feat(registry/coder/modules/agentapi): add state persistence

AgentAPI can save and restore conversation state across workspace restarts.
The base module exports env vars (AGENTAPI_STATE_FILE, AGENTAPI_SAVE_STATE,
AGENTAPI_LOAD_STATE, AGENTAPI_PID_FILE) that the binary reads directly.
No consumer module start scripts need changes.

New variables:
- enable_state_persistence (bool, default true)
- state_file_path (string, defaults to $HOME/<module_dir_name>/state.json)
- pid_file_path (string, defaults to $HOME/<module_dir_name>/agentapi.pid)

State persistence requires agentapi >= v0.12.0. A shared version_at_least
function in scripts/lib.sh gates both the env var exports in main.sh and
SIGUSR1 in the shutdown script. The version is queried from the real binary
(agentapi --version) rather than the Terraform variable, so it works
correctly when install_agentapi is false.

Shutdown script now performs a three-phase shutdown:
1. SIGUSR1 to trigger state save (gated on version + persistence enabled)
2. Log snapshot capture (existing behavior, now fault-tolerant via subshell)
3. SIGTERM for graceful termination with wait loop

Also bumps agentapi module version to 2.2.0.

Refs: internal#1257, internal#1256, registry#696

Author: mafredri

registry/coder/modules/agentapi/README.md

@@ -16,7 +16,7 @@ The AgentAPI module is a building block for modules that need to run an AgentAPI
 ```tf
 module "agentapi" {
   source  = "registry.coder.com/coder/agentapi/coder"
-  version = "2.1.1"
+  version = "2.2.0"
 
   agent_id             = var.agent_id
   web_app_slug         = local.app_slug
@@ -62,6 +62,33 @@ module "agentapi" {
 }
 ```
 
+## State Persistence
+
+AgentAPI can save and restore conversation state across workspace restarts.
+This is enabled by default and requires agentapi binary >= v0.12.0.
+
+State and PID files are stored in `$HOME/<module_dir_name>/` alongside other
+module files (e.g. `$HOME/.claude-module/state.json`).
+
+To disable:
+
+```tf
+module "agentapi" {
+  # ... other config
+  enable_state_persistence = false
+}
+```
+
+To override file paths:
+
+```tf
+module "agentapi" {
+  # ... other config
+  state_file_path = "/custom/path/state.json"
+  pid_file_path   = "/custom/path/agentapi.pid"
+}
+```
+
 ## For module developers
 
 For a complete example of how to use this module, see the [Goose module](https://github.com/coder/registry/blob/main/registry/coder/modules/goose/main.tf).

registry/coder/modules/agentapi/agentapi.tftest.hcl

@@ -0,0 +1,108 @@
+mock_provider "coder" {}
+
+variables {
+  agent_id             = "test-agent"
+  web_app_icon         = "/icon/test.svg"
+  web_app_display_name = "Test"
+  web_app_slug         = "test"
+  cli_app_display_name = "Test CLI"
+  cli_app_slug         = "test-cli"
+  start_script         = "echo test"
+  module_dir_name      = ".test-module"
+}
+
+run "default_values" {
+  command = plan
+
+  assert {
+    condition     = var.enable_state_persistence == true
+    error_message = "enable_state_persistence should default to true"
+  }
+
+  assert {
+    condition     = var.state_file_path == ""
+    error_message = "state_file_path should default to empty string"
+  }
+
+  assert {
+    condition     = var.pid_file_path == ""
+    error_message = "pid_file_path should default to empty string"
+  }
+
+  # Verify start script contains state persistence ARG_ vars.
+  assert {
+    condition     = can(regex("ARG_ENABLE_STATE_PERSISTENCE", coder_script.agentapi.script))
+    error_message = "start script should contain ARG_ENABLE_STATE_PERSISTENCE"
+  }
+
+  assert {
+    condition     = can(regex("ARG_STATE_FILE_PATH", coder_script.agentapi.script))
+    error_message = "start script should contain ARG_STATE_FILE_PATH"
+  }
+
+  assert {
+    condition     = can(regex("ARG_PID_FILE_PATH", coder_script.agentapi.script))
+    error_message = "start script should contain ARG_PID_FILE_PATH"
+  }
+
+  # Verify shutdown script contains PID-related ARG_ vars.
+  assert {
+    condition     = can(regex("ARG_PID_FILE_PATH", coder_script.agentapi_shutdown.script))
+    error_message = "shutdown script should contain ARG_PID_FILE_PATH"
+  }
+
+  assert {
+    condition     = can(regex("ARG_MODULE_DIR_NAME", coder_script.agentapi_shutdown.script))
+    error_message = "shutdown script should contain ARG_MODULE_DIR_NAME"
+  }
+
+  assert {
+    condition     = can(regex("ARG_ENABLE_STATE_PERSISTENCE", coder_script.agentapi_shutdown.script))
+    error_message = "shutdown script should contain ARG_ENABLE_STATE_PERSISTENCE"
+  }
+}
+
+run "state_persistence_disabled" {
+  command = plan
+
+  variables {
+    enable_state_persistence = false
+  }
+
+  assert {
+    condition     = var.enable_state_persistence == false
+    error_message = "enable_state_persistence should be false"
+  }
+
+  # Even when disabled, the ARG_ vars should still be in the script
+  # (the shell script handles the conditional logic).
+  assert {
+    condition     = can(regex("ARG_ENABLE_STATE_PERSISTENCE='false'", coder_script.agentapi.script))
+    error_message = "start script should contain ARG_ENABLE_STATE_PERSISTENCE='false'"
+  }
+}
+
+run "custom_paths" {
+  command = plan
+
+  variables {
+    state_file_path = "/custom/state.json"
+    pid_file_path   = "/custom/agentapi.pid"
+  }
+
+  assert {
+    condition     = can(regex("/custom/state.json", coder_script.agentapi.script))
+    error_message = "start script should contain custom state_file_path"
+  }
+
+  assert {
+    condition     = can(regex("/custom/agentapi.pid", coder_script.agentapi.script))
+    error_message = "start script should contain custom pid_file_path"
+  }
+
+  # Verify custom paths also appear in shutdown script.
+  assert {
+    condition     = can(regex("/custom/agentapi.pid", coder_script.agentapi_shutdown.script))
+    error_message = "shutdown script should contain custom pid_file_path"
+  }
+}

registry/coder/modules/agentapi/main.test.ts

@@ -258,11 +258,71 @@ describe("agentapi", async () => {
     expect(agentApiStartLog).toContain("AGENTAPI_ALLOWED_HOSTS: *");
   });
 
+  test("state-persistence-disabled", async () => {
+    const { id } = await setup({
+      moduleVariables: {
+        enable_state_persistence: "false",
+      },
+    });
+    await execModuleScript(id);
+    await expectAgentAPIStarted(id);
+    const mockLog = await readFileContainer(
+      id,
+      "/home/coder/agentapi-mock.log",
+    );
+    // PID file should always be exported
+    expect(mockLog).toContain("AGENTAPI_PID_FILE:");
+    // State vars should NOT be present when disabled
+    expect(mockLog).not.toContain("AGENTAPI_STATE_FILE:");
+    expect(mockLog).not.toContain("AGENTAPI_SAVE_STATE:");
+    expect(mockLog).not.toContain("AGENTAPI_LOAD_STATE:");
+  });
+
+  test("state-persistence-custom-paths", async () => {
+    const { id } = await setup({
+      moduleVariables: {
+        state_file_path: "/home/coder/custom/state.json",
+        pid_file_path: "/home/coder/custom/agentapi.pid",
+      },
+    });
+    await execModuleScript(id);
+    await expectAgentAPIStarted(id);
+    const mockLog = await readFileContainer(
+      id,
+      "/home/coder/agentapi-mock.log",
+    );
+    expect(mockLog).toContain(
+      "AGENTAPI_STATE_FILE: /home/coder/custom/state.json",
+    );
+    expect(mockLog).toContain(
+      "AGENTAPI_PID_FILE: /home/coder/custom/agentapi.pid",
+    );
+  });
+
+  test("state-persistence-default-paths", async () => {
+    const { id } = await setup();
+    await execModuleScript(id);
+    await expectAgentAPIStarted(id);
+    const mockLog = await readFileContainer(
+      id,
+      "/home/coder/agentapi-mock.log",
+    );
+    expect(mockLog).toContain(
+      `AGENTAPI_STATE_FILE: /home/coder/${moduleDirName}/state.json`,
+    );
+    expect(mockLog).toContain(
+      `AGENTAPI_PID_FILE: /home/coder/${moduleDirName}/agentapi.pid`,
+    );
+    expect(mockLog).toContain("AGENTAPI_SAVE_STATE: true");
+    expect(mockLog).toContain("AGENTAPI_LOAD_STATE: true");
+  });
+
   describe("shutdown script", async () => {
     const setupMocks = async (
       containerId: string,
       agentapiPreset: string,
       httpCode: number = 204,
+      pidFilePath: string = "",
     ) => {
       const agentapiMock = await loadTestFile(
         import.meta.dir,
@@ -285,10 +345,11 @@ describe("agentapi", async () => {
         content: coderMock,
       });
 
+      const pidFileEnv = pidFilePath ? `AGENTAPI_PID_FILE=${pidFilePath}` : "";
       await execContainer(containerId, [
         "bash",
         "-c",
-        `PRESET=${agentapiPreset} nohup node /usr/local/bin/mock-agentapi 3284 > /tmp/mock-agentapi.log 2>&1 &`,
+        `PRESET=${agentapiPreset} ${pidFileEnv} nohup node /usr/local/bin/mock-agentapi 3284 > /tmp/mock-agentapi.log 2>&1 &`,
       ]);
 
       await execContainer(containerId, [
@@ -303,12 +364,25 @@ describe("agentapi", async () => {
     const runShutdownScript = async (
       containerId: string,
       taskId: string = "test-task",
+      pidFilePath: string = "",
+      enableStatePersistence: string = "true",
     ) => {
       const shutdownScript = await loadTestFile(
         import.meta.dir,
         "../scripts/agentapi-shutdown.sh",
       );
 
+      const libScript = await loadTestFile(
+        import.meta.dir,
+        "../scripts/lib.sh",
+      );
+
+      await writeExecutable({
+        containerId,
+        filePath: "/tmp/agentapi-lib.sh",
+        content: libScript,
+      });
+
       await writeExecutable({
         containerId,
         filePath: "/tmp/shutdown.sh",
@@ -318,7 +392,7 @@ describe("agentapi", async () => {
       return await execContainer(containerId, [
         "bash",
         "-c",
-        `ARG_TASK_ID=${taskId} ARG_AGENTAPI_PORT=3284 CODER_AGENT_URL=http://localhost:18080 CODER_AGENT_TOKEN=test-token /tmp/shutdown.sh`,
+        `ARG_TASK_ID=${taskId} ARG_AGENTAPI_PORT=3284 ARG_PID_FILE_PATH=${pidFilePath} ARG_ENABLE_STATE_PERSISTENCE=${enableStatePersistence} CODER_AGENT_URL=http://localhost:18080 CODER_AGENT_TOKEN=test-token /tmp/shutdown.sh`,
       ]);
     };
 
@@ -409,5 +483,126 @@ describe("agentapi", async () => {
         "Log snapshot endpoint not supported by this Coder version",
       );
     });
+
+    test("sends SIGUSR1 before shutdown", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      const pidFile = "/tmp/agentapi-test.pid";
+      await setupMocks(id, "normal", 204, pidFile);
+      const result = await runShutdownScript(id, "test-task", pidFile, "true");
+
+      expect(result.exitCode).toBe(0);
+      expect(result.stdout).toContain("Sending SIGUSR1 to AgentAPI");
+
+      const sigusr1Log = await readFileContainer(id, "/tmp/sigusr1-received");
+      expect(sigusr1Log).toContain("SIGUSR1 received");
+    });
+
+    test("handles missing PID file gracefully", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      await setupMocks(id, "normal");
+      // Pass a non-existent PID file path
+      const result = await runShutdownScript(
+        id,
+        "test-task",
+        "/tmp/nonexistent.pid",
+      );
+
+      expect(result.exitCode).toBe(0);
+      expect(result.stdout).toContain("Shutdown complete");
+    });
+
+    test("sends SIGTERM even when snapshot fails", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      const pidFile = "/tmp/agentapi-test.pid";
+      // HTTP 500 will cause snapshot to fail
+      await setupMocks(id, "normal", 500, pidFile);
+      const result = await runShutdownScript(id, "test-task", pidFile);
+
+      expect(result.exitCode).toBe(0);
+      expect(result.stdout).toContain(
+        "Log snapshot capture failed, continuing shutdown",
+      );
+      expect(result.stdout).toContain("Sending SIGTERM to AgentAPI");
+    });
+
+    test("resolves default PID path from MODULE_DIR_NAME", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      // Start mock with PID file at the module_dir_name default location.
+      const defaultPidPath = `/home/coder/${moduleDirName}/agentapi.pid`;
+      await setupMocks(id, "normal", 204, defaultPidPath);
+      // Don't pass pidFilePath - let shutdown script compute it from MODULE_DIR_NAME.
+      const shutdownScript = await loadTestFile(
+        import.meta.dir,
+        "../scripts/agentapi-shutdown.sh",
+      );
+      const libScript = await loadTestFile(
+        import.meta.dir,
+        "../scripts/lib.sh",
+      );
+      await writeExecutable({
+        containerId: id,
+        filePath: "/tmp/agentapi-lib.sh",
+        content: libScript,
+      });
+      await writeExecutable({
+        containerId: id,
+        filePath: "/tmp/shutdown.sh",
+        content: shutdownScript,
+      });
+      const result = await execContainer(id, [
+        "bash",
+        "-c",
+        `ARG_TASK_ID=test-task ARG_AGENTAPI_PORT=3284 ARG_MODULE_DIR_NAME=${moduleDirName} ARG_ENABLE_STATE_PERSISTENCE=true CODER_AGENT_URL=http://localhost:18080 CODER_AGENT_TOKEN=test-token /tmp/shutdown.sh`,
+      ]);
+
+      expect(result.exitCode).toBe(0);
+      expect(result.stdout).toContain("Sending SIGUSR1 to AgentAPI");
+      expect(result.stdout).toContain("Sending SIGTERM to AgentAPI");
+    });
+
+    test("skips SIGUSR1 when no PID file available", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      await setupMocks(id, "normal", 204);
+      // No pidFilePath and no MODULE_DIR_NAME, so no PID file can be resolved.
+      const result = await runShutdownScript(id, "test-task", "", "false");
+
+      expect(result.exitCode).toBe(0);
+      // Should not send SIGUSR1 or SIGTERM (no PID to signal).
+      expect(result.stdout).not.toContain("Sending SIGUSR1");
+      expect(result.stdout).not.toContain("Sending SIGTERM");
+      expect(result.stdout).toContain("Shutdown complete");
+    });
+
+    test("skips SIGUSR1 when state persistence disabled", async () => {
+      const { id } = await setup({
+        moduleVariables: {},
+        skipAgentAPIMock: true,
+      });
+      const pidFile = "/tmp/agentapi-test.pid";
+      await setupMocks(id, "normal", 204, pidFile);
+      // PID file exists but state persistence is disabled.
+      const result = await runShutdownScript(id, "test-task", pidFile, "false");
+
+      expect(result.exitCode).toBe(0);
+      // Should NOT send SIGUSR1 (persistence disabled).
+      expect(result.stdout).not.toContain("Sending SIGUSR1");
+      // Should still send SIGTERM (graceful shutdown always happens).
+      expect(result.stdout).toContain("Sending SIGTERM to AgentAPI");
+    });
   });
 });