feat: use 1M context model for implement nodes in bundled workflows (#1018)

* feat: use 1M context model for implement nodes in bundled workflows (#1016)

Large codebases fill the 200k context window during implementation, triggering
SDK auto-compaction which loses context detail and slows execution. Setting
claude-opus-4-6[1m] on implementation nodes gives 5x more room before compaction.

Changes:
- Set model: claude-opus-4-6[1m] on implement nodes in 8 bundled workflows
- Fix loop nodes to respect per-node model overrides (previously only used
  workflow-level model)
- Review/classify/report nodes stay on sonnet/haiku for cost efficiency

Fixes #1016

* fix: resolve per-node provider/model overrides for loop nodes

Move provider and model resolution for loop nodes to the call site,
matching the pattern used by command/prompt/bash nodes. This fixes:

- Loop nodes now respect per-node `provider` overrides (previously ignored)
- Model/provider compatibility is validated before execution
- JSDoc on buildLoopNodeOptions accurately describes the function

.archon/workflows/defaults/archon-adversarial-dev.yaml

@@ -115,6 +115,7 @@ nodes:
   - id: adversarial-sprint
     depends_on: [init-workspace]
     idle_timeout: 600000
+    model: claude-opus-4-6[1m]
     loop:
       prompt: |
         # Adversarial Development — Sprint Loop

.archon/workflows/defaults/archon-feature-development.yaml

@@ -8,6 +8,7 @@ description: |
 nodes:
   - id: implement
     command: archon-implement
+    model: claude-opus-4-6[1m]
 
   - id: create-pr
     command: archon-create-pr

.archon/workflows/defaults/archon-fix-github-issue.yaml

@@ -133,7 +133,7 @@ nodes:
     command: archon-fix-issue
     depends_on: [bridge-artifacts]
     context: fresh
-    model: opus
+    model: claude-opus-4-6[1m]
 
   # ═══════════════════════════════════════════════════════════════
   # PHASE 5: VALIDATE

.archon/workflows/defaults/archon-idea-to-pr.yaml

@@ -52,6 +52,7 @@ nodes:
     command: archon-implement-tasks
     depends_on: [confirm-plan]
     context: fresh
+    model: claude-opus-4-6[1m]
 
   # ═══════════════════════════════════════════════════════════════════
   # PHASE 4: VALIDATE

.archon/workflows/defaults/archon-piv-loop.yaml

@@ -415,6 +415,7 @@ nodes:
   - id: implement
     depends_on: [implement-setup]
     idle_timeout: 600000
+    model: claude-opus-4-6[1m]
     loop:
       prompt: |
         # PIV Loop — Implementation Agent

.archon/workflows/defaults/archon-plan-to-pr.yaml

@@ -42,6 +42,7 @@ nodes:
     command: archon-implement-tasks
     depends_on: [confirm-plan]
     context: fresh
+    model: claude-opus-4-6[1m]
 
   # ═══════════════════════════════════════════════════════════════════
   # PHASE 4: VALIDATE

.archon/workflows/defaults/archon-ralph-dag.yaml

@@ -189,6 +189,7 @@ nodes:
   - id: implement
     depends_on: [validate-prd]
     idle_timeout: 600000
+    model: claude-opus-4-6[1m]
     loop:
       prompt: |
         # Ralph Agent — Autonomous Story Implementation

.archon/workflows/defaults/archon-refactor-safely.yaml

@@ -207,6 +207,7 @@ nodes:
   # ═══════════════════════════════════════════════════════════════
 
   - id: execute-refactor
+    model: claude-opus-4-6[1m]
     prompt: |
       You are executing a refactoring plan with strict safety guardrails.
 

packages/workflows/src/dag-executor.ts

@@ -1438,8 +1438,8 @@ async function executeBashNode(
 }
 
 /**
- * Build WorkflowAssistantOptions from workflow-level config.
- * Loop nodes use workflow-level provider/model only; per-node overrides are not supported.
+ * Build WorkflowAssistantOptions from resolved provider, model, and config.
+ * Caller is responsible for resolving per-node overrides before passing model.
  */
 function buildLoopNodeOptions(
   provider: 'claude' | 'codex',
@@ -2373,6 +2373,34 @@ export async function executeDagWorkflow(
 
           // 3b. Loop node dispatch — manages its own AI sessions and iteration
           if (isLoopNode(node)) {
+            // Resolve per-node provider/model overrides (same logic as other node types)
+            let loopProvider: 'claude' | 'codex';
+            if (node.provider) {
+              loopProvider = node.provider;
+            } else if (node.model && isClaudeModel(node.model)) {
+              loopProvider = 'claude';
+            } else if (node.model) {
+              loopProvider = 'codex';
+            } else {
+              loopProvider = workflowProvider;
+            }
+            const loopModel =
+              node.model ??
+              (loopProvider === workflowProvider
+                ? workflowModel
+                : config.assistants[loopProvider]?.model);
+
+            if (!isModelCompatible(loopProvider, loopModel)) {
+              return {
+                nodeId: node.id,
+                output: {
+                  state: 'failed' as const,
+                  output: '',
+                  error: `Node '${node.id}': model "${loopModel ?? 'default'}" is not compatible with provider "${loopProvider}"`,
+                },
+              };
+            }
+
             const output = await executeLoopNode(
               deps,
               platform,
@@ -2380,8 +2408,8 @@ export async function executeDagWorkflow(
               cwd,
               workflowRun,
               node,
-              workflowProvider,
-              workflowModel,
+              loopProvider,
+              loopModel,
               artifactsDir,
               logDir,
               baseBranch,