Support Claude Code Max via OAuth token

Pass CLAUDE_CODE_OAUTH_TOKEN to workspaces so they use the Max
subscription instead of pay-per-use API credits. Falls back to
ANTHROPIC_API_KEY if OAuth token not set.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.gitea/workflows/publish-workspace.yml

@@ -0,0 +1,27 @@
+name: Publish Workspace Image
+
+on:
+  push:
+    paths:
+      - 'coder/workspace.Dockerfile'
+    branches:
+      - main
+
+concurrency:
+  group: publish-workspace
+  cancel-in-progress: false
+
+jobs:
+  publish:
+    runs-on: self-hosted
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Log in to registry
+        run: echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.samson.media -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
+
+      - name: Build and push
+        run: |
+          IMAGE=registry.samson.media/coder-workspace
+          docker build -f coder/workspace.Dockerfile -t "$IMAGE:latest" .
+          docker push "$IMAGE:latest"

coder/cloudflare-worker/main.tf

@@ -76,27 +76,6 @@ data "coder_parameter" "memory" {
   }
 }
 
-data "coder_parameter" "disk_size" {
-  name         = "disk_size"
-  display_name = "Disk Size (GB)"
-  description  = "Persistent home directory size"
-  type         = "number"
-  default      = "10"
-  mutable      = false
-
-  option {
-    name  = "5 GB"
-    value = "5"
-  }
-  option {
-    name  = "10 GB"
-    value = "10"
-  }
-  option {
-    name  = "20 GB"
-    value = "20"
-  }
-}
 
 # ─── Automation Parameters ───────────────────────────────────────────────────
 
@@ -217,6 +196,15 @@ data "coder_parameter" "callback_url" {
   mutable      = false
 }
 
+data "coder_parameter" "claude_oauth_token" {
+  name         = "claude_oauth_token"
+  display_name = "Claude OAuth Token"
+  description  = "OAuth token for Claude Code Max subscription"
+  type         = "string"
+  default      = ""
+  mutable      = false
+}
+
 data "coder_parameter" "deploy_env" {
   name         = "deploy_env"
   display_name = "Deploy Environment"
@@ -375,33 +363,6 @@ resource "kubernetes_resource_quota_v1" "workspace" {
       "limits.cpu"             = "${tonumber(data.coder_parameter.cpu.value) * 1000}m"
       "requests.memory"        = "${tonumber(data.coder_parameter.memory.value) / 2}Mi"
       "limits.memory"          = "${data.coder_parameter.memory.value}Mi"
-      "requests.storage"       = "${data.coder_parameter.disk_size.value}Gi"
-      "persistentvolumeclaims" = "1"
-    }
-  }
-}
-
-# =============================================================================
-# Storage
-# =============================================================================
-
-resource "kubernetes_persistent_volume_claim_v1" "home" {
-  metadata {
-    name      = "home"
-    namespace = kubernetes_namespace_v1.workspace.metadata[0].name
-    labels    = local.labels
-  }
-
-  wait_until_bound = false
-
-  spec {
-    access_modes       = ["ReadWriteOnce"]
-    storage_class_name = "longhorn-backup"
-
-    resources {
-      requests = {
-        storage = "${data.coder_parameter.disk_size.value}Gi"
-      }
     }
   }
 }
@@ -442,8 +403,28 @@ resource "coder_agent" "main" {
     web_terminal           = true
   }
 
+  metadata {
+    display_name = "Task Status"
+    key          = "task_status"
+    script       = <<-EOS
+      if [ -f ~/task-output.log ]; then
+        if grep -q "Task completed" ~/task-output.log 2>/dev/null; then
+          echo "✅ Complete"
+        else
+          echo "⏳ Running ($(wc -l < ~/task-output.log) lines)"
+        fi
+      elif [ -n "$TASK_TYPE" ]; then
+        echo "⏳ Starting..."
+      else
+        echo "Interactive"
+      fi
+    EOS
+    interval     = 10
+  }
+
   env = {
     ANTHROPIC_API_KEY        = data.coder_parameter.anthropic_api_key.value
+    CLAUDE_CODE_OAUTH_TOKEN  = data.coder_parameter.claude_oauth_token.value
     GITHUB_TOKEN      = data.coder_external_auth.github.access_token
     GITEA_TOKEN       = data.coder_parameter.gitea_token.value
     GITEA_ORG         = data.coder_parameter.gitea_org.value
@@ -457,30 +438,19 @@ resource "coder_agent" "main" {
 
   startup_script = <<-EOT
     #!/bin/bash
+
+    # Always notify the orchestrator when done, even on failure
+    notify_complete() {
+      if [ -n "$CALLBACK_URL" ]; then
+        curl -s -X POST -H "Content-Type: application/json" \
+          -d "{\"status\":\"$1\"}" \
+          "$CALLBACK_URL" || echo "Callback failed (non-fatal)"
+      fi
+    }
+    trap 'notify_complete "failed"' ERR EXIT
+
     set -e
 
-    # --- Install Node.js 22 ---
-    if ! command -v node &> /dev/null; then
-      curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
-      sudo apt-get install -y nodejs
-    fi
-
-    # --- Install global tools ---
-    if ! command -v wrangler &> /dev/null; then
-      sudo npm install -g wrangler @anthropic-ai/claude-code
-    fi
-
-    # --- Install Playwright system dependencies ---
-    if ! dpkg -s libgbm1 &> /dev/null; then
-      sudo apt-get update
-      sudo apt-get install -y libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
-        libcups2t64 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
-        libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libasound2t64 libatspi2.0-0 \
-        || sudo apt-get install -y libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
-        libcups2 libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
-        libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libasound2 libatspi2.0-0
-    fi
-
     # --- Configure git ---
     git config --global user.name "${data.coder_workspace_owner.me.full_name}"
     git config --global user.email "${data.coder_workspace_owner.me.email}"
@@ -493,27 +463,39 @@ resource "coder_agent" "main" {
     fi
 
     # --- Clone repository ---
-    if [ -n "$REPO_CLONE_URL" ] && [ ! -d ~/project ]; then
+    if [ -n "$REPO_CLONE_URL" ]; then
       git clone "$REPO_CLONE_URL" ~/project
       cd ~/project
 
       # Switch to develop branch if it exists
       git fetch origin develop 2>/dev/null && git checkout develop 2>/dev/null || true
 
-      # Install backend deps
-      npm ci --legacy-peer-deps
+      # Lightweight stages only need the code, not a full build
+      LIGHT_STAGES="analyse architect release maintenance"
+      if echo "$LIGHT_STAGES" | grep -qw "$TASK_TYPE"; then
+        echo "Lightweight stage ($TASK_TYPE) — skipping build"
+      else
+        # Install deps if package.json exists
+        if [ -f package.json ]; then
+          npm ci --legacy-peer-deps || npm ci
+        fi
 
-      # Install frontend deps
+        # Install frontend deps if present
+        if [ -f frontend/package.json ]; then
           cd frontend && npm ci && cd ..
+          npm run build:frontend 2>/dev/null || true
+        fi
 
-      # Build frontend (required — vitest fails without frontend/dist)
-      npm run build:frontend
-
-      # Install Playwright Chromium
+        # Install Playwright if needed
+        if grep -q "playwright" package.json 2>/dev/null; then
           npx playwright install chromium
+        fi
 
-      # Apply local migrations
-      npm run db:migrate:local
+        # Apply local migrations if script exists
+        if npm run --silent db:migrate:local 2>/dev/null; then
+          echo "Local migrations applied"
+        fi
+      fi
     fi
 
     # --- Automated task execution ---
@@ -525,18 +507,21 @@ resource "coder_agent" "main" {
         ARGS="$DEPLOY_ENV"
       fi
 
-      # Run Claude Code in non-interactive mode
-      claude --print --dangerously-skip-permissions "/project:$TASK_TYPE $ARGS" 2>&1 | tee ~/task-output.log
-
-      echo "Task completed. Output saved to ~/task-output.log"
-
-      # Notify orchestrator that the task is done
-      if [ -n "$CALLBACK_URL" ]; then
-        curl -s -X POST -H "Content-Type: application/json" \
-          -d '{"status":"complete"}' \
-          "$CALLBACK_URL" || echo "Callback failed (non-fatal)"
+      # Read the slash command .md file, strip YAML frontmatter, substitute $ARGUMENTS
+      CMD_FILE=".claude/commands/$TASK_TYPE.md"
+      if [ ! -f "$CMD_FILE" ]; then
+        echo "ERROR: Command file not found: $CMD_FILE"
+        exit 1
       fi
+      PROMPT=$(sed '1{/^---$/!q}; 1,/^---$/d' "$CMD_FILE" | sed "s/\\\$ARGUMENTS/$ARGS/g")
+
+      # Run Claude Code in non-interactive mode with tool access
+      claude -p --dangerously-skip-permissions --verbose "$PROMPT"
     fi
+
+    # Success — override the trap
+    trap - ERR EXIT
+    notify_complete "complete"
   EOT
 }
 
@@ -585,42 +570,9 @@ resource "kubernetes_deployment_v1" "workspace" {
           name = kubernetes_secret_v1.registry.metadata[0].name
         }
 
-        init_container {
-          name  = "fix-permissions"
-          image = "busybox:latest"
-
-          command = ["sh", "-c", <<-EOC
-            if [ ! -d /home/coder/project ]; then
-              mkdir -p /home/coder/project
-            fi
-            chown -R 1000:1000 /home/coder
-          EOC
-          ]
-
-          volume_mount {
-            name       = "home"
-            mount_path = "/home/coder"
-          }
-
-          resources {
-            requests = {
-              cpu    = "5m"
-              memory = "8Mi"
-            }
-            limits = {
-              cpu    = "50m"
-              memory = "32Mi"
-            }
-          }
-
-          security_context {
-            run_as_user = 0
-          }
-        }
-
         container {
           name  = "coder-agent"
-          image = "codercom/enterprise-base:ubuntu-arm64"
+          image = "registry.samson.media/coder-workspace:latest"
 
           command = ["sh", "-c", coder_agent.main.init_script]
 
@@ -634,6 +586,11 @@ resource "kubernetes_deployment_v1" "workspace" {
             value = data.coder_parameter.anthropic_api_key.value
           }
 
+          env {
+            name  = "CLAUDE_CODE_OAUTH_TOKEN"
+            value = data.coder_parameter.claude_oauth_token.value
+          }
+
           env {
             name  = "GITHUB_TOKEN"
             value = data.coder_external_auth.github.access_token
@@ -703,9 +660,7 @@ resource "kubernetes_deployment_v1" "workspace" {
 
         volume {
           name = "home"
-          persistent_volume_claim {
-            claim_name = kubernetes_persistent_volume_claim_v1.home.metadata[0].name
-          }
+          empty_dir {}
         }
       }
     }

coder/workspace.Dockerfile

@@ -0,0 +1,23 @@
+FROM codercom/enterprise-base:latest
+
+USER root
+
+# Node.js 22
+RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
+    && apt-get install -y nodejs \
+    && rm -rf /var/lib/apt/lists/*
+
+# Global npm tools
+RUN npm install -g wrangler @anthropic-ai/claude-code
+
+# Playwright system dependencies (both Ubuntu 24.04 and 22.04 package names)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 \
+    libdrm2 libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 \
+    libxrandr2 libgbm1 libpango-1.0-0 libcairo2 libatspi2.0-0 \
+    jq netcat-openbsd \
+    && (apt-get install -y libcups2t64 libasound2t64 2>/dev/null \
+        || apt-get install -y libcups2 libasound2 2>/dev/null) \
+    && rm -rf /var/lib/apt/lists/*
+
+USER coder

src/config.ts

@@ -11,8 +11,10 @@ export interface Config {
   giteaDevToken: string;
   /** Gitea API token for the review bot account */
   giteaReviewToken: string;
-  /** Anthropic API key passed to Claude Code in workspaces */
+  /** Anthropic API key passed to Claude Code in workspaces (fallback) */
   anthropicApiKey: string;
+  /** Claude Code OAuth token for Max subscription (preferred) */
+  claudeOauthToken: string;
   /** Username of the dev bot (to filter out self-replies) */
   botDevUsername: string;
   /** Username of the review bot (to filter out self-replies) */
@@ -41,7 +43,8 @@ export function loadConfig(): Config {
     coderTemplateId: required("CODER_TEMPLATE_ID"),
     giteaDevToken: required("GITEA_DEV_TOKEN"),
     giteaReviewToken: required("GITEA_REVIEW_TOKEN"),
-    anthropicApiKey: required("ANTHROPIC_API_KEY"),
+    anthropicApiKey: process.env.ANTHROPIC_API_KEY || "",
+    claudeOauthToken: process.env.CLAUDE_OAUTH_TOKEN || "",
     botDevUsername: process.env.BOT_DEV_USERNAME || "claude-dev",
     botReviewUsername: process.env.BOT_REVIEW_USERNAME || "claude-review",
     giteaUrl: process.env.GITEA_URL || "https://gitea.samson.media",

src/index.ts

@@ -84,6 +84,11 @@ if (maintenanceRepos.length > 0) {
 // Start
 // ---------------------------------------------------------------------------
 
+// Reconcile queue state with Coder before accepting traffic
+queue.reconcile().catch((err) =>
+  console.error("[startup] reconcile failed:", err),
+);
+
 serve({ fetch: app.fetch, port: config.port }, (info) => {
   console.log(`SDLC Orchestrator listening on :${info.port} (concurrency: ${concurrency})`);
 });

src/queue.ts

@@ -35,6 +35,34 @@ export class TaskQueue {
     this.concurrency = concurrency;
   }
 
+  /**
+   * Reconcile in-memory state with Coder on startup.
+   * Re-adopts any running workspaces so callbacks and dedup work correctly.
+   */
+  async reconcile(): Promise<void> {
+    const workspaces = await this.coder.listWorkspaces();
+    const runningStatuses = ["starting", "running", "started"];
+
+    for (const ws of workspaces) {
+      if (!runningStatuses.includes(ws.latestBuildStatus)) continue;
+
+      // Only adopt workspaces that match our naming pattern: {taskType}-{repo}-{issue}
+      const parts = ws.name.match(/^(.+?)-(.+?)-(\d+)$/);
+      if (!parts) continue;
+
+      this.active.set(ws.name, {
+        workspaceId: ws.id,
+        workspaceName: ws.name,
+        startedAt: new Date(), // approximate — we don't know the real start time
+      });
+      console.log(`[queue] reconciled: adopted workspace "${ws.name}" (status: ${ws.latestBuildStatus})`);
+    }
+
+    if (this.active.size > 0) {
+      console.log(`[queue] reconcile complete: ${this.active.size} active workspace(s) adopted`);
+    }
+  }
+
   /** Build a dedup key for a task. */
   static key(task: TaskRequest): string {
     return `${task.taskType}-${task.giteaRepo}-${task.issueNumber}`;

src/services/coder.ts

@@ -7,6 +7,7 @@ export class CoderClient {
   private token: string;
   private templateId: string;
   private anthropicApiKey: string;
+  private claudeOauthToken: string;
   private callbackUrl: string;
 
   constructor(config: Config) {
@@ -14,6 +15,7 @@ export class CoderClient {
     this.token = config.coderToken;
     this.templateId = config.coderTemplateId;
     this.anthropicApiKey = config.anthropicApiKey;
+    this.claudeOauthToken = config.claudeOauthToken;
     this.callbackUrl = config.callbackUrl;
   }
 
@@ -31,6 +33,7 @@ export class CoderClient {
         { name: "gitea_org", value: task.giteaOrg },
         { name: "gitea_repo", value: task.giteaRepo },
         { name: "anthropic_api_key", value: this.anthropicApiKey },
+        { name: "claude_oauth_token", value: this.claudeOauthToken },
         { name: "callback_url", value: `${this.callbackUrl}/webhook/task-complete/${name}` },
         ...(task.deployEnv
           ? [{ name: "deploy_env", value: task.deployEnv }]
@@ -50,6 +53,32 @@ export class CoderClient {
       },
     );
 
+    // Handle 409 conflict — workspace with this name already exists.
+    // This can happen if the orchestrator restarted and lost in-memory state.
+    if (res.status === 409) {
+      const existing = await this.findWorkspaceByName(name);
+      if (!existing) {
+        throw new Error(`Coder 409 but workspace "${name}" not found — possible race condition`);
+      }
+
+      const stoppedStatuses = ["stopped", "failed", "canceled", "deleted"];
+      if (stoppedStatuses.includes(existing.latestBuildStatus)) {
+        // Workspace is done — safe to replace
+        console.log(
+          `[coder] workspace "${name}" exists but ${existing.latestBuildStatus} — deleting and retrying`,
+        );
+        await this.deleteWorkspace(existing.id);
+        await new Promise((resolve) => setTimeout(resolve, 5000));
+        return this.createWorkspace(task);
+      }
+
+      // Workspace is still running — adopt it, don't kill it
+      console.log(
+        `[coder] workspace "${name}" is still ${existing.latestBuildStatus} — adopting existing workspace`,
+      );
+      return { id: existing.id, name: existing.name };
+    }
+
     if (!res.ok) {
       const text = await res.text();
       throw new Error(`Coder API error ${res.status}: ${text}`);
@@ -95,7 +124,42 @@ export class CoderClient {
     }
   }
 
-  async findWorkspaceByName(name: string): Promise<{ id: string } | null> {
+  /**
+   * List all workspaces owned by the authenticated user.
+   * Used at startup to reconcile in-memory state with Coder.
+   */
+  async listWorkspaces(): Promise<
+    Array<{ id: string; name: string; latestBuildStatus: string }>
+  > {
+    const res = await fetch(
+      `${this.baseUrl}/api/v2/workspaces?q=owner:me`,
+      {
+        headers: { "Coder-Session-Token": this.token },
+      },
+    );
+
+    if (!res.ok) return [];
+
+    const data = (await res.json()) as {
+      workspaces: Array<{
+        id: string;
+        name: string;
+        latest_build: { status: string };
+      }>;
+    };
+    return (data.workspaces ?? []).map((w) => ({
+      id: w.id,
+      name: w.name,
+      latestBuildStatus: w.latest_build?.status ?? "unknown",
+    }));
+  }
+
+  async findWorkspaceByName(name: string): Promise<{
+    id: string;
+    name: string;
+    createdAt: string;
+    latestBuildStatus: string;
+  } | null> {
     const res = await fetch(
       `${this.baseUrl}/api/v2/workspaces?q=name:${encodeURIComponent(name)}`,
       {
@@ -107,8 +171,21 @@ export class CoderClient {
 
     if (!res.ok) return null;
 
-    const data = (await res.json()) as { workspaces: Array<{ id: string; name: string }> };
+    const data = (await res.json()) as {
+      workspaces: Array<{
+        id: string;
+        name: string;
+        created_at: string;
+        latest_build: { status: string };
+      }>;
+    };
     const match = data.workspaces?.find((w) => w.name === name);
-    return match ? { id: match.id } : null;
+    if (!match) return null;
+    return {
+      id: match.id,
+      name: match.name,
+      createdAt: match.created_at,
+      latestBuildStatus: match.latest_build?.status ?? "unknown",
+    };
   }
 }