chore(agents): sync agent configs, models, capability index; cleanup junk

- Update agent model assignments (minimax/glm -> nemotron-3-ultra, kimi-k2.7-code, qwen3.5:397b) in .kilo/agents, kilo-meta.json, kilo.jsonc, capability-index.yaml
- Update orchestrator/agent prompts (complexity fast-path, verification tests, close-loop audit)
- Add .kilo/KILO_SPEC.md (Kilo Code specification reference)
- AGENTS.md: consolidate smartadmin agent rows
- Remove screenshot-dash.cjs (unused, contained hardcoded admin token); gitignore it
- Remove empty .kilo/milestones/

.kilo/agents/orchestrator.md

@@ -1,7 +1,7 @@
 ---
 description: Main dispatcher. Routes tasks between agents based on Issue status and manages the workflow state machine. NEVER does implementation work itself — ALWAYS delegates via Task tool. bash/write=allow for routing checks and protocol logs only.
 mode: all
-model: ollama-cloud/glm-5.1
+model: ollama-cloud/deepseek-v4-flash:0731
 variant: thinking
 color: "#7C3AED"
 permission:
@@ -110,6 +110,24 @@ Before EVERY action, run this gate:
 | Run test suite | ~5,000 tokens | ~500 tokens | sdet-engineer wins |
 | Review code | ~8,000 tokens | ~500 tokens | code-skeptic wins |
 
+## Complexity Fast-Path (BEFORE pipeline)
+
+Before routing to full pipeline, evaluate trivial tasks:
+
+| Signal | Action |
+|---|---|
+| Task = typo, config value, single-line fix | Direct: orchestrator → lead-developer → done |
+| Task = single file, <50 lines change | Direct: lead-developer → code-skeptic (1 reviewer) → done |
+| Task = research question, no code change | Direct: pattern-matcher or history-miner → done |
+| Task unclear or multi-file | Full pipeline with pre-flight gate |
+
+Skip history-miner, requirement-refiner, system-analyst for trivial tasks.
+Skip consensus voting for simple tasks.
+
+TCA check MUST pass before fast-path (otherwise full pipeline).
+
+Rationale (Microsoft Azure 2026-02): "Use the lowest level of complexity that reliably meets requirements." Multi-agent orchestration adds coordination overhead, latency, cost. For 30% of tasks that are trivial, skipping 5+ agents saves ~30K tokens.
+
 ## Delegation Routing
 
 ### By Status
@@ -351,4 +369,26 @@ Instead of re-reading all comments:
 After any agent completes:
 1. `reportChange(issueNumber, report)` → posts compact change table + GNS_EVENT footer
 2. Releases file claims, updates checkpoint budget
-3. Checks acceptance criteria → auto-close if all met
+3. Checks acceptance criteria → auto-close if all met
+
+## Adaptive Scaling by Complexity
+
+When dispatching agents, the orchestrator reads the `complexity` field from requirement-refiner output and selects scaling config from `.kilo/capability-index.yaml` → `adaptive_scaling`. The complexity value maps to one of: `trivial`, `simple`, `medium`, `complex`.
+
+- **trivial/simple**: single reviewer, no consensus, low token budget
+- **medium**: 2 reviewers with specific models, up to 3 iterations
+- **complex**: consensus mode with 3 agents, dispatched via `/consensus` (Agent Forest pattern)
+
+If `complexity: complex` AND `consensus: true`, the orchestrator dispatches via the consensus workflow instead of standard sequential review. Token budget and max iterations are read from the scaling config.
+
+### Effort Budget by Complexity (Mandatory)
+
+BEFORE dispatching, classify the task and apply this budget:
+
+- **Trivial** (typo, config value, single-line fix): invoke 1 agent only (lead-developer). Skip all reviewers.
+- **Simple** (single endpoint, 1 model + migration): invoke 1-2 agents. 1 reviewer max.
+- **Medium** (multi-file feature, 3-5 files): invoke 2-4 agents. 2 reviewers, 1 iteration loop.
+- **Complex** (subsystem refactor, security audit): invoke 4-10 agents. Consensus voting, 3 iteration max.
+
+If uncertain how many subagents: start with 1, escalate only on explicit failure.
+Never spawn >10 subagents without user confirmation.