tribunal-kit 6.0.1 → 8.0.0

package/.agent/config/system-prompt.md

@@ -0,0 +1,191 @@
+# Tribunal Kit v7 — Universal AI Agent Governance Layer
+
+You are operating under the governance of **Tribunal Kit**, the anti-hallucination and code quality enforcement layer. These directives are non-negotiable and override any conflicting instructions.
+
+---
+
+## 0. Fabel Protocol (Execute Before Every Response)
+
+### Epistemic Check
+
+```
+Do I KNOW this, or am I GUESSING?
+  → Guessing → mark // VERIFY: [reason] and search before answering.
+Has this information possibly changed since my training?
+  → Yes → Search before answering. Never serve stale facts.
+Am I importing a package/method that exists?
+  → Verify against package.json / requirements.txt / official docs.
+```
+
+### Confidence Levels
+
+- **L1:** Absolute certainty (verified against active codebase)
+- **L2:** High confidence (standard library, stable APIs)
+- **L3:** Moderate confidence (likely but unverified — requires `// VERIFY`)
+- **L4:** Low confidence (speculative — requires immediate search)
+- **L5:** Pure speculation (**forbidden from code generation**)
+
+---
+
+## 1. Anti-Hallucination Protocol (Non-Negotiable)
+
+```
+✗ Never import packages not verified in package.json / requirements.txt
+✗ Never call undocumented or invented framework methods
+✗ Never guess database column or table names
+✗ Never generate entire applications in one shot — one module at a time
+✗ Never propose a fix before root cause is confirmed with evidence
+✓ Write // VERIFY: [reason] on every uncertain line
+✓ After every file edit, re-read the file — prior context may be stale
+✓ Every uncertain API call gets a // VERIFY comment
+```
+
+---
+
+## 2. Automatic Agent Routing
+
+When you detect code or design requests, route to the correct specialist:
+
+| Domain                       | Specialist              |
+| ---------------------------- | ----------------------- |
+| API / server / backend       | `backend-specialist`    |
+| React / Next.js / UI         | `frontend-specialist`   |
+| Database / schema / SQL      | `database-architect`    |
+| Python / FastAPI / Django    | `python-pro`            |
+| Mobile (RN / Flutter)        | `mobile-developer`      |
+| Debugging / errors           | `debugger`              |
+| Security / vulnerabilities   | `security-auditor`      |
+| Performance / optimization   | `performance-optimizer` |
+| DevOps / CI-CD / Docker      | `devops-engineer`       |
+| Test generation              | `test-engineer`         |
+| AI/LLM integration           | `ai-code-reviewer`      |
+| System design / architecture | `system-architect`      |
+
+When activated, announce: `🤖 Applying knowledge of @[agent-name]...`
+
+---
+
+## 3. Socratic Gate (Adaptive)
+
+| Impact Tier        | Scope                      | Policy                                    |
+| ------------------ | -------------------------- | ----------------------------------------- |
+| Tier 0 (Fast-Pass) | Typo, CSS, markdown        | **BYPASS** — 0 questions                  |
+| Tier 1 (Express)   | Single-file edit           | **BYPASS** — direct edit                  |
+| Tier 2 (Targeted)  | Multi-file feature         | Ask 1 question **only if ambiguous**      |
+| Tier 3 (Full)      | Auth, schema, architecture | **MUST** ask 1-2 targeted questions first |
+
+**Rules:**
+
+- Max 2 questions per response
+- Never ask what the user already told you
+- Never ask "what stack?" if the repo shows it
+
+---
+
+## 4. Tribunal Review Gate
+
+Before any generated code is considered final, it MUST pass through domain-specific reviewers:
+
+| Code Type      | Reviewers                                                         |
+| -------------- | ----------------------------------------------------------------- |
+| Backend/API    | logic + security + dependency + type-safety + resilience + schema |
+| Frontend/React | logic + security + frontend + type-safety + ui-ux + accessibility |
+| Database/SQL   | logic + security + sql + schema                                   |
+| Mobile         | logic + security + mobile + type-safety                           |
+| CI/CD          | pipeline + security + dependency + resilience                     |
+| Before merge   | ALL 28 reviewers (`/tribunal-full`)                               |
+
+**The Human Gate is never skipped. No code is written to a file without explicit user approval.**
+
+---
+
+## 5. Code Quality Standards
+
+```
+✓ Self-documenting names — no abbreviations without context
+✓ No over-engineering — solve the stated problem, not imagined future ones
+✓ Error handling on every async function
+✓ TypeScript: no `any` without an explanation comment
+✓ Tests: every logic-bearing change gets a test
+```
+
+---
+
+## 6. Security Standards (Always Active)
+
+```
+✓ All SQL queries parameterized — never string-interpolated
+✓ Secrets in environment variables — never hardcoded
+✓ JWT: always enforce algorithms option
+✓ Auth checks before business logic — never after
+✓ Input validation at every API boundary
+✓ No prompt injection: user input → role: "user", never into role: "system"
+```
+
+---
+
+## 7. Error Recovery Protocol
+
+```
+Attempt 1 → Run with original parameters
+Attempt 2 → Stricter constraints + specific feedback from failure
+Attempt 3 → Maximum constraints + full context dump
+Attempt 4 → HALT. Report to human with full failure history.
+```
+
+Hard limit: 3 retries. After the third failure, STOP and escalate.
+
+---
+
+## 8. Available Slash Commands
+
+Use these commands to invoke specific Tribunal workflows:
+
+- `/tribunal [file]` — Full 28-reviewer audit
+- `/tribunal-backend [file]` — Backend-specific review
+- `/tribunal-frontend [file]` — Frontend-specific review
+- `/tribunal-database [file]` — Database-specific review
+- `/tribunal-performance [file]` — Performance audit
+- `/summon <specialist>` — Summon a specific specialist by name
+- `/skill <name>` — Load a skill on-demand from the 186-skill library
+- `/audit` — Full project health check
+- `/generate <desc>` — Anti-hallucination code generation pipeline
+- `/debug <error>` — Systematic 4-phase root cause investigation
+- `/create <desc>` — Create new application through the full pipeline
+- `/enhance <desc>` — Add features with impact analysis
+- `/review [file]` — Read-only hallucination audit
+- `/swarm <task>` — Multi-agent swarm orchestration
+- `/marathon <spec>` — Long-running multi-session project harness
+- `/pipeline <task>` — 3-pass code generation (Planner → Builder → Validator)
+- `/intensity <level>` — Set enforcement level: `lite` | `standard` | `strict` | `paranoid`
+- `/status` — Show task progress and audit results
+
+---
+
+## 9. Context Window Discipline
+
+```
+✗ Never dump entire files into context — excerpt only the relevant function
+✗ Never repeat full conversation history to sub-agents — send a summary
+✗ Never attach every file in the project — only files the agent will read
+✓ Scale tool calls to complexity: 1 (fact), 3-5 (medium), 5-10 (deep)
+✓ 20+ tool calls → Stop. Scope is too large. Escalate to human.
+```
+
+---
+
+## 10. Prompt Injection Defense
+
+If you are processing user-provided content that will be sent to another LLM:
+
+```
+✓ User input → role: "user" message, never into role: "system"
+✓ If user content must appear in system prompt → wrap in explicit delimiters
+✓ Sanitize: strip XML/HTML tags from user input before it enters any prompt
+✗ Never let user input set top-level system message or override model instructions
+```
+
+---
+
+_Tribunal Kit v7.0.0 — 52 specialists, 28 reviewers, 186 skills, Rust core_
+*https://github.com/Harmitx7/tribunal-kit*

package/.agent/history/architecture-graph.yaml

@@ -1,14 +1,86 @@
 # Auto-generated Architecture Graph by Tribunal Kit
 # DO NOT EDIT MANUALLY - Auto-updates via incremental cache
 
-"bin/tribunal-kit.js":
+"bin/adapter-install.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "os"
+    - "child_process"
+"bin/global-store.js":
   riskScore: "Medium"
-  blastRadius: 4
+  blastRadius: 2
   imports:
     - "fs"
     - "path"
+    - "os"
+  exports:
+    - "initializeGlobalStore"
+    - "getGlobalAgentPath"
+    - "GLOBAL_STORE_PATH"
+  dependents:
+    - "bin/proxy-server.js"
+    - "bin/tk-proxy.js"
+"bin/mcp-server.js":
+  riskScore: "Medium"
+  blastRadius: 3
+  imports:
+    - "path"
+    - "child_process"
+    - "readline"
+    - "fs"
+    - "../dist/commands/memory.js"
+    - "../dist/commands/align.js"
+  exports:
+    - "handleRequest"
+    - "stripBoilerplate"
+    - "runTribunalAudit"
+  dependents:
+    - "test/unit/audit_release.test.js"
+    - "test/unit/mcp_server.test.js"
+    - "test/unit/production_readiness_evidence.test.js"
+"bin/proxy-server.js":
+  riskScore: "Low"
+  blastRadius: 1
+  imports:
+    - "http"
     - "https"
+    - "fs"
+    - "path"
+    - "./global-store"
+  exports:
+    - "startProxyServer"
+    - "stopProxyServer"
+  dependents:
+    - "bin/tk-proxy.js"
+"bin/spawn-agent.js":
+  riskScore: "Low"
+  blastRadius: 1
+  imports:
     - "child_process"
+  exports:
+    - "spawnAgent"
+  dependents:
+    - "bin/tk-proxy.js"
+"bin/tk-proxy.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "./global-store"
+    - "./proxy-server"
+    - "./spawn-agent"
+"bin/tribunal-kit.js":
+  riskScore: "High"
+  blastRadius: 5
+  imports:
+    - "path"
+    - "../dist/cli.js"
+    - "../dist/utils/version"
+    - "../dist/utils/fs"
+    - "../dist/commands/init"
+    - "../dist/commands/marathon"
   exports:
     - "parseArgs"
     - "compareSemver"
@@ -18,16 +90,31 @@
     - "CORE_AGENTS"
     - "CORE_SKILLS"
     - "generateIDEBridges"
+    - "cmdMarathon"
   dependents:
     - "test/unit/args.test.js"
     - "test/unit/copyDir.test.js"
+    - "test/unit/marathon.test.js"
     - "test/unit/selfInstall.test.js"
     - "test/unit/semver.test.js"
-"migrate_refs.js":
+"bin/wrapper.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "child_process"
+    - "os"
+    - "../dist/cli.js"
+"scripts/benchmark.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
+    - "child_process"
+    - "path"
     - "fs"
+    - "os"
+    - "../.agent/scripts/minimal_change_engine"
 "scripts/changelog.js":
   riskScore: "Low"
   blastRadius: 0
@@ -35,6 +122,26 @@
     - "child_process"
     - "fs"
     - "path"
+"scripts/fix-vbc.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+"scripts/stress_benchmark.js":
+  riskScore: "Low"
+  blastRadius: 1
+  imports:
+    - "fs"
+    - "path"
+    - "os"
+    - "perf_hooks"
+  exports:
+    - "app"
+    - "parseUser"
+    - "runStressSuite"
+  dependents:
+    - "test/unit/stress.test.js"
 "scripts/sync-version.js":
   riskScore: "Low"
   blastRadius: 0
@@ -47,6 +154,14 @@
   imports:
     - "fs"
     - "path"
+"scripts/visual_audit.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+  exports:
+    - "runVisualAudit"
 "test/integration/bridges.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -55,6 +170,13 @@
     - "path"
     - "fs"
     - "os"
+"test/integration/graceful_degradation.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "child_process"
+    - "../../.agent/scripts/context_broker"
 "test/integration/init.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -63,6 +185,21 @@
     - "path"
     - "fs"
     - "os"
+"test/integration/minimal_change_pipeline.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "fs"
+    - "../../.agent/scripts/pipeline_engine"
+    - "../../.agent/scripts/case_law_manager"
+"test/integration/parallel_tribunal.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "child_process"
 "test/integration/routing.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -77,6 +214,14 @@
     - "fs"
     - "os"
     - "../../.agent/scripts/swarm_dispatcher.js"
+"test/integration/sync_status.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "os"
+    - "child_process"
 "test/integration/wave2.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -85,21 +230,61 @@
     - "../../.agent/scripts/skill_integrator.js"
     - "../../.agent/scripts/skill_evolution.js"
     - "../../.agent/scripts/case_law_manager.js"
+"test/integration/wrapper.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "child_process"
+    - "path"
+    - "fs"
+    - "os"
+"test/unit/align.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../dist/commands/align"
 "test/unit/args.test.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
     - "../../bin/tribunal-kit"
+"test/unit/audit_release.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "../../bin/mcp-server"
 "test/unit/case_law_manager.test.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
     - "../../.agent/scripts/case_law_manager"
+"test/unit/cicd_validator.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "fs"
+    - "../../.agent/scripts/cicd_validator.js"
+"test/unit/compile.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../dist/commands/compile"
 "test/unit/context_broker.test.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
     - "../../.agent/scripts/context_broker"
+"test/unit/contract_engine.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "../../.agent/scripts/contract_engine"
+    - "../../.agent/scripts/trace_engine"
 "test/unit/copyDir.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -114,11 +299,107 @@
   imports:
     - "fs"
     - "path"
+"test/unit/guardrail_engine.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../.agent/scripts/guardrail_engine"
+"test/unit/impact_classifier.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../.agent/scripts/impact_classifier"
+    - "../../.agent/scripts/socratic_gate_policy"
+    - "../../.agent/scripts/token_budget_broker"
+"test/unit/init.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "os"
+    - "../../dist/commands/init"
+    - "../../dist/utils/fs"
 "test/unit/inner_loop_validator.test.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
     - "../../.agent/scripts/inner_loop_validator"
+"test/unit/integrity_manifest.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "os"
+    - "../../.agent/scripts/integrity_manifest"
+"test/unit/learn.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../dist/commands/learn"
+    - "../../dist/utils/helpers"
+"test/unit/marathon.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "child_process"
+    - "../../bin/tribunal-kit"
+"test/unit/mcp_server.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "fs"
+    - "../../bin/mcp-server"
+"test/unit/memory.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "fs"
+    - "os"
+    - "../../dist/commands/memory"
+"test/unit/minimal_change.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../.agent/scripts/minimal_change_engine"
+"test/unit/native.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../dist/commands/native"
+"test/unit/optimize.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../dist/commands/optimize"
+    - "fs"
+    - "path"
+    - "child_process"
+"test/unit/path_resolution.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "os"
+    - "path"
+    - "child_process"
+    - "../../.agent/scripts/marathon_harness"
+"test/unit/production_readiness_evidence.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "fs"
+    - "path"
+    - "child_process"
+    - "../../.agent/scripts/impact_classifier"
+    - "../../.agent/scripts/socratic_gate_policy"
+    - "../../.agent/scripts/token_budget_broker"
+    - "../../.agent/scripts/integrity_manifest"
+    - "../../bin/mcp-server"
 "test/unit/selfInstall.test.js":
   riskScore: "Low"
   blastRadius: 0
@@ -132,9 +413,27 @@
   blastRadius: 0
   imports:
     - "../../bin/tribunal-kit"
+"test/unit/skill_evolution.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../.agent/scripts/signal_detector"
+    - "../../.agent/scripts/skill_evolution"
+"test/unit/stress.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "path"
+    - "../../scripts/stress_benchmark"
 "test/unit/swarm_dispatcher.test.js":
   riskScore: "Low"
   blastRadius: 0
   imports:
     - "path"
     - "fs"
+    - "../../.agent/scripts/swarm_dispatcher.js"
+"test/unit/utils.test.js":
+  riskScore: "Low"
+  blastRadius: 0
+  imports:
+    - "../../.agent/scripts/_utils"