😏

profiles/high-confidence-debugging/README.md

@@ -0,0 +1,7 @@
+# High-Confidence Debugging
+
+Use this featured profile for ambiguous or high-impact failures where changing code before independent reproduction would be risky. The DeepSeek V4 Pro root investigates and repairs; Sonnet independently reproduces and may contribute only a test-scope patch; fresh Sol verification attacks the fix, with one correction/reverification cycle.
+
+Only one worker runs alongside the root at a time. The sequence deliberately overlaps root diagnosis with reproduction, then enforces reproduction, repair, and verification barriers. Missing optional routes reduce confidence but do not prevent the root from reporting a blocked or evidence-limited diagnosis.
+
+Reproducer and verifier are persistent supervised Unix app-server workers. The root controls both, and each can steer or return the other to the precise missing proof through reciprocal action grants without gaining patch-integration authority. Long inference uses generous goal tokens or a clock-free turn; silence only warns, and suspension retains terminal history, reproduction artifacts, traces, and partial conclusions.

profiles/high-confidence-debugging/agents/debug-lead.md

@@ -0,0 +1 @@
+Own diagnosis, canonical repair, and final correctness. Launch independent reproduction early while you investigate non-overlapping hypotheses. Do not repair from symptoms alone when reproducible evidence is obtainable. At the reproduction barrier, inspect and explicitly accept or reject the result; integrate only a narrowly scoped regression-test patch after review. Implement the repair yourself, then request fresh verification. One correction and reverification cycle is available. Resolve disagreement using reproduction, tests, traces, and code—not voting.

profiles/high-confidence-debugging/agents/fix-verifier.md

@@ -0,0 +1 @@
+Adversarially verify the proposed fix against the original reproduction, hidden adjacent cases, and plausible regressions. Run focused commands and correlate their exit codes. Do not edit. A pass requires evidence that the original failure is fixed and meaningful negative/adjacent cases still behave correctly. Identify a precise correction target for every failure.

profiles/high-confidence-debugging/agents/independent-reproducer.md

@@ -0,0 +1 @@
+Independently reproduce the reported failure before seeing a proposed repair. Minimize the reproducer and distinguish observed behavior from hypotheses. You may edit only the assigned test scope and may return only a regression-test patch; never modify production source. Record exact correlated commands, exit codes, expected behavior, observed behavior, and environmental limitations. The root alone accepts and integrates your patch.

profiles/high-confidence-debugging/contracts/reproduction.json

@@ -0,0 +1,33 @@
+{
+  "title": "Independent failure reproduction",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "status": {"type": "string", "enum": ["reproduced", "not_reproduced", "blocked"]},
+    "minimal_reproduction": {"type": "string"},
+    "expected": {"type": "string", "minLength": 1},
+    "observed": {"type": "string", "minLength": 1},
+    "commands": {
+      "type": "array",
+      "maxItems": 30,
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "command": {"type": "string", "minLength": 1},
+          "exit_code": {"type": "integer"},
+          "observation": {"type": "string", "minLength": 1}
+        },
+        "required": ["command", "exit_code", "observation"]
+      }
+    },
+    "test_files": {"type": "array", "items": {"type": "string"}, "maxItems": 20, "uniqueItems": true},
+    "hypotheses": {"type": "array", "items": {"type": "string"}, "maxItems": 20},
+    "limitations": {"type": "array", "items": {"type": "string"}, "maxItems": 20}
+  },
+  "required": ["status", "minimal_reproduction", "expected", "observed", "commands", "test_files", "hypotheses", "limitations"],
+  "allOf": [
+    {"if": {"properties": {"status": {"const": "reproduced"}}, "required": ["status"]}, "then": {"properties": {"minimal_reproduction": {"minLength": 1}, "commands": {"minItems": 1}, "test_files": {"minItems": 1}}}},
+    {"if": {"properties": {"status": {"const": "blocked"}}, "required": ["status"]}, "then": {"properties": {"limitations": {"minItems": 1}}}}
+  ]
+}

profiles/high-confidence-debugging/contracts/verification.json

@@ -0,0 +1,33 @@
+{
+  "title": "Adversarial fix verification",
+  "type": "object",
+  "additionalProperties": false,
+  "properties": {
+    "verdict": {"type": "string", "enum": ["pass", "fail", "blocked"]},
+    "original_failure_fixed": {"type": "boolean"},
+    "adjacent_cases_preserved": {"type": "boolean"},
+    "commands": {
+      "type": "array",
+      "maxItems": 30,
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "command": {"type": "string", "minLength": 1},
+          "exit_code": {"type": "integer"},
+          "observation": {"type": "string", "minLength": 1}
+        },
+        "required": ["command", "exit_code", "observation"]
+      }
+    },
+    "findings": {"type": "array", "items": {"type": "string"}, "maxItems": 30},
+    "correction_targets": {"type": "array", "items": {"type": "string"}, "maxItems": 30},
+    "blockers": {"type": "array", "items": {"type": "string"}, "maxItems": 20}
+  },
+  "required": ["verdict", "original_failure_fixed", "adjacent_cases_preserved", "commands", "findings", "correction_targets", "blockers"],
+  "allOf": [
+    {"if": {"properties": {"verdict": {"const": "pass"}}, "required": ["verdict"]}, "then": {"properties": {"original_failure_fixed": {"const": true}, "adjacent_cases_preserved": {"const": true}, "commands": {"minItems": 1}, "findings": {"maxItems": 0}, "blockers": {"maxItems": 0}}}},
+    {"if": {"properties": {"verdict": {"const": "fail"}}, "required": ["verdict"]}, "then": {"properties": {"findings": {"minItems": 1}, "correction_targets": {"minItems": 1}}}},
+    {"if": {"properties": {"verdict": {"const": "blocked"}}, "required": ["verdict"]}, "then": {"properties": {"blockers": {"minItems": 1}}}}
+  ]
+}

profiles/high-confidence-debugging/profile.toml

@@ -0,0 +1,93 @@
+schema_version = 8
+id = "high-confidence-debugging"
+version = "8.0.0"
+display_name = "High-Confidence Debugging"
+description = "An economical DeepSeek diagnostician overlaps an independent Sonnet reproduction, repairs only after reproduction evidence, and submits the fix to fresh Sol verification."
+tags = ["debugging", "reproduction", "actor-critic", "featured"]
+maturity = "featured"
+root = "debug_lead"
+smoke = "smoke.toml"
+
+[agents.debug_lead]
+kind = "root"
+description = "Diagnostician, sole repair writer, correction owner, and final debugger"
+model = "opencode_go_openai_chat__deepseek_v4_pro"
+reasoning = "high"
+allowed_reasoning_efforts = ["high", "max"]
+execution_mode = "goal"
+goal_token_budget = 600000
+max_goal_token_budget = 1000000
+stall_warning_seconds = 3600
+finalization_grace_seconds = 1800
+plan_reasoning = "high"
+permissions = "workspace-write"
+can_spawn = ["independent_reproducer", "fix_verifier"]
+max_active = 1
+trust = "high"
+verification = "always"
+instructions = "agents/debug-lead.md"
+
+[agents.independent_reproducer]
+description = "Independent reproducer allowed to return only a regression-test patch"
+model = "opencode_zen_anthropic_messages__claude_sonnet_5"
+reasoning = "high"
+allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
+execution_mode = "goal"
+goal_token_budget = 200000
+max_goal_token_budget = 300000
+stall_warning_seconds = 1800
+finalization_grace_seconds = 1200
+permissions = "workspace-write"
+backends = ["mcp"]
+can_spawn = []
+max_active = 1
+allowed_task_kinds = ["reproduction", "test"]
+trust = "high"
+verification = "always"
+contract_enforcement = "strict"
+output_contract = "contracts/reproduction.json"
+instructions = "agents/independent-reproducer.md"
+
+[agents.fix_verifier]
+description = "Fresh Sol adversarial verifier, reusable once for a correction/reverification cycle"
+model = "codex_chatgpt_builtin__gpt_5_6_sol"
+reasoning = "high"
+allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
+execution_mode = "turn"
+stall_warning_seconds = 1800
+finalization_grace_seconds = 900
+permissions = "read-only"
+backends = ["mcp"]
+can_spawn = []
+max_active = 1
+allowed_task_kinds = ["verification", "review", "test_analysis"]
+trust = "adversarial_reviewer"
+verification = "root_adjudication"
+contract_enforcement = "strict"
+output_contract = "contracts/verification.json"
+instructions = "agents/fix-verifier.md"
+
+[agents.debug_lead.controls.independent_reproducer]
+actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
+
+[agents.debug_lead.controls.fix_verifier]
+actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
+
+[agents.independent_reproducer.controls.fix_verifier]
+actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
+
+[agents.fix_verifier.controls.independent_reproducer]
+actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
+
+[coordination]
+mode = "reproduce_repair_verify"
+orchestration = "mcp"
+max_active_agents = 2
+max_depth = 1
+max_children_per_agent = 2
+max_active_writers = 1
+reject_ancestor_role = true
+wait_policy = "dependency_only"
+write_conflict_policy = "reject"
+contradiction_policy = "primary_evidence"
+result_visibility = "ancestors"

profiles/high-confidence-debugging/smoke.toml

@@ -0,0 +1,24 @@
+schema_version = 8
+
+[[tasks]]
+agent = "debug_lead"
+task_kind = "analysis"
+task = "Inspect the debugging evaluation fixture read-only and describe the reproduction, repair, and verification barriers."
+mode = "read-only"
+wall_timeout_seconds = 600
+
+[[tasks]]
+agent = "independent_reproducer"
+task_kind = "reproduction"
+task = "Reproduce the currently passing debugging fixture without editing production source. If no failure exists, return only valid reproduction JSON with status not_reproduced and correlated command evidence; make no changes."
+backend = "mcp"
+mode = "read-only"
+wall_timeout_seconds = 900
+
+[[tasks]]
+agent = "fix_verifier"
+task_kind = "verification"
+task = "Verify the current debugging fixture tests read-only. Return only valid verification JSON with captured command evidence and no unsupported pass claim."
+backend = "mcp"
+mode = "read-only"
+wall_timeout_seconds = 900