feat: add per-workflow model assignment configuration

.archeflow/config.yaml

@@ -26,6 +26,30 @@ memory:
   max_lessons: 10
   decay_after_runs: 10
 
+# Models — default and per-archetype/per-workflow model selection.
+# ArcheFlow reads this to assign models to agents. The default applies unless overridden.
+models:
+  default: sonnet
+  # Per-archetype overrides (uncomment to customize):
+  # archetypes:
+  #   explorer: haiku         # Cheap model for research/exploration
+  #   creator: sonnet         # Creative tasks need stronger model
+  #   maker: sonnet           # Implementation needs full capability
+  #   guardian: sonnet        # Security review — don't skimp
+  #   skeptic: haiku          # Assumption checking is analytical
+  #   sage: haiku             # Quality review can use cheaper model
+  #   trickster: sonnet       # Adversarial testing benefits from stronger model
+  # Per-workflow overrides (uncomment to customize):
+  # workflows:
+  #   fast:
+  #     default: haiku        # Fast workflow uses cheaper models by default
+  #     archetypes:
+  #       guardian: sonnet     # Except Guardian — always needs strong model
+  #   standard:
+  #     default: sonnet
+  #   thorough:
+  #     default: sonnet
+
 # Progress
 progress:
   enabled: true

skills/orchestration/SKILL.md

@@ -89,6 +89,12 @@ Events are optional — if the events dir doesn't exist, skip logging. Never let
 
 ---
 
+## Model Configuration
+
+Model assignment per archetype and workflow is configured in `.archeflow/config.yaml` under the `models:` section. The `archeflow:run` skill (section 0c) handles resolution with fallback chain: per-workflow per-archetype > per-workflow default > per-archetype > global default. When spawning agents manually, read the config to select the appropriate model.
+
+---
+
 ## Step 1: Plan Phase
 
 Spawn agents sequentially — Creator needs Explorer's findings.

skills/run/SKILL.md

@@ -121,6 +121,49 @@ ${MEMORY_LESSONS}"
 fi
 ```
 
+#### 0c. Model Configuration
+
+Read model assignment from `.archeflow/config.yaml` and resolve the model for each archetype based on the current workflow. Per-workflow overrides take precedence over per-archetype overrides, which take precedence over the default.
+
+```bash
+CONFIG=".archeflow/config.yaml"
+
+# Read default model
+DEFAULT_MODEL=$(grep -A1 '^models:' "$CONFIG" 2>/dev/null | grep 'default:' | sed 's/.*default:\s*//' | tr -d '"' | head -1)
+DEFAULT_MODEL="${DEFAULT_MODEL:-sonnet}"
+
+# Resolve model for a given archetype and workflow
+# Usage: resolve_model <archetype> <workflow>
+resolve_model() {
+  local arch="$1" wf="$2" model=""
+
+  # Check per-workflow per-archetype override
+  model=$(sed -n "/workflows:/,\$p" "$CONFIG" 2>/dev/null \
+    | sed -n "/${wf}:/,/^    [a-z]/p" \
+    | grep -A1 "archetypes:" | grep "${arch}:" \
+    | sed "s/.*${arch}:\s*//" | tr -d '"' | head -1)
+  [[ -n "$model" ]] && echo "$model" && return
+
+  # Check per-workflow default
+  model=$(sed -n "/workflows:/,\$p" "$CONFIG" 2>/dev/null \
+    | sed -n "/${wf}:/,/^    [a-z]/p" \
+    | grep 'default:' | sed 's/.*default:\s*//' | tr -d '"' | head -1)
+  [[ -n "$model" ]] && echo "$model" && return
+
+  # Check per-archetype override
+  model=$(sed -n "/^  archetypes:/,/^  [a-z]/p" "$CONFIG" 2>/dev/null \
+    | grep "${arch}:" | sed "s/.*${arch}:\s*//" | tr -d '"' | head -1)
+  [[ -n "$model" ]] && echo "$model" && return
+
+  # Fall back to default
+  echo "$DEFAULT_MODEL"
+}
+
+# Example: EXPLORER_MODEL=$(resolve_model explorer "$WORKFLOW")
+```
+
+Use `resolve_model` when spawning each agent to pass the correct model. The resolved model can be included in the `agent.start` event data for cost tracking.
+
 ---
 
 ### 1. Plan Phase