFingerprint?: string;
+    sourceImplementationFingerprint?: unknown;
+    producedImplementationFingerprint?: unknown;
+    observedImplementationFingerprint?: unknown;
+    inputRefDigest?: string;
+    command?: string;
+    cwd?: string;
+    phase?: string;
+    testId?: string;
+    exitCode?: number;
+    maxBytes?: number;
+    metadata?: JsonMap;
+};
+export declare const APPLY_WORKER_MAX_INLINE_REPORT_CHARS = 12000;
+export declare const APPLY_TEST_RUNNER_REPORT_REQUIRED_FIELDS: readonly ["role", "command", "command_source", "cwd", "phase", "task_id", "test_id", "exit_code", "semantic_status_candidate", "result_summary", "runtime_raw_transcript_ref", "repo_head", "pre_dirty_state", "post_dirty_state", "changed_files", "untracked_files", "invariant_refs", "source_refs", "origin_packet_fingerprint", "input_ref_digest", "source_implementation_fingerprint", "observed_implementation_fingerprint", "guard_fingerprint", "unverified_items"];
+export declare const APPLY_EXECUTOR_REPORT_REQUIRED_FIELDS: readonly ["role", "task_id", "apply_worker_chain_id", "cwd", "repo_head", "guard_fingerprint", "changed_files", "suggested_green_checks", "test_invariant_mapping", "runtime_artifact_refs", "origin_packet_fingerprint", "input_ref_digest", "source_implementation_fingerprint", "produced_implementation_fingerprint", "unverified_items", "risk_notes"];
+export declare const APPLY_CODE_REVIEW_REPORT_REQUIRED_FIELDS: readonly ["role", "review_status_candidate", "cwd", "repo_head", "guard_fingerprint", "executor_report_ref", "actual_changed_files", "changed_files", "untracked_files", "implementation_dirty_file_list", "implementation_fingerprint", "guard_artifact_manifest_fingerprint", "scope_verdict", "protected_path_verdict", "executor_report_mismatch", "test_invariant_mapping_verdict", "suggested_green_test_ids", "risk_notes", "runtime_raw_git_status_transcript_ref", "runtime_raw_git_diff_name_status_transcript_ref", "runtime_path_scoped_diff_transcript_refs", "origin_packet_fingerprint", "input_ref_digest", "source_implementation_fingerprint", "observed_implementation_fingerprint", "unverified_items"];
+export declare const APPLY_VERIFIER_REPORT_REQUIRED_FIELDS: readonly ["role", "verification_status_candidate", "task_completion_verdict", "chain_consistency_verdict", "acceptance_coverage_verdict", "invariant_coverage_verdict", "test_coverage_verdict", "cwd", "repo_head", "guard_fingerprint", "expected_freshness_fingerprint", "observed_freshness_fingerprint", "freshness_verdict", "green_test_run_evidence_refs", "executor_report_ref", "task_code_review_report_ref", "actual_changed_files", "changed_files", "untracked_files", "implementation_dirty_file_list", "implementation_fingerprint", "guard_artifact_manifest_fingerprint", "unexpected_guard_owned_dirty_paths", "scope_verdict", "protected_path_verdict", "executor_code_review_mismatch", "test_evidence_mismatch", "runtime_raw_git_status_transcript_ref", "runtime_raw_git_diff_name_status_transcript_ref", "runtime_path_scoped_diff_transcript_refs", "diff_summary_refs", "origin_packet_fingerprint", "input_ref_digest", "source_implementation_fingerprint", "observed_implementation_fingerprint", "risk_notes", "triggered_stop_conditions", "unverified_items"];
+export declare function apply_worker_implementation_fingerprint(repoRoot: string, changeRoot: string, expectedGuardRefs?: unknown[], opts?: {
+    declaredTaskWriteScope?: string[];
+    protectedPathRefs?: unknown[];
+}): JsonMap;
+export declare function apply_worker_protected_path_refs(repoRoot: string, changeRoot: string, expectedGuardRefs?: unknown[]): JsonMap[];
+export declare function worker_input_ref_digest(refs: unknown[]): string;
+export declare function apply_worker_executor_input_ref_digest(evidences: JsonMap[], active: JsonMap): string;
+export declare function apply_worker_guard_artifact_manifest_fingerprint(items: JsonMap): JsonMap;
+export declare function fingerprint_digest(value: unknown): string;
+export declare function fingerprint_matches(actual: unknown, expected: unknown): boolean;
+export declare function read_pinned_artifact_json(changeRoot: string, refItem: unknown): JsonMap | null;
+export declare function materialize_apply_worker_artifact_ref(changeRoot: string, input: ApplyWorkerArtifactMaterializeInput): JsonMap;
+export declare function pinned_artifact_ref_reasons(changeRoot: string, refItem: unknown, label: string, expected?: ArtifactRefExpected, code?: string): Reason[];
+export declare function worker_test_run_reasons(changeRoot: string, ev: JsonMap, taskId: string, chainId: string | null, code?: string): Reason[];
+export declare function pre_edit_evidence_ref_reasons(evidences: JsonMap[], active: JsonMap | null | undefined, taskId: string, code?: string): Reason[];
+export declare function compute_apply_worker_freshness(repoRoot: string, changeRoot: string, evidences: JsonMap[], taskId: string, chainId: string, refs: {
+    executor_report_ref: unknown;
+    task_code_review_report_ref: unknown;
+    green_test_run_evidence_ref: string;
+    green_test_run_evidence_refs?: string[];
+    verifier_report_ref?: unknown;
+}): JsonMap;