diff --git a/checkpoint.json b/checkpoint.json
index 909337e13..4143643b0 100644
--- a/checkpoint.json
+++ b/checkpoint.json
@@ -1,11 +1,13 @@
 {
-  "timestamp": "2026-03-20T01:26:52.199740Z",
-  "current_node": "toolchain",
+  "timestamp": "2026-03-20T01:28:04.088707Z",
+  "current_node": "preflight_compile",
   "completed_nodes": [
     "start",
-    "toolchain"
+    "toolchain",
+    "preflight_compile"
   ],
   "node_retries": {
+    "preflight_compile": 1,
     "start": 1,
     "toolchain": 1
   },
@@ -13,15 +15,17 @@
     "graph.model_stylesheet": "\n            * { backend: api; model: claude-opus-4-6;}\n        ",
     "internal.retry_count.toolchain": 1,
     "command.stderr": "",
-    "command.output": "cargo 1.94.0 (85eff7c80 2026-01-15)\n",
+    "command.output": "",
     "failure_class": "",
+    "thread.toolchain.current_node": "preflight_compile",
+    "internal.retry_count.preflight_compile": 1,
     "internal.node_visit_count": 1,
-    "internal.thread_id": "start",
+    "internal.thread_id": "toolchain",
     "internal.retry_count.start": 1,
     "internal.fidelity": "compact",
     "graph.goal": "# Plan: Map `reasoning_effort` to Anthropic `output_config.effort`\n\n## Context\n\nThe Anthropic Messages API now supports `output_config: { effort: \"low\" | \"medium\" | \"high\" | \"max\" }` as the recommended way to control thinking depth for Claude Opus 4.6 and Sonnet 4.6 (replacing deprecated `budget_tokens`). Fabro's unified `Request` already carries `reasoning_effort: Option<String>` and workflow nodes default it to `\"high\"`, but the Anthropic provider silently drops this field — it never appears in the API request. The OpenAI provider correctly maps it to `reasoning: { effort }`, but the Anthropic provider has no equivalent.\n\n## Single file to modify\n\n`lib/crates/fabro-llm/src/providers/anthropic.rs`\n\n## Step 1: Add failing tests\n\nAdd tests at the end of the `#[cfg(test)] mod tests` block (before line 2043's `}`). These tests reference a new `output_config` field on `ApiRequest` that doesn't exist yet, so they won't compile until Step 2.\n\n**Test A** — `build_api_request_maps_reasoning_effort_to_output_config`: Build a `Request` with `reasoning_effort: Some(\"medium\")`, call `build_api_request`, assert `api_request.output_config == Some(json!({\"effort\": \"medium\"}))`. Pattern: follows existing `build_api_request_omits_whitespace_only_system_prompt` test (line 1592).\n\n**Test B** — `build_api_request_omits_output_config_when_no_reasoning_effort`: Same but with `reasoning_effort: None`, assert `api_request.output_config.is_none()`.\n\n## Step 2: Add `output_config` field to `ApiRequest` struct\n\nAt line 108 (after `thinking`), add:\n\n```rust\n#[serde(skip_serializing_if = \"Option::is_none\")]\noutput_config: Option<serde_json::Value>,\n```\n\nUpdate every existing `ApiRequest` construction to include `output_config: None`:\n- line 1566 (serialization test)\n- line 1962 (merge_provider_options test)\n- line 1993 (merge_provider_options test)\n\nAt this point: code compiles, Test B passes, **Test A fails** (proving the bug exists).\n\n## Step 3: Map `reasoning_effort` → `output_config` in `build_api_request`\n\nAt line 1073 (next to the `thinking` extraction), add:\n\n```rust\nlet output_config = request\n    .reasoning_effort\n    .as_ref()\n    .map(|effort| serde_json::json!({\"effort\": effort}));\n```\n\nAdd `output_config,` to the `ApiRequest` construction at line 1075.\n\nThis mirrors the OpenAI provider pattern at `openai.rs:385-388`.\n\nAll tests pass.\n\n## Verification\n\n```sh\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_maps_reasoning_effort\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_omits_output_config\ncargo test -p fabro-llm  # all provider tests still pass\ncargo clippy --workspace -- -D warnings\n```\n",
-    "current_node": "toolchain",
-    "current.preamble": "Goal: # Plan: Map `reasoning_effort` to Anthropic `output_config.effort`\n\n## Context\n\nThe Anthropic Messages API now supports `output_config: { effort: \"low\" | \"medium\" | \"high\" | \"max\" }` as the recommended way to control thinking depth for Claude Opus 4.6 and Sonnet 4.6 (replacing deprecated `budget_tokens`). Fabro's unified `Request` already carries `reasoning_effort: Option<String>` and workflow nodes default it to `\"high\"`, but the Anthropic provider silently drops this field — it never appears in the API request. The OpenAI provider correctly maps it to `reasoning: { effort }`, but the Anthropic provider has no equivalent.\n\n## Single file to modify\n\n`lib/crates/fabro-llm/src/providers/anthropic.rs`\n\n## Step 1: Add failing tests\n\nAdd tests at the end of the `#[cfg(test)] mod tests` block (before line 2043's `}`). These tests reference a new `output_config` field on `ApiRequest` that doesn't exist yet, so they won't compile until Step 2.\n\n**Test A** — `build_api_request_maps_reasoning_effort_to_output_config`: Build a `Request` with `reasoning_effort: Some(\"medium\")`, call `build_api_request`, assert `api_request.output_config == Some(json!({\"effort\": \"medium\"}))`. Pattern: follows existing `build_api_request_omits_whitespace_only_system_prompt` test (line 1592).\n\n**Test B** — `build_api_request_omits_output_config_when_no_reasoning_effort`: Same but with `reasoning_effort: None`, assert `api_request.output_config.is_none()`.\n\n## Step 2: Add `output_config` field to `ApiRequest` struct\n\nAt line 108 (after `thinking`), add:\n\n```rust\n#[serde(skip_serializing_if = \"Option::is_none\")]\noutput_config: Option<serde_json::Value>,\n```\n\nUpdate every existing `ApiRequest` construction to include `output_config: None`:\n- line 1566 (serialization test)\n- line 1962 (merge_provider_options test)\n- line 1993 (merge_provider_options test)\n\nAt this point: code compiles, Test B passes, **Test A fails** (proving the bug exists).\n\n## Step 3: Map `reasoning_effort` → `output_config` in `build_api_request`\n\nAt line 1073 (next to the `thinking` extraction), add:\n\n```rust\nlet output_config = request\n    .reasoning_effort\n    .as_ref()\n    .map(|effort| serde_json::json!({\"effort\": effort}));\n```\n\nAdd `output_config,` to the `ApiRequest` construction at line 1075.\n\nThis mirrors the OpenAI provider pattern at `openai.rs:385-388`.\n\nAll tests pass.\n\n## Verification\n\n```sh\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_maps_reasoning_effort\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_omits_output_config\ncargo test -p fabro-llm  # all provider tests still pass\ncargo clippy --workspace -- -D warnings\n```\n\n",
+    "current_node": "preflight_compile",
+    "current.preamble": "Goal: # Plan: Map `reasoning_effort` to Anthropic `output_config.effort`\n\n## Context\n\nThe Anthropic Messages API now supports `output_config: { effort: \"low\" | \"medium\" | \"high\" | \"max\" }` as the recommended way to control thinking depth for Claude Opus 4.6 and Sonnet 4.6 (replacing deprecated `budget_tokens`). Fabro's unified `Request` already carries `reasoning_effort: Option<String>` and workflow nodes default it to `\"high\"`, but the Anthropic provider silently drops this field — it never appears in the API request. The OpenAI provider correctly maps it to `reasoning: { effort }`, but the Anthropic provider has no equivalent.\n\n## Single file to modify\n\n`lib/crates/fabro-llm/src/providers/anthropic.rs`\n\n## Step 1: Add failing tests\n\nAdd tests at the end of the `#[cfg(test)] mod tests` block (before line 2043's `}`). These tests reference a new `output_config` field on `ApiRequest` that doesn't exist yet, so they won't compile until Step 2.\n\n**Test A** — `build_api_request_maps_reasoning_effort_to_output_config`: Build a `Request` with `reasoning_effort: Some(\"medium\")`, call `build_api_request`, assert `api_request.output_config == Some(json!({\"effort\": \"medium\"}))`. Pattern: follows existing `build_api_request_omits_whitespace_only_system_prompt` test (line 1592).\n\n**Test B** — `build_api_request_omits_output_config_when_no_reasoning_effort`: Same but with `reasoning_effort: None`, assert `api_request.output_config.is_none()`.\n\n## Step 2: Add `output_config` field to `ApiRequest` struct\n\nAt line 108 (after `thinking`), add:\n\n```rust\n#[serde(skip_serializing_if = \"Option::is_none\")]\noutput_config: Option<serde_json::Value>,\n```\n\nUpdate every existing `ApiRequest` construction to include `output_config: None`:\n- line 1566 (serialization test)\n- line 1962 (merge_provider_options test)\n- line 1993 (merge_provider_options test)\n\nAt this point: code compiles, Test B passes, **Test A fails** (proving the bug exists).\n\n## Step 3: Map `reasoning_effort` → `output_config` in `build_api_request`\n\nAt line 1073 (next to the `thinking` extraction), add:\n\n```rust\nlet output_config = request\n    .reasoning_effort\n    .as_ref()\n    .map(|effort| serde_json::json!({\"effort\": effort}));\n```\n\nAdd `output_config,` to the `ApiRequest` construction at line 1075.\n\nThis mirrors the OpenAI provider pattern at `openai.rs:385-388`.\n\nAll tests pass.\n\n## Verification\n\n```sh\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_maps_reasoning_effort\ncargo test -p fabro-llm -- anthropic::tests::build_api_request_omits_output_config\ncargo test -p fabro-llm  # all provider tests still pass\ncargo clippy --workspace -- -D warnings\n```\n\n\n## Completed stages\n- **toolchain**: success\n  - Script: `command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1`\n  - Stdout:\n    ```\n    cargo 1.94.0 (85eff7c80 2026-01-15)\n    ```\n  - Stderr: (empty)\n",
     "outcome": "success",
     "thread.start.current_node": "toolchain",
     "failure_signature": "",
@@ -42,10 +46,20 @@
       },
       "notes": "Script completed: command -v cargo >/dev/null || { curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && sudo ln -sf $HOME/.cargo/bin/* /usr/local/bin/; }; cargo --version 2>&1",
       "duration_ms": 57
+    },
+    "preflight_compile": {
+      "status": "success",
+      "context_updates": {
+        "command.stderr": "",
+        "command.output": ""
+      },
+      "notes": "Script completed: cargo check -q --workspace 2>&1",
+      "duration_ms": 69458
     }
   },
-  "next_node_id": "preflight_compile",
+  "next_node_id": "preflight_lint",
   "node_visits": {
+    "preflight_compile": 1,
     "start": 1,
     "toolchain": 1
   }
diff --git a/nodes/preflight_compile/script_invocation.json b/nodes/preflight_compile/script_invocation.json
new file mode 100644
index 000000000..ccbef36c7
--- /dev/null
+++ b/nodes/preflight_compile/script_invocation.json
@@ -0,0 +1,5 @@
+{
+  "command": "cargo check -q --workspace 2>&1",
+  "language": "shell",
+  "timeout_ms": null
+}
\ No newline at end of file
diff --git a/nodes/preflight_compile/script_timing.json b/nodes/preflight_compile/script_timing.json
new file mode 100644
index 000000000..7a1364527
--- /dev/null
+++ b/nodes/preflight_compile/script_timing.json
@@ -0,0 +1,5 @@
+{
+  "duration_ms": 69456,
+  "exit_code": 0,
+  "timed_out": false
+}
\ No newline at end of file
diff --git a/nodes/preflight_compile/status.json b/nodes/preflight_compile/status.json
new file mode 100644
index 000000000..149b24301
--- /dev/null
+++ b/nodes/preflight_compile/status.json
@@ -0,0 +1,6 @@
+{
+  "status": "success",
+  "notes": "Script completed: cargo check -q --workspace 2>&1",
+  "failure_reason": null,
+  "timestamp": "2026-03-20T01:28:04.088059+00:00"
+}
\ No newline at end of file