fix: inline --json-schema file paths so structured output works on CLI 2.1.160 (closes #3 )

The docs recommend the file-path form (`--json-schema /path/to/schema.json`) as primary, but the default-pinned Claude CLI 2.1.160 only accepts an inline JSON string. Passing a path makes the CLI exit 0 with empty output, so the action's fail-loud branch trips on every run. Resolve the value before spawning the CLI: a file-path schema is read in-process and passed inline (validated + compacted), while an already-inline schema is left untouched. Because the value is handed to spawn() as an argv element (never through a shell), a schema with `$ref`/`$defs` round-trips intact. Unreadable files and invalid JSON now fail with a clear error instead of the CLI's silent empty output. Docs (README, example workflow, action.yml) are corrected to explain that the file-path form is auto-inlined and works on the default CLI. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Merge pull request 'feat: add claude_args passthrough + structured_output output (#1 )' (#2 ) from feat/claude-args-structured-output into gitea
2026-06-03 10:45:40 +10:00 · 2026-06-02 14:33:57 +02:00 · 2026-06-02 22:22:51 +10:00
11 changed files with 682 additions and 99 deletions
@@ -67,6 +67,7 @@ jobs:
 | `use_vertex`          | Use Google Vertex AI with OIDC authentication instead of direct Anthropic API                                                | No       | `false`                |
 | `allowed_tools`       | Additional tools for Claude to use (the base GitHub tools will always be included)                                           | No       | ""                     |
 | `disallowed_tools`    | Tools that Claude should never use                                                                                           | No       | ""                     |
+| `claude_args`         | Additional arguments forwarded verbatim to the Claude CLI (e.g. `--json-schema /path/to/schema.json`). See [Structured output](#structured-output). Requires a Claude CLI new enough to support the flags used. | No       | ""                     |
 | `custom_instructions` | Additional custom instructions to include in the prompt for Claude                                                           | No       | ""                     |
 | `assignee_trigger`    | The assignee username that triggers the action (e.g. @claude). Only used for issue and PR assignment                                | No       | -                      |
 | `trigger_phrase`      | The trigger phrase to look for in comments, issue/PR bodies, and issue titles                                                | No       | `@claude`              |
@@ -77,6 +78,53 @@ jobs:

 > **Note**: This action is currently in beta. Features and APIs may change as we continue to improve the integration.

+## Outputs
+
+| Output              | Description                                                                                                                              |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
+| `execution_file`    | Path to the JSON file containing the Claude Code execution log                                                                           |
+| `structured_output` | JSON string of the schema-validated result, set only when `--json-schema` is passed via `claude_args`. Parse with `fromJSON()` or `jq`.  |
+| `branch_name`       | The branch created by Claude Code for this execution (issue flows)                                                                       |
+
+## Structured output
+
+`claude_args` forwards arbitrary flags straight to the Claude CLI. The primary use case is asking the model for a **schema-validated result** instead of having the agent write it to a file. When you pass `--json-schema`, the action surfaces the validated object as the `structured_output` action output (no agent-written file required).
+
+```yaml
+- uses: ryan/claude-code-gitea-action@gitea
+  id: review
+  with:
+    gitea_token: ${{ secrets.GITHUB_TOKEN }}
+    anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+    direct_prompt: "Review this PR and return a verdict that matches the schema."
+    # Prefer the file-path form — it has no spaces or `$` for the shell
+    # tokenizer to mangle, so a schema containing $ref/$defs round-trips safely.
+    claude_args: --json-schema ${{ github.workspace }}/.gitea/review-schema.json
+
+- name: Use the verdict
+  shell: bash
+  run: |
+    echo '${{ steps.review.outputs.structured_output }}' | jq -r '.decision'
+```
+
+Notes:
+
+- **Use the file-path form** (`--json-schema /path/to/schema.json`). The action reads the file and passes its contents to the CLI **inline**, so the file-path form works even on CLIs whose `--json-schema` only accepts an inline string (including the default-pinned `2.1.160`). The path is preferred because it has no spaces or `$` for the shell to mangle, so a schema with `$ref`/`$defs` round-trips intact. An inline schema also works if single-quoted (`--json-schema '{"type":"object"}'`) so the shell treats it as one literal token and does not expand `$` (e.g. `$ref`).
+- If the `--json-schema` value is a path that can't be read, or the file isn't valid JSON, the run **fails loudly** with a clear error (rather than the CLI silently emitting empty output).
+- If `--json-schema` is supplied but the model returns no structured result, the run **fails loudly** rather than emitting an empty output.
+- **Claude CLI version.** The default-installed CLI (`2.1.160`) supports `--json-schema`, and the action inlines a file-path schema for you — so the file-path form is not version-sensitive. If you pin `path_to_claude_code_executable` (e.g. a pre-baked runner image), that baked CLI must still be new enough to support the `--json-schema` flag itself — bump it independently. See [Version pins](#version-pins).
+
+### Version pins
+
+This fork runs Claude via the vendored `base-action/` (invoked directly, not the external `anthropics/claude-code-base-action`). The moving pieces:
+
+| Component                              | Where it's pinned                                  | Current value |
+| -------------------------------------- | -------------------------------------------------- | ------------- |
+| Claude CLI (default install)           | `action.yml` → "Install Claude" step               | `2.1.160`     |
+| Claude CLI (pre-baked runner image)    | the runner image's Dockerfile (`CLAUDE_CLI_VERSION`) | set by you  |
+
+If you consume this action through a pre-baked runner image that sets `path_to_claude_code_executable`, the action's own install step is skipped — so enabling `--json-schema` there requires **rebuilding that runner image** with a `--json-schema`-capable CLI and restarting the runner. That is outside this repository.
+
 ## Gitea Configuration

 This action has been enhanced to work with Gitea installations. The main differences from GitHub are:
@@ -81,6 +81,10 @@ inputs:
    description: "Enable automatic fallback to specified model when default model is overloaded"
    required: false
    default: ""
+  claude_args:
+    description: "Additional arguments to pass directly to the Claude CLI, forwarded verbatim (e.g. '--json-schema /path/to/schema.json' to get schema-validated output via the structured_output output; a file path given to --json-schema is read and inlined automatically, so it works on the default-installed CLI). Requires a Claude CLI new enough to support the flags used (see README)."
+    required: false
+    default: ""

  # Auth configuration
  anthropic_api_key:
@@ -131,6 +135,9 @@ outputs:
  execution_file:
    description: "Path to the Claude Code execution output file"
    value: ${{ steps.claude-code.outputs.execution_file }}
+  structured_output:
+    description: "JSON string of the schema-validated result when --json-schema is provided in claude_args (parse with fromJSON() or jq)"
+    value: ${{ steps.claude-code.outputs.structured_output }}
  branch_name:
    description: "The branch created by Claude Code for this execution"
    value: ${{ steps.prepare.outputs.CLAUDE_BRANCH }}
@@ -177,10 +184,13 @@ runs:
      if: steps.prepare.outputs.contains_trigger == 'true'
      shell: bash
      run: |
-        # Install Claude Code if no custom executable is provided
+        # Install Claude Code if no custom executable is provided.
+        # Version must be new enough to support any flags passed via claude_args
+        # (e.g. --json-schema). Runner images that bake their own CLI via
+        # path_to_claude_code_executable must bump their pin independently.
        if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then
          echo "Installing Claude Code..."
-          curl -fsSL https://claude.ai/install.sh | bash -s 1.0.117
+          curl -fsSL https://claude.ai/install.sh | bash -s 2.1.160
          echo "$HOME/.local/bin" >> "$GITHUB_PATH"
        else
          echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}"
@@ -189,51 +199,41 @@ runs:
          echo "$CLAUDE_DIR" >> "$GITHUB_PATH"
        fi
    # TODO pass claude_code_executable as input and use it here
-
    - name: Run Claude Code
      id: claude-code
      if: steps.prepare.outputs.contains_trigger == 'true'
-      uses: anthropics/claude-code-base-action@v0.0.63
-      with:
-        prompt_file: /tmp/claude-prompts/claude-prompt.txt
-        allowed_tools: ${{ env.ALLOWED_TOOLS }}
-        disallowed_tools: ${{ env.DISALLOWED_TOOLS }}
-        max_turns: ${{ inputs.max_turns }}
-        timeout_minutes: ${{ inputs.timeout_minutes }}
-        model: ${{ inputs.model || inputs.anthropic_model }}
-        mcp_config: ${{ steps.prepare.outputs.mcp_config }}
-        use_bedrock: ${{ inputs.use_bedrock }}
-        use_vertex: ${{ inputs.use_vertex }}
-        anthropic_api_key: ${{ inputs.anthropic_api_key }}
-        claude_code_oauth_token: ${{ inputs.claude_code_oauth_token }}
-        settings: ${{ inputs.settings }}
-        system_prompt: ${{ inputs.system_prompt }}
-        append_system_prompt: ${{ inputs.append_system_prompt }}
-        claude_env: ${{ inputs.claude_env }}
-        fallback_model: ${{ inputs.fallback_model }}
-        use_node_cache: ${{ inputs.use_node_cache }}
+      shell: bash
+      run: |
+        bun run ${{ github.action_path }}/base-action/src/index.ts
      env:
-        # Core configuration
-        PROMPT_FILE: /tmp/claude-prompts/claude-prompt.txt
-        ALLOWED_TOOLS: ${{ env.ALLOWED_TOOLS }}
-        DISALLOWED_TOOLS: ${{ env.DISALLOWED_TOOLS }}
-        TIMEOUT_MINUTES: ${{ inputs.timeout_minutes }}
-        MODEL: ${{ inputs.model || inputs.anthropic_model }}
+        # Core configuration. The vendored base-action reads these INPUT_* env
+        # vars directly (see base-action/src/index.ts), so we map them here
+        # instead of delegating to the external claude-code-base-action. This
+        # lets us forward claude_args and surface structured_output while
+        # keeping the Gitea adaptations this fork relies on.
+        CLAUDE_CODE_ACTION: "1"
+        INPUT_PROMPT_FILE: /tmp/claude-prompts/claude-prompt.txt
+        INPUT_ALLOWED_TOOLS: ${{ env.ALLOWED_TOOLS }}
+        INPUT_DISALLOWED_TOOLS: ${{ env.DISALLOWED_TOOLS }}
+        INPUT_MAX_TURNS: ${{ inputs.max_turns }}
+        INPUT_TIMEOUT_MINUTES: ${{ inputs.timeout_minutes }}
+        INPUT_MCP_CONFIG: ${{ steps.prepare.outputs.mcp_config }}
+        INPUT_SETTINGS: ${{ inputs.settings }}
+        INPUT_SYSTEM_PROMPT: ${{ inputs.system_prompt }}
+        INPUT_APPEND_SYSTEM_PROMPT: ${{ inputs.append_system_prompt }}
+        INPUT_CLAUDE_ENV: ${{ inputs.claude_env }}
+        INPUT_FALLBACK_MODEL: ${{ inputs.fallback_model }}
+        INPUT_CLAUDE_ARGS: ${{ inputs.claude_args }}
        ANTHROPIC_MODEL: ${{ inputs.model || inputs.anthropic_model }}
-        MCP_CONFIG: ${{ steps.prepare.outputs.mcp_config }}
-        USE_BEDROCK: ${{ inputs.use_bedrock }}
-        USE_VERTEX: ${{ inputs.use_vertex }}
+
+        # Provider selection (base-action validate-env reads the '1'/'' form).
+        CLAUDE_CODE_USE_BEDROCK: ${{ inputs.use_bedrock == 'true' && '1' || '' }}
+        CLAUDE_CODE_USE_VERTEX: ${{ inputs.use_vertex == 'true' && '1' || '' }}
+
+        # Auth configuration
        ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}
        CLAUDE_CODE_OAUTH_TOKEN: ${{ inputs.claude_code_oauth_token }}

-        # New settings support
-        SETTINGS: ${{ inputs.settings }}
-        SYSTEM_PROMPT: ${{ inputs.system_prompt }}
-        APPEND_SYSTEM_PROMPT: ${{ inputs.append_system_prompt }}
-        CLAUDE_ENV: ${{ inputs.claude_env }}
-        FALLBACK_MODEL: ${{ inputs.fallback_model }}
-        USE_NODE_CACHE: ${{ inputs.use_node_cache }}
-
        # GitHub token for repository access
        GITHUB_TOKEN: ${{ steps.prepare.outputs.GITHUB_TOKEN }}
        GITEA_API_URL: ${{ env.GITHUB_SERVER_URL }}
@@ -242,7 +242,7 @@ runs:
        CLAUDE_GIT_NAME: ${{ inputs.claude_git_name }}
        CLAUDE_GIT_EMAIL: ${{ inputs.claude_git_email }}

-        # Provider configuration (for future cloud provider support)
+        # Provider configuration (for cloud provider support)
        ANTHROPIC_BASE_URL: ${{ env.ANTHROPIC_BASE_URL }}
        AWS_REGION: ${{ env.AWS_REGION }}
        AWS_ACCESS_KEY_ID: ${{ env.AWS_ACCESS_KEY_ID }}
@@ -55,6 +55,10 @@ inputs:
    description: "Custom environment variables to pass to Claude Code execution (YAML multiline format)"
    required: false
    default: ""
+  claude_args:
+    description: "Additional arguments to pass directly to the Claude CLI (e.g. '--json-schema /path/to/schema.json'). Forwarded verbatim after the action-managed arguments."
+    required: false
+    default: ""

  # Action settings
  timeout_minutes:
@@ -92,6 +96,9 @@ outputs:
  execution_file:
    description: "Path to the JSON file containing Claude Code execution log"
    value: ${{ steps.run_claude.outputs.execution_file }}
+  structured_output:
+    description: "JSON string of the schema-validated result when --json-schema is provided in claude_args (parse with fromJSON() or jq)"
+    value: ${{ steps.run_claude.outputs.structured_output }}

 runs:
  using: "composite"
@@ -143,6 +150,7 @@ runs:
        INPUT_TIMEOUT_MINUTES: ${{ inputs.timeout_minutes }}
        INPUT_CLAUDE_ENV: ${{ inputs.claude_env }}
        INPUT_FALLBACK_MODEL: ${{ inputs.fallback_model }}
+        INPUT_CLAUDE_ARGS: ${{ inputs.claude_args }}

        # Provider configuration
        ANTHROPIC_API_KEY: ${{ inputs.anthropic_api_key }}
@@ -1,14 +1,17 @@
 {
  "lockfileVersion": 1,
+  "configVersion": 0,
  "workspaces": {
    "": {
      "name": "@anthropic-ai/claude-code-base-action",
      "dependencies": {
        "@actions/core": "^1.10.1",
+        "shell-quote": "^1.8.1",
      },
      "devDependencies": {
        "@types/bun": "^1.2.12",
        "@types/node": "^20.0.0",
+        "@types/shell-quote": "^1.7.5",
        "prettier": "3.5.3",
        "typescript": "^5.8.3",
      },
@@ -31,12 +34,16 @@

    "@types/react": ["@types/react@19.1.8", "", { "dependencies": { "csstype": "^3.0.2" } }, "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g=="],

+    "@types/shell-quote": ["@types/shell-quote@1.7.5", "", {}, "sha512-+UE8GAGRPbJVQDdxi16dgadcBfQ+KG2vgZhV1+3A1XmHbmwcdwhCUwIdy+d3pAGrbvgRoVSjeI9vOWyq376Yzw=="],
+
    "bun-types": ["bun-types@1.2.19", "", { "dependencies": { "@types/node": "*" }, "peerDependencies": { "@types/react": "^19" } }, "sha512-uAOTaZSPuYsWIXRpj7o56Let0g/wjihKCkeRqUBhlLVM/Bt+Fj9xTo+LhC1OV1XDaGkz4hNC80et5xgy+9KTHQ=="],

    "csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="],

    "prettier": ["prettier@3.5.3", "", { "bin": { "prettier": "bin/prettier.cjs" } }, "sha512-QQtaxnoDJeAkDvDKWCLiwIXkTgRhwYDEQCghU9Z6q03iyek/rxRh/2lC3HB7P8sWT2xC/y5JDctPLBIGzHKbhw=="],

+    "shell-quote": ["shell-quote@1.8.4", "", {}, "sha512-VsC6n6vz1ihYYyZZwX7YZSF5l5x36ca17OC+a69h94YqB7X6XLwf+5MOgynYir2SLFUbl8gIYvBo8K8RoNQ6bQ=="],
+
    "tunnel": ["tunnel@0.0.6", "", {}, "sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg=="],

    "typescript": ["typescript@5.8.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ=="],
@@ -10,11 +10,13 @@
    "typecheck": "tsc --noEmit"
  },
  "dependencies": {
-    "@actions/core": "^1.10.1"
+    "@actions/core": "^1.10.1",
+    "shell-quote": "^1.8.1"
  },
  "devDependencies": {
    "@types/bun": "^1.2.12",
    "@types/node": "^20.0.0",
+    "@types/shell-quote": "^1.7.5",
    "prettier": "3.5.3",
    "typescript": "^5.8.3"
  }
@@ -27,6 +27,7 @@ async function run() {
      claudeEnv: process.env.INPUT_CLAUDE_ENV,
      fallbackModel: process.env.INPUT_FALLBACK_MODEL,
      model: process.env.ANTHROPIC_MODEL,
+      claudeArgs: process.env.INPUT_CLAUDE_ARGS,
    });
  } catch (error) {
    core.setFailed(`Action failed with error: ${error}`);
@@ -2,8 +2,9 @@ import * as core from "@actions/core";
 import { exec } from "child_process";
 import { promisify } from "util";
 import { unlink, writeFile, stat } from "fs/promises";
-import { createWriteStream } from "fs";
+import { createWriteStream, readFileSync } from "fs";
 import { spawn } from "child_process";
+import { parse as parseShellArgs } from "shell-quote";

 const execAsync = promisify(exec);

@@ -22,14 +23,159 @@ export type ClaudeOptions = {
  fallbackModel?: string;
  timeoutMinutes?: string;
  model?: string;
+  // Raw, additional arguments forwarded verbatim to the Claude CLI. Mirrors the
+  // upstream v1 `claude_args` passthrough so downstream workflows can use newer
+  // CLI flags (e.g. `--json-schema`) without this fork enumerating each one.
+  claudeArgs?: string;
 };

 type PreparedConfig = {
  claudeArgs: string[];
  promptPath: string;
  env: Record<string, string>;
+  // True when the forwarded claude_args request schema-validated output
+  // (`--json-schema`), which means we must surface `structured_output`.
+  hasJsonSchema: boolean;
 };

+/**
+ * Strip full comment lines (first non-whitespace char is `#`) from a shell
+ * argument string before tokenizing. Inline `#` inside a quoted value is left
+ * untouched — shell-quote handles quoting. Ported from upstream
+ * claude-code-base-action's claude_args parsing.
+ */
+function stripShellComments(input: string): string {
+  return input
+    .split("\n")
+    .filter((line) => !line.trim().startsWith("#"))
+    .join("\n");
+}
+
+/**
+ * Tokenize the raw `claude_args` string into individual CLI argument tokens
+ * using shell-quote, so quoted values (e.g. `--json-schema '{"$ref": ...}'`)
+ * survive as a single token. Non-string tokens (shell operators/globs) are
+ * dropped, matching upstream behavior. Returns [] for empty/whitespace input.
+ */
+export function parseClaudeArgs(claudeArgs?: string): string[] {
+  if (!claudeArgs?.trim()) {
+    return [];
+  }
+  return parseShellArgs(stripShellComments(claudeArgs)).filter(
+    (arg): arg is string => typeof arg === "string",
+  );
+}
+
+/**
+ * Resolve a single `--json-schema` value. The Claude CLI's `--json-schema`
+ * flag accepts an *inline* JSON string. The documented (and recommended) form
+ * passes a file *path* so a schema containing `$ref`/`$defs` survives shell
+ * tokenization without `$` expansion — but CLIs that only accept inline schemas
+ * (including the default-pinned 2.1.160) silently ignore a path and emit no
+ * structured output. To make the file-path form work everywhere, we read the
+ * file in-process and return its contents as compact inline JSON; because this
+ * value is handed to the CLI as an argv element (never through a shell), the
+ * `$` characters are safe. Values that are already inline JSON (the trimmed
+ * value starts with `{` or `[`) are passed through untouched.
+ */
+function resolveJsonSchemaValue(value: string): string {
+  const trimmed = value.trim();
+  if (trimmed.startsWith("{") || trimmed.startsWith("[")) {
+    return value; // Already an inline JSON schema — leave exactly as supplied.
+  }
+
+  let contents: string;
+  try {
+    contents = readFileSync(value, "utf8");
+  } catch (e) {
+    throw new Error(
+      `Failed to read --json-schema file "${value}": ${
+        e instanceof Error ? e.message : String(e)
+      }`,
+    );
+  }
+
+  try {
+    return JSON.stringify(JSON.parse(contents));
+  } catch (e) {
+    throw new Error(
+      `--json-schema file "${value}" is not valid JSON: ${
+        e instanceof Error ? e.message : String(e)
+      }`,
+    );
+  }
+}
+
+/**
+ * Walk tokenized CLI args and inline any file-path value supplied to
+ * `--json-schema` (both the `--json-schema <path>` and `--json-schema=<path>`
+ * forms). See {@link resolveJsonSchemaValue} for why. Non-schema args and
+ * already-inline schemas are returned unchanged.
+ */
+export function inlineJsonSchemaArgs(args: string[]): string[] {
+  const result: string[] = [];
+  const PREFIX = "--json-schema=";
+
+  for (let i = 0; i < args.length; i++) {
+    const arg = args[i];
+    if (arg === undefined) {
+      continue;
+    }
+
+    if (arg === "--json-schema") {
+      result.push(arg);
+      const value = args[i + 1];
+      if (value !== undefined) {
+        result.push(resolveJsonSchemaValue(value));
+        i++; // Consume the value token we just inlined.
+      }
+      continue;
+    }
+
+    if (arg.startsWith(PREFIX)) {
+      const value = arg.slice(PREFIX.length);
+      result.push(`${PREFIX}${resolveJsonSchemaValue(value)}`);
+      continue;
+    }
+
+    result.push(arg);
+  }
+
+  return result;
+}
+
+/**
+ * Locate the schema-validated result emitted by the Claude CLI. With
+ * `--output-format stream-json` the CLI prints one JSON object per line and the
+ * final `{"type":"result", ...}` event carries a `structured_output` field when
+ * `--json-schema` was supplied. We scan from the end (the result is last) and
+ * return the first `structured_output` we find. Returns undefined when absent.
+ */
+export function extractStructuredOutput(output: string): unknown {
+  const lines = output.split("\n");
+  for (let i = lines.length - 1; i >= 0; i--) {
+    const line = lines[i]?.trim();
+    if (!line) {
+      continue;
+    }
+    let parsed: unknown;
+    try {
+      parsed = JSON.parse(line);
+    } catch {
+      continue; // Not a JSON line (e.g. human-readable log output)
+    }
+    if (
+      parsed &&
+      typeof parsed === "object" &&
+      "structured_output" in parsed &&
+      (parsed as { structured_output?: unknown }).structured_output != null
+    ) {
+      return (parsed as { structured_output: unknown }).structured_output;
+    }
+  }
+  return undefined;
+}
+
 function parseCustomEnvVars(claudeEnv?: string): Record<string, string> {
  if (!claudeEnv || claudeEnv.trim() === "") {
    return {};
@@ -107,6 +253,18 @@ export function prepareRunConfig(
    }
  }

+  // Forward any additional raw CLI arguments verbatim, after the args this
+  // action manages. Empty/unset claude_args leaves the arg list byte-identical
+  // to before this feature, preserving behavior for existing callers. A
+  // file-path value passed to `--json-schema` is inlined here so it works on
+  // CLIs that only accept inline schemas (e.g. the default-pinned 2.1.160).
+  const extraArgs = inlineJsonSchemaArgs(parseClaudeArgs(options.claudeArgs));
+  claudeArgs.push(...extraArgs);
+
+  const hasJsonSchema = extraArgs.some(
+    (arg) => arg === "--json-schema" || arg.startsWith("--json-schema="),
+  );
+
  // Parse custom environment variables
  const customEnv = parseCustomEnvVars(options.claudeEnv);

@@ -114,6 +272,7 @@ export function prepareRunConfig(
    claudeArgs,
    promptPath,
    env: customEnv,
+    hasJsonSchema,
  };
 }

@@ -309,8 +468,30 @@ export async function runClaude(promptPath: string, options: ClaudeOptions) {
      core.warning(`Failed to process output for execution metrics: ${e}`);
    }

-    core.setOutput("conclusion", "success");
    core.setOutput("execution_file", EXECUTION_FILE);
+
+    // When claude_args requested schema-validated output, surface it as the
+    // `structured_output` action output. Fail loudly (rather than emit empty)
+    // if the schema was requested but no structured result came back, matching
+    // upstream claude-code-base-action behavior.
+    if (config.hasJsonSchema) {
+      const structuredOutput = extractStructuredOutput(output);
+      if (structuredOutput == null) {
+        core.setOutput("conclusion", "failure");
+        core.setFailed(
+          "--json-schema was provided in claude_args but Claude did not return structured_output.",
+        );
+        process.exit(1);
+      }
+      core.setOutput("structured_output", JSON.stringify(structuredOutput));
+      const fieldCount =
+        typeof structuredOutput === "object"
+          ? Object.keys(structuredOutput as object).length
+          : 0;
+      core.info(`Set structured_output with ${fieldCount} field(s)`);
+    }
+
+    core.setOutput("conclusion", "success");
  } else {
    core.setOutput("conclusion", "failure");

@@ -1,7 +1,16 @@
 #!/usr/bin/env bun

-import { describe, test, expect } from "bun:test";
-import { prepareRunConfig, type ClaudeOptions } from "../src/run-claude";
+import { describe, test, expect, beforeAll, afterAll } from "bun:test";
+import { mkdtempSync, writeFileSync, rmSync } from "fs";
+import { tmpdir } from "os";
+import { join } from "path";
+import {
+  prepareRunConfig,
+  parseClaudeArgs,
+  inlineJsonSchemaArgs,
+  extractStructuredOutput,
+  type ClaudeOptions,
+} from "../src/run-claude";

 describe("prepareRunConfig", () => {
  test("should prepare config with basic arguments", () => {
@@ -294,4 +303,237 @@ describe("prepareRunConfig", () => {
      expect(prepared.env).toEqual({});
    });
  });
+
+  describe("claude_args passthrough", () => {
+    test("empty/undefined claude_args leaves the arg list byte-identical", () => {
+      const baseline = prepareRunConfig("/tmp/test-prompt.txt", {
+        allowedTools: "Bash,Read",
+        maxTurns: "3",
+      });
+      const withEmpty = prepareRunConfig("/tmp/test-prompt.txt", {
+        allowedTools: "Bash,Read",
+        maxTurns: "3",
+        claudeArgs: "",
+      });
+      const withWhitespace = prepareRunConfig("/tmp/test-prompt.txt", {
+        allowedTools: "Bash,Read",
+        maxTurns: "3",
+        claudeArgs: "   \n  ",
+      });
+
+      const expected = [
+        "-p",
+        "--verbose",
+        "--output-format",
+        "stream-json",
+        "--allowedTools",
+        "Bash,Read",
+        "--max-turns",
+        "3",
+      ];
+      expect(baseline.claudeArgs).toEqual(expected);
+      expect(withEmpty.claudeArgs).toEqual(expected);
+      expect(withWhitespace.claudeArgs).toEqual(expected);
+      expect(baseline.hasJsonSchema).toBe(false);
+    });
+
+    test("claude_args tokens are appended after the managed arguments", () => {
+      const prepared = prepareRunConfig("/tmp/test-prompt.txt", {
+        maxTurns: "3",
+        claudeArgs: `--output-format json --json-schema '{"type":"object"}'`,
+      });
+
+      expect(prepared.claudeArgs).toEqual([
+        "-p",
+        "--verbose",
+        "--output-format",
+        "stream-json",
+        "--max-turns",
+        "3",
+        "--output-format",
+        "json",
+        "--json-schema",
+        '{"type":"object"}',
+      ]);
+      expect(prepared.hasJsonSchema).toBe(true);
+    });
+
+    test("a single-quoted inline JSON schema survives as one token (incl. $ref)", () => {
+      const schema = '{"$ref":"#/$defs/Verdict","type":"object"}';
+      const tokens = parseClaudeArgs(`--json-schema '${schema}'`);
+      expect(tokens).toEqual(["--json-schema", schema]);
+    });
+
+    test("comment lines are stripped before tokenizing", () => {
+      const tokens = parseClaudeArgs(
+        "# leading comment\n--max-turns 5\n  # indented comment\n--verbose",
+      );
+      expect(tokens).toEqual(["--max-turns", "5", "--verbose"]);
+    });
+
+    test("hasJsonSchema is detected for both space and equals forms", () => {
+      expect(
+        prepareRunConfig("/tmp/test-prompt.txt", {
+          claudeArgs: `--json-schema '{"type":"object"}'`,
+        }).hasJsonSchema,
+      ).toBe(true);
+      expect(
+        prepareRunConfig("/tmp/test-prompt.txt", {
+          claudeArgs: `--json-schema='{"type":"object"}'`,
+        }).hasJsonSchema,
+      ).toBe(true);
+      expect(
+        prepareRunConfig("/tmp/test-prompt.txt", {
+          claudeArgs: "--max-turns 3",
+        }).hasJsonSchema,
+      ).toBe(false);
+    });
+  });
+
+  describe("inlineJsonSchemaArgs (issue #3 — file-path schemas)", () => {
+    let dir: string;
+
+    beforeAll(() => {
+      dir = mkdtempSync(join(tmpdir(), "json-schema-test-"));
+    });
+
+    afterAll(() => {
+      rmSync(dir, { recursive: true, force: true });
+    });
+
+    test("passes through args that don't touch --json-schema", () => {
+      const args = ["-p", "--max-turns", "3", "--verbose"];
+      expect(inlineJsonSchemaArgs(args)).toEqual(args);
+    });
+
+    test("leaves an already-inline JSON schema untouched (space form)", () => {
+      const inline = '{"type":"object","properties":{"x":{"type":"string"}}}';
+      expect(inlineJsonSchemaArgs(["--json-schema", inline])).toEqual([
+        "--json-schema",
+        inline,
+      ]);
+    });
+
+    test("leaves an already-inline JSON schema untouched (equals form)", () => {
+      const inline = '{"type":"object"}';
+      expect(inlineJsonSchemaArgs([`--json-schema=${inline}`])).toEqual([
+        `--json-schema=${inline}`,
+      ]);
+    });
+
+    test("inlines a file-path schema (space form)", () => {
+      const schema = { type: "object", required: ["decision"] };
+      const file = join(dir, "space.json");
+      writeFileSync(file, JSON.stringify(schema, null, 2));
+
+      expect(inlineJsonSchemaArgs(["--json-schema", file])).toEqual([
+        "--json-schema",
+        JSON.stringify(schema),
+      ]);
+    });
+
+    test("inlines a file-path schema (equals form)", () => {
+      const schema = { type: "object" };
+      const file = join(dir, "equals.json");
+      writeFileSync(file, JSON.stringify(schema));
+
+      expect(inlineJsonSchemaArgs([`--json-schema=${file}`])).toEqual([
+        `--json-schema=${JSON.stringify(schema)}`,
+      ]);
+    });
+
+    // The reason the file-path form exists: a schema with $ref/$defs must
+    // round-trip without the shell expanding `$`. Inlining in-process and
+    // handing the result to spawn() as an argv element keeps it intact.
+    test("inlines a file-path schema containing $ref/$defs intact", () => {
+      const schema = {
+        $ref: "#/$defs/Verdict",
+        $defs: {
+          Verdict: {
+            type: "object",
+            additionalProperties: false,
+            required: ["decision"],
+            properties: {
+              decision: { type: "string", enum: ["approve", "reject"] },
+            },
+          },
+        },
+      };
+      const file = join(dir, "ref-schema.json");
+      writeFileSync(file, JSON.stringify(schema, null, 2));
+
+      const [flag, value] = inlineJsonSchemaArgs(["--json-schema", file]);
+      expect(flag).toBe("--json-schema");
+      expect(value).toContain("$ref");
+      expect(value).toContain("$defs");
+      expect(JSON.parse(value as string)).toEqual(schema);
+    });
+
+    test("throws a clear error when the schema file is missing", () => {
+      const missing = join(dir, "does-not-exist.json");
+      expect(() => inlineJsonSchemaArgs(["--json-schema", missing])).toThrow(
+        /Failed to read --json-schema file/,
+      );
+    });
+
+    test("throws a clear error when the schema file is not valid JSON", () => {
+      const file = join(dir, "invalid.json");
+      writeFileSync(file, "{ this is not json ");
+      expect(() => inlineJsonSchemaArgs(["--json-schema", file])).toThrow(
+        /is not valid JSON/,
+      );
+    });
+
+    test("prepareRunConfig inlines a file-path schema end-to-end", () => {
+      const schema = { $ref: "#/$defs/V", $defs: { V: { type: "object" } } };
+      const file = join(dir, "prepare.json");
+      writeFileSync(file, JSON.stringify(schema, null, 2));
+
+      const prepared = prepareRunConfig("/tmp/test-prompt.txt", {
+        claudeArgs: `--json-schema ${file}`,
+      });
+
+      expect(prepared.hasJsonSchema).toBe(true);
+      const idx = prepared.claudeArgs.indexOf("--json-schema");
+      expect(idx).toBeGreaterThanOrEqual(0);
+      expect(prepared.claudeArgs[idx + 1]).toBe(JSON.stringify(schema));
+    });
+  });
+
+  describe("extractStructuredOutput", () => {
+    test("returns structured_output from the stream-json result event", () => {
+      const verdict = { decision: "approve", score: 9 };
+      const output = [
+        JSON.stringify({ type: "system", subtype: "init" }),
+        JSON.stringify({ type: "assistant", message: { content: [] } }),
+        JSON.stringify({
+          type: "result",
+          subtype: "success",
+          is_error: false,
+          structured_output: verdict,
+        }),
+      ].join("\n");
+
+      expect(extractStructuredOutput(output)).toEqual(verdict);
+    });
+
+    test("returns undefined when no structured_output is present", () => {
+      const output = [
+        JSON.stringify({ type: "system", subtype: "init" }),
+        JSON.stringify({ type: "result", subtype: "success", is_error: false }),
+      ].join("\n");
+
+      expect(extractStructuredOutput(output)).toBeUndefined();
+    });
+
+    test("ignores non-JSON lines and trailing whitespace", () => {
+      const verdict = { ok: true };
+      const output = `Running Claude...\n${JSON.stringify({
+        type: "result",
+        structured_output: verdict,
+      })}\n\n`;
+
+      expect(extractStructuredOutput(output)).toEqual(verdict);
+    });
+  });
 });
@@ -1,22 +1,25 @@
 {
  "lockfileVersion": 1,
+  "configVersion": 0,
  "workspaces": {
    "": {
      "name": "@anthropic-ai/claude-code-action",
      "dependencies": {
        "@actions/core": "^1.10.1",
        "@actions/github": "^6.0.1",
+        "@anthropic-ai/sdk": "^0.30.0",
        "@modelcontextprotocol/sdk": "^1.11.0",
-        "@octokit/graphql": "^8.2.2",
-        "@octokit/rest": "^21.1.1",
+        "@octokit/rest": "^22.0.0",
        "@octokit/webhooks-types": "^7.6.1",
        "node-fetch": "^3.3.2",
+        "shell-quote": "^1.8.1",
        "zod": "^3.24.4",
      },
      "devDependencies": {
        "@types/bun": "1.2.11",
        "@types/node": "^20.0.0",
        "@types/node-fetch": "^2.6.12",
+        "@types/shell-quote": "^1.7.5",
        "prettier": "3.5.3",
        "typescript": "^5.8.3",
      },
@@ -33,6 +36,8 @@

    "@actions/io": ["@actions/io@1.1.3", "", {}, "sha512-wi9JjgKLYS7U/z8PPbco+PvTb/nRWjeoFlJ1Qer83k/3C5PHQi28hiVdeE2kHXmIL99mQFawx8qt/JPjZilJ8Q=="],

+    "@anthropic-ai/sdk": ["@anthropic-ai/sdk@0.30.1", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" } }, "sha512-nuKvp7wOIz6BFei8WrTdhmSsx5mwnArYyJgh4+vYu3V4J0Ltb8Xm3odPm51n1aSI0XxNCrDl7O88cxCtUdAkaw=="],
+
    "@fastify/busboy": ["@fastify/busboy@2.1.1", "", {}, "sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA=="],

    "@modelcontextprotocol/sdk": ["@modelcontextprotocol/sdk@1.16.0", "", { "dependencies": { "ajv": "^6.12.6", "content-type": "^1.0.5", "cors": "^2.8.5", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "express": "^5.0.1", "express-rate-limit": "^7.5.0", "pkce-challenge": "^5.0.0", "raw-body": "^3.0.0", "zod": "^3.23.8", "zod-to-json-schema": "^3.24.1" } }, "sha512-8ofX7gkZcLj9H9rSd50mCgm3SSF8C7XoclxJuLoV0Cz3rEQ1tv9MZRYYvJtm9n1BiEQQMzSmE/w2AEkNacLYfg=="],
@@ -43,13 +48,13 @@

    "@octokit/endpoint": ["@octokit/endpoint@9.0.6", "", { "dependencies": { "@octokit/types": "^13.1.0", "universal-user-agent": "^6.0.0" } }, "sha512-H1fNTMA57HbkFESSt3Y9+FBICv+0jFceJFPWDePYlR/iMGrwM5ph+Dd4XRQs+8X+PUFURLQgX9ChPfhJ/1uNQw=="],

-    "@octokit/graphql": ["@octokit/graphql@8.2.2", "", { "dependencies": { "@octokit/request": "^9.2.3", "@octokit/types": "^14.0.0", "universal-user-agent": "^7.0.0" } }, "sha512-Yi8hcoqsrXGdt0yObxbebHXFOiUA+2v3n53epuOg1QUgOB6c4XzvisBNVXJSl8RYA5KrDuSL2yq9Qmqe5N0ryA=="],
+    "@octokit/graphql": ["@octokit/graphql@7.1.1", "", { "dependencies": { "@octokit/request": "^8.4.1", "@octokit/types": "^13.0.0", "universal-user-agent": "^6.0.0" } }, "sha512-3mkDltSfcDUoa176nlGoA32RGjeWjl3K7F/BwHwRMJUW/IteSa4bnSV8p2ThNkcIcZU2umkZWxwETSSCJf2Q7g=="],

-    "@octokit/openapi-types": ["@octokit/openapi-types@25.1.0", "", {}, "sha512-idsIggNXUKkk0+BExUn1dQ92sfysJrje03Q0bv0e+KPLrvyqZF8MnBpFz8UNfYDwB3Ie7Z0TByjWfzxt7vseaA=="],
+    "@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],

    "@octokit/plugin-paginate-rest": ["@octokit/plugin-paginate-rest@9.2.2", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-u3KYkGF7GcZnSD/3UP0S7K5XUFT2FkOQdcfXZGZQPGv3lm4F2Xbf71lvjldr8c1H3nNbF+33cLEkWYbokGWqiQ=="],

-    "@octokit/plugin-request-log": ["@octokit/plugin-request-log@5.3.1", "", { "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-n/lNeCtq+9ofhC15xzmJCNKP2BWTv8Ih2TTy+jatNCCq/gQP/V7rK3fjIfuz0pDWDALO/o/4QY4hyOF6TQQFUw=="],
+    "@octokit/plugin-request-log": ["@octokit/plugin-request-log@6.0.0", "", { "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-UkOzeEN3W91/eBq9sPZNQ7sUBvYCqYbrrD8gTbBuGtHEuycE4/awMXcYvx6sVYo7LypPhmQwwpUe4Yyu4QZN5Q=="],

    "@octokit/plugin-rest-endpoint-methods": ["@octokit/plugin-rest-endpoint-methods@10.4.1", "", { "dependencies": { "@octokit/types": "^12.6.0" }, "peerDependencies": { "@octokit/core": "5" } }, "sha512-xV1b+ceKV9KytQe3zCVqjg+8GTGfDYwaT1ATU5isiUyVtlVAO3HNdzpS4sr4GBx4hxQ46s7ITtZrAsxG22+rVg=="],

@@ -57,9 +62,9 @@

    "@octokit/request-error": ["@octokit/request-error@5.1.1", "", { "dependencies": { "@octokit/types": "^13.1.0", "deprecation": "^2.0.0", "once": "^1.4.0" } }, "sha512-v9iyEQJH6ZntoENr9/yXxjuezh4My67CBSu9r6Ve/05Iu5gNgnisNWOsoJHTP6k0Rr0+HQIpnH+kyammu90q/g=="],

-    "@octokit/rest": ["@octokit/rest@21.1.1", "", { "dependencies": { "@octokit/core": "^6.1.4", "@octokit/plugin-paginate-rest": "^11.4.2", "@octokit/plugin-request-log": "^5.3.1", "@octokit/plugin-rest-endpoint-methods": "^13.3.0" } }, "sha512-sTQV7va0IUVZcntzy1q3QqPm/r8rWtDCqpRAmb8eXXnKkjoQEtFe3Nt5GTVsHft+R6jJoHeSiVLcgcvhtue/rg=="],
+    "@octokit/rest": ["@octokit/rest@22.0.1", "", { "dependencies": { "@octokit/core": "^7.0.6", "@octokit/plugin-paginate-rest": "^14.0.0", "@octokit/plugin-request-log": "^6.0.0", "@octokit/plugin-rest-endpoint-methods": "^17.0.0" } }, "sha512-Jzbhzl3CEexhnivb1iQ0KJ7s5vvjMWcmRtq5aUsKmKDrRW6z3r84ngmiFKFvpZjpiU/9/S6ITPFRpn5s/3uQJw=="],

-    "@octokit/types": ["@octokit/types@14.1.0", "", { "dependencies": { "@octokit/openapi-types": "^25.1.0" } }, "sha512-1y6DgTy8Jomcpu33N+p5w58l6xyt55Ar2I91RPiIA0xCJBXyUAhXCcmZaDWSANiha7R9a6qJJ2CRomGPZ6f46g=="],
+    "@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],

    "@octokit/webhooks-types": ["@octokit/webhooks-types@7.6.1", "", {}, "sha512-S8u2cJzklBC0FgTwWVLaM8tMrDuDMVE4xiTK4EYXM9GntyvrdbSoxqDQa+Fh57CCNApyIpyeqPhhFEmHPfrXgw=="],

@@ -69,8 +74,14 @@

    "@types/node-fetch": ["@types/node-fetch@2.6.12", "", { "dependencies": { "@types/node": "*", "form-data": "^4.0.0" } }, "sha512-8nneRWKCg3rMtF69nLQJnOYUcbafYeFSjqkw3jCRLsqkWFlHaoQrr5mXmofFGOx3DKn7UfmBMyov8ySvLRVldA=="],

+    "@types/shell-quote": ["@types/shell-quote@1.7.5", "", {}, "sha512-+UE8GAGRPbJVQDdxi16dgadcBfQ+KG2vgZhV1+3A1XmHbmwcdwhCUwIdy+d3pAGrbvgRoVSjeI9vOWyq376Yzw=="],
+
+    "abort-controller": ["abort-controller@3.0.0", "", { "dependencies": { "event-target-shim": "^5.0.0" } }, "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg=="],
+
    "accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],

+    "agentkeepalive": ["agentkeepalive@4.6.0", "", { "dependencies": { "humanize-ms": "^1.2.1" } }, "sha512-kja8j7PjmncONqaTsB8fQ+wE2mSU2DJ9D4XKoJ5PFWIdRMa6SLSN1ff4mOr4jCbfRSsxR4keIiySJU0N9T5hIQ=="],
+
    "ajv": ["ajv@6.12.6", "", { "dependencies": { "fast-deep-equal": "^3.1.1", "fast-json-stable-stringify": "^2.0.0", "json-schema-traverse": "^0.4.1", "uri-js": "^4.2.2" } }, "sha512-j3fVLgvTo527anyYyJOGTYJbG+vnnQYvE0m5mmkc1TK+nxAppkCLMIL0aZ4dblVCNoGShhm+kzE4ZUykBoMg4g=="],

    "asynckit": ["asynckit@0.4.0", "", {}, "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="],
@@ -129,6 +140,8 @@

    "etag": ["etag@1.8.1", "", {}, "sha512-aIL5Fx7mawVa300al2BnEE4iNvo1qETxLrPI/o05L7z6go7fCw1J6EQmbK4FmJ2AS7kgVF/KEZWufBfdClMcPg=="],

+    "event-target-shim": ["event-target-shim@5.0.1", "", {}, "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ=="],
+
    "eventsource": ["eventsource@3.0.7", "", { "dependencies": { "eventsource-parser": "^3.0.1" } }, "sha512-CRT1WTyuQoD771GW56XEZFQ/ZoSfWid1alKGDYMmkt2yl8UXrVR4pspqWNEcqKvVIzg6PAltWjxcSSPrboA4iA=="],

    "eventsource-parser": ["eventsource-parser@3.0.3", "", {}, "sha512-nVpZkTMM9rF6AQ9gPJpFsNAMt48wIzB5TQgiTLdHiuO8XEDhUgZEhqKlZWXbIzo9VmJ/HvysHqEaVeD5v9TPvA=="],
@@ -137,8 +150,6 @@

    "express-rate-limit": ["express-rate-limit@7.5.1", "", { "peerDependencies": { "express": ">= 4.11" } }, "sha512-7iN8iPMDzOMHPUYllBEsQdWVB6fPDMPqwjBaFrgr4Jgr/+okjvzAy+UHlYYL/Vs0OsOrMkwS6PJDkFlJwoxUnw=="],

-    "fast-content-type-parse": ["fast-content-type-parse@2.0.1", "", {}, "sha512-nGqtvLrj5w0naR6tDPfB4cUmYCqouzyQiz6C5y/LtcDllJdrcc6WaWW6iXyIIOErTa/XRybj28aasdn4LkVk6Q=="],
-
    "fast-deep-equal": ["fast-deep-equal@3.1.3", "", {}, "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q=="],

    "fast-json-stable-stringify": ["fast-json-stable-stringify@2.1.0", "", {}, "sha512-lhd/wF+Lk98HZoTCtlVraHtfh5XYijIjalXck7saUtuanSDyLMxnHhSXEDJqHxD7msR8D0uCmqlkwjCV8xvwHw=="],
@@ -149,6 +160,10 @@

    "form-data": ["form-data@4.0.4", "", { "dependencies": { "asynckit": "^0.4.0", "combined-stream": "^1.0.8", "es-set-tostringtag": "^2.1.0", "hasown": "^2.0.2", "mime-types": "^2.1.12" } }, "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow=="],

+    "form-data-encoder": ["form-data-encoder@1.7.2", "", {}, "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A=="],
+
+    "formdata-node": ["formdata-node@4.4.1", "", { "dependencies": { "node-domexception": "1.0.0", "web-streams-polyfill": "4.0.0-beta.3" } }, "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ=="],
+
    "formdata-polyfill": ["formdata-polyfill@4.0.10", "", { "dependencies": { "fetch-blob": "^3.1.2" } }, "sha512-buewHzMvYL29jdeQTVILecSaZKnt/RJWjoZCF5OW60Z67/GmSLBkOFM7qh1PI3zFNtJbaZL5eQu1vLfazOwj4g=="],

    "forwarded": ["forwarded@0.2.0", "", {}, "sha512-buRG0fpBtRHSTCOASe6hD258tEubFoRLb4ZNA6NxMVHNw2gOcwHo9wyablzMzOA5z9xA9L1KNjk/Nt6MT9aYow=="],
@@ -171,6 +186,8 @@

    "http-errors": ["http-errors@2.0.0", "", { "dependencies": { "depd": "2.0.0", "inherits": "2.0.4", "setprototypeof": "1.2.0", "statuses": "2.0.1", "toidentifier": "1.0.1" } }, "sha512-FtwrG/euBzaEjYeRqOgly7G0qviiXoJWnvEH2Z1plBdXgbyjv34pHTSb9zoeHMyDy33+DWy5Wt9Wo+TURtOYSQ=="],

+    "humanize-ms": ["humanize-ms@1.2.1", "", { "dependencies": { "ms": "^2.0.0" } }, "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ=="],
+
    "iconv-lite": ["iconv-lite@0.6.3", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw=="],

    "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="],
@@ -183,6 +200,8 @@

    "json-schema-traverse": ["json-schema-traverse@0.4.1", "", {}, "sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg=="],

+    "json-with-bigint": ["json-with-bigint@3.5.8", "", {}, "sha512-eq/4KP6K34kwa7TcFdtvnftvHCD9KvHOGGICWwMFc4dOOKF5t4iYqnfLK8otCRCRv06FXOzGGyqE8h8ElMvvdw=="],
+
    "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="],

    "media-typer": ["media-typer@1.1.0", "", {}, "sha512-aisnrDP4GNe06UcKFnV5bfMNPBUw4jsLGaWwWfnH3v02GnBuXX2MCVn5RbrWo0j3pczUilYblq7fQ7Nw2t5XKw=="],
@@ -245,6 +264,8 @@

    "shebang-regex": ["shebang-regex@3.0.0", "", {}, "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A=="],

+    "shell-quote": ["shell-quote@1.8.4", "", {}, "sha512-VsC6n6vz1ihYYyZZwX7YZSF5l5x36ca17OC+a69h94YqB7X6XLwf+5MOgynYir2SLFUbl8gIYvBo8K8RoNQ6bQ=="],
+
    "side-channel": ["side-channel@1.1.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3", "side-channel-list": "^1.0.0", "side-channel-map": "^1.0.1", "side-channel-weakmap": "^1.0.2" } }, "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw=="],

    "side-channel-list": ["side-channel-list@1.0.0", "", { "dependencies": { "es-errors": "^1.3.0", "object-inspect": "^1.13.3" } }, "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA=="],
@@ -257,6 +278,8 @@

    "toidentifier": ["toidentifier@1.0.1", "", {}, "sha512-o5sSPKEkg/DIQNmH43V0/uerLrpzVedkUh8tGNvaeXpfpuwjKenlSox/2O/BTlZUtEe+JG7s5YhEz608PlAHRA=="],

+    "tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="],
+
    "tunnel": ["tunnel@0.0.6", "", {}, "sha512-1h/Lnq9yajKY2PEbBadPXj3VxsDDu844OnaAo52UVmIzIvwwtBPIuNvkjuzBlTWpfJyUbG3ez0KSBibQkj4ojg=="],

    "type-is": ["type-is@2.0.1", "", { "dependencies": { "content-type": "^1.0.5", "media-typer": "^1.1.0", "mime-types": "^3.0.0" } }, "sha512-OZs6gsjF4vMp32qrCbiVSkrFmXtG/AZhY3t0iAMrMBiAZyV9oALtXO8hsrHbMXF9x6L3grlFuwW2oAz7cav+Gw=="],
@@ -267,7 +290,7 @@

    "undici-types": ["undici-types@6.21.0", "", {}, "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ=="],

-    "universal-user-agent": ["universal-user-agent@7.0.3", "", {}, "sha512-TmnEAEAsBJVZM/AADELsK76llnwcf9vMKuPz8JflO1frO8Lchitr0fNaN9d+Ap0BjKtqWqd/J17qeDnXh8CL2A=="],
+    "universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],

    "unpipe": ["unpipe@1.0.0", "", {}, "sha512-pjy2bYhSsufwWlKwPc+l3cN7+wuJlK6uz0YdJEOlQDbl6jo/YlPi4mb8agUkVC8BF7V8NuzeyPNqRksA3hztKQ=="],

@@ -275,7 +298,11 @@

    "vary": ["vary@1.1.2", "", {}, "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg=="],

-    "web-streams-polyfill": ["web-streams-polyfill@3.3.3", "", {}, "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw=="],
+    "web-streams-polyfill": ["web-streams-polyfill@4.0.0-beta.3", "", {}, "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug=="],
+
+    "webidl-conversions": ["webidl-conversions@3.0.1", "", {}, "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="],
+
+    "whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="],

    "which": ["which@2.0.2", "", { "dependencies": { "isexe": "^2.0.0" }, "bin": { "node-which": "./bin/node-which" } }, "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA=="],

@@ -285,79 +312,69 @@

    "zod-to-json-schema": ["zod-to-json-schema@3.24.6", "", { "peerDependencies": { "zod": "^3.24.1" } }, "sha512-h/z3PKvcTcTetyjl1fkj79MHNEjm+HpD6NXheWjzOekY7kV+lwDYnHw+ivHkijnCSMz1yJaWBD9vu/Fcmk+vEg=="],

-    "@octokit/core/@octokit/graphql": ["@octokit/graphql@7.1.1", "", { "dependencies": { "@octokit/request": "^8.4.1", "@octokit/types": "^13.0.0", "universal-user-agent": "^6.0.0" } }, "sha512-3mkDltSfcDUoa176nlGoA32RGjeWjl3K7F/BwHwRMJUW/IteSa4bnSV8p2ThNkcIcZU2umkZWxwETSSCJf2Q7g=="],
+    "@anthropic-ai/sdk/@types/node": ["@types/node@18.19.130", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-GRaXQx6jGfL8sKfaIDD6OupbIHBr9jv7Jnaml9tB7l4v068PAOXqfcujMMo5PhbIs6ggR1XODELqahT2R8v0fg=="],

-    "@octokit/core/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
-
-    "@octokit/core/universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],
-
-    "@octokit/endpoint/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
-
-    "@octokit/endpoint/universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],
-
-    "@octokit/graphql/@octokit/request": ["@octokit/request@9.2.4", "", { "dependencies": { "@octokit/endpoint": "^10.1.4", "@octokit/request-error": "^6.1.8", "@octokit/types": "^14.0.0", "fast-content-type-parse": "^2.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-q8ybdytBmxa6KogWlNa818r0k1wlqzNC+yNkcQDECHvQo8Vmstrg18JwqJHdJdUiHD2sjlwBgSm9kHkOKe2iyA=="],
+    "@anthropic-ai/sdk/node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="],

    "@octokit/plugin-paginate-rest/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],

-    "@octokit/plugin-request-log/@octokit/core": ["@octokit/core@6.1.6", "", { "dependencies": { "@octokit/auth-token": "^5.0.0", "@octokit/graphql": "^8.2.2", "@octokit/request": "^9.2.3", "@octokit/request-error": "^6.1.8", "@octokit/types": "^14.0.0", "before-after-hook": "^3.0.2", "universal-user-agent": "^7.0.0" } }, "sha512-kIU8SLQkYWGp3pVKiYzA5OSaNF5EE03P/R8zEmmrG6XwOg5oBjXyQVVIauQ0dgau4zYhpZEhJrvIYt6oM+zZZA=="],
+    "@octokit/plugin-request-log/@octokit/core": ["@octokit/core@7.0.6", "", { "dependencies": { "@octokit/auth-token": "^6.0.0", "@octokit/graphql": "^9.0.3", "@octokit/request": "^10.0.6", "@octokit/request-error": "^7.0.2", "@octokit/types": "^16.0.0", "before-after-hook": "^4.0.0", "universal-user-agent": "^7.0.0" } }, "sha512-DhGl4xMVFGVIyMwswXeyzdL4uXD5OGILGX5N8Y+f6W7LhC1Ze2poSNrkF/fedpVDHEEZ+PHFW0vL14I+mm8K3Q=="],

    "@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],

-    "@octokit/request/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
+    "@octokit/rest/@octokit/core": ["@octokit/core@7.0.6", "", { "dependencies": { "@octokit/auth-token": "^6.0.0", "@octokit/graphql": "^9.0.3", "@octokit/request": "^10.0.6", "@octokit/request-error": "^7.0.2", "@octokit/types": "^16.0.0", "before-after-hook": "^4.0.0", "universal-user-agent": "^7.0.0" } }, "sha512-DhGl4xMVFGVIyMwswXeyzdL4uXD5OGILGX5N8Y+f6W7LhC1Ze2poSNrkF/fedpVDHEEZ+PHFW0vL14I+mm8K3Q=="],

-    "@octokit/request/universal-user-agent": ["universal-user-agent@6.0.1", "", {}, "sha512-yCzhz6FN2wU1NiiQRogkTQszlQSlpWaw8SvVegAc+bDxbzHgh1vX8uIe8OYyMH6DwH+sdTJsgMl36+mSMdRJIQ=="],
+    "@octokit/rest/@octokit/plugin-paginate-rest": ["@octokit/plugin-paginate-rest@14.0.0", "", { "dependencies": { "@octokit/types": "^16.0.0" }, "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-fNVRE7ufJiAA3XUrha2omTA39M6IXIc6GIZLvlbsm8QOQCYvpq/LkMNGyFlB1d8hTDzsAXa3OKtybdMAYsV/fw=="],

-    "@octokit/request-error/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
-
-    "@octokit/rest/@octokit/core": ["@octokit/core@6.1.6", "", { "dependencies": { "@octokit/auth-token": "^5.0.0", "@octokit/graphql": "^8.2.2", "@octokit/request": "^9.2.3", "@octokit/request-error": "^6.1.8", "@octokit/types": "^14.0.0", "before-after-hook": "^3.0.2", "universal-user-agent": "^7.0.0" } }, "sha512-kIU8SLQkYWGp3pVKiYzA5OSaNF5EE03P/R8zEmmrG6XwOg5oBjXyQVVIauQ0dgau4zYhpZEhJrvIYt6oM+zZZA=="],
-
-    "@octokit/rest/@octokit/plugin-paginate-rest": ["@octokit/plugin-paginate-rest@11.6.0", "", { "dependencies": { "@octokit/types": "^13.10.0" }, "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-n5KPteiF7pWKgBIBJSk8qzoZWcUkza2O6A0za97pMGVrGfPdltxrfmfF5GucHYvHGZD8BdaZmmHGz5cX/3gdpw=="],
-
-    "@octokit/rest/@octokit/plugin-rest-endpoint-methods": ["@octokit/plugin-rest-endpoint-methods@13.5.0", "", { "dependencies": { "@octokit/types": "^13.10.0" }, "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-9Pas60Iv9ejO3WlAX3maE1+38c5nqbJXV5GrncEfkndIpZrJ/WPMRd2xYDcPPEt5yzpxcjw9fWNoPhsSGzqKqw=="],
+    "@octokit/rest/@octokit/plugin-rest-endpoint-methods": ["@octokit/plugin-rest-endpoint-methods@17.0.0", "", { "dependencies": { "@octokit/types": "^16.0.0" }, "peerDependencies": { "@octokit/core": ">=6" } }, "sha512-B5yCyIlOJFPqUUeiD0cnBJwWJO8lkJs5d8+ze9QDP6SvfiXSz1BF+91+0MeI1d2yxgOhU/O+CvtiZ9jSkHhFAw=="],

    "accepts/mime-types": ["mime-types@3.0.1", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-xRc4oEhT6eaBpU1XF7AjpOFD+xQmXNB5OVKwp4tqCuBpHLS/ZbBDrc07mYTDqVMg6PfxUjjNp85O6Cd2Z/5HWA=="],

    "express/mime-types": ["mime-types@3.0.1", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-xRc4oEhT6eaBpU1XF7AjpOFD+xQmXNB5OVKwp4tqCuBpHLS/ZbBDrc07mYTDqVMg6PfxUjjNp85O6Cd2Z/5HWA=="],

+    "fetch-blob/web-streams-polyfill": ["web-streams-polyfill@3.3.3", "", {}, "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw=="],
+
    "send/mime-types": ["mime-types@3.0.1", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-xRc4oEhT6eaBpU1XF7AjpOFD+xQmXNB5OVKwp4tqCuBpHLS/ZbBDrc07mYTDqVMg6PfxUjjNp85O6Cd2Z/5HWA=="],

    "type-is/mime-types": ["mime-types@3.0.1", "", { "dependencies": { "mime-db": "^1.54.0" } }, "sha512-xRc4oEhT6eaBpU1XF7AjpOFD+xQmXNB5OVKwp4tqCuBpHLS/ZbBDrc07mYTDqVMg6PfxUjjNp85O6Cd2Z/5HWA=="],

-    "@octokit/core/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
-
-    "@octokit/endpoint/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
-
-    "@octokit/graphql/@octokit/request/@octokit/endpoint": ["@octokit/endpoint@10.1.4", "", { "dependencies": { "@octokit/types": "^14.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-OlYOlZIsfEVZm5HCSR8aSg02T2lbUWOsCQoPKfTXJwDzcHQBrVBGdGXb89dv2Kw2ToZaRtudp8O3ZIYoaOjKlA=="],
-
-    "@octokit/graphql/@octokit/request/@octokit/request-error": ["@octokit/request-error@6.1.8", "", { "dependencies": { "@octokit/types": "^14.0.0" } }, "sha512-WEi/R0Jmq+IJKydWlKDmryPcmdYSVjL3ekaiEL1L9eo1sUnqMJ+grqmC9cjk7CA7+b2/T397tO5d8YLOH3qYpQ=="],
+    "@anthropic-ai/sdk/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="],

    "@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],

-    "@octokit/plugin-request-log/@octokit/core/@octokit/auth-token": ["@octokit/auth-token@5.1.2", "", {}, "sha512-JcQDsBdg49Yky2w2ld20IHAlwr8d/d8N6NiOXbtuoPCqzbsiJgF633mVUw3x4mo0H5ypataQIX7SFu3yy44Mpw=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/auth-token": ["@octokit/auth-token@6.0.0", "", {}, "sha512-P4YJBPdPSpWTQ1NU4XYdvHvXJJDxM6YwpS0FZHRgP7YFkdVxsWcpWGy/NVqlAA7PcPCnMacXlRm1y2PFZRWL/w=="],

-    "@octokit/plugin-request-log/@octokit/core/@octokit/request": ["@octokit/request@9.2.4", "", { "dependencies": { "@octokit/endpoint": "^10.1.4", "@octokit/request-error": "^6.1.8", "@octokit/types": "^14.0.0", "fast-content-type-parse": "^2.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-q8ybdytBmxa6KogWlNa818r0k1wlqzNC+yNkcQDECHvQo8Vmstrg18JwqJHdJdUiHD2sjlwBgSm9kHkOKe2iyA=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/graphql": ["@octokit/graphql@9.0.3", "", { "dependencies": { "@octokit/request": "^10.0.6", "@octokit/types": "^16.0.0", "universal-user-agent": "^7.0.0" } }, "sha512-grAEuupr/C1rALFnXTv6ZQhFuL1D8G5y8CN04RgrO4FIPMrtm+mcZzFG7dcBm+nq+1ppNixu+Jd78aeJOYxlGA=="],

-    "@octokit/plugin-request-log/@octokit/core/@octokit/request-error": ["@octokit/request-error@6.1.8", "", { "dependencies": { "@octokit/types": "^14.0.0" } }, "sha512-WEi/R0Jmq+IJKydWlKDmryPcmdYSVjL3ekaiEL1L9eo1sUnqMJ+grqmC9cjk7CA7+b2/T397tO5d8YLOH3qYpQ=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/request": ["@octokit/request@10.0.10", "", { "dependencies": { "@octokit/endpoint": "^11.0.3", "@octokit/request-error": "^7.0.2", "@octokit/types": "^16.0.0", "content-type": "^2.0.0", "json-with-bigint": "^3.5.3", "universal-user-agent": "^7.0.2" } }, "sha512-KxNC2pTqqhszMNrf12ZRd4PonRgyJdsM4F/jySiddQK+DsRcfBtUvqn8t7UsyZhnRJHvX46OohDt5N3VqIWC2w=="],

-    "@octokit/plugin-request-log/@octokit/core/before-after-hook": ["before-after-hook@3.0.2", "", {}, "sha512-Nik3Sc0ncrMK4UUdXQmAnRtzmNQTAAXmXIopizwZ1W1t8QmfJj+zL4OA2I7XPTPW5z5TDqv4hRo/JzouDJnX3A=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/request-error": ["@octokit/request-error@7.1.0", "", { "dependencies": { "@octokit/types": "^16.0.0" } }, "sha512-KMQIfq5sOPpkQYajXHwnhjCC0slzCNScLHs9JafXc4RAJI+9f+jNDlBNaIMTvazOPLgb4BnlhGJOTbnN0wIjPw=="],
+
+    "@octokit/plugin-request-log/@octokit/core/@octokit/types": ["@octokit/types@16.0.0", "", { "dependencies": { "@octokit/openapi-types": "^27.0.0" } }, "sha512-sKq+9r1Mm4efXW1FCk7hFSeJo4QKreL/tTbR0rz/qx/r1Oa2VV83LTA/H/MuCOX7uCIJmQVRKBcbmWoySjAnSg=="],
+
+    "@octokit/plugin-request-log/@octokit/core/before-after-hook": ["before-after-hook@4.0.0", "", {}, "sha512-q6tR3RPqIB1pMiTRMFcZwuG5T8vwp+vUvEG0vuI6B+Rikh5BfPp2fQ82c925FOs+b0lcFQ8CFrL+KbilfZFhOQ=="],
+
+    "@octokit/plugin-request-log/@octokit/core/universal-user-agent": ["universal-user-agent@7.0.3", "", {}, "sha512-TmnEAEAsBJVZM/AADELsK76llnwcf9vMKuPz8JflO1frO8Lchitr0fNaN9d+Ap0BjKtqWqd/J17qeDnXh8CL2A=="],

    "@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],

-    "@octokit/request-error/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
+    "@octokit/rest/@octokit/core/@octokit/auth-token": ["@octokit/auth-token@6.0.0", "", {}, "sha512-P4YJBPdPSpWTQ1NU4XYdvHvXJJDxM6YwpS0FZHRgP7YFkdVxsWcpWGy/NVqlAA7PcPCnMacXlRm1y2PFZRWL/w=="],

-    "@octokit/request/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
+    "@octokit/rest/@octokit/core/@octokit/graphql": ["@octokit/graphql@9.0.3", "", { "dependencies": { "@octokit/request": "^10.0.6", "@octokit/types": "^16.0.0", "universal-user-agent": "^7.0.0" } }, "sha512-grAEuupr/C1rALFnXTv6ZQhFuL1D8G5y8CN04RgrO4FIPMrtm+mcZzFG7dcBm+nq+1ppNixu+Jd78aeJOYxlGA=="],

-    "@octokit/rest/@octokit/core/@octokit/auth-token": ["@octokit/auth-token@5.1.2", "", {}, "sha512-JcQDsBdg49Yky2w2ld20IHAlwr8d/d8N6NiOXbtuoPCqzbsiJgF633mVUw3x4mo0H5ypataQIX7SFu3yy44Mpw=="],
+    "@octokit/rest/@octokit/core/@octokit/request": ["@octokit/request@10.0.10", "", { "dependencies": { "@octokit/endpoint": "^11.0.3", "@octokit/request-error": "^7.0.2", "@octokit/types": "^16.0.0", "content-type": "^2.0.0", "json-with-bigint": "^3.5.3", "universal-user-agent": "^7.0.2" } }, "sha512-KxNC2pTqqhszMNrf12ZRd4PonRgyJdsM4F/jySiddQK+DsRcfBtUvqn8t7UsyZhnRJHvX46OohDt5N3VqIWC2w=="],

-    "@octokit/rest/@octokit/core/@octokit/request": ["@octokit/request@9.2.4", "", { "dependencies": { "@octokit/endpoint": "^10.1.4", "@octokit/request-error": "^6.1.8", "@octokit/types": "^14.0.0", "fast-content-type-parse": "^2.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-q8ybdytBmxa6KogWlNa818r0k1wlqzNC+yNkcQDECHvQo8Vmstrg18JwqJHdJdUiHD2sjlwBgSm9kHkOKe2iyA=="],
+    "@octokit/rest/@octokit/core/@octokit/request-error": ["@octokit/request-error@7.1.0", "", { "dependencies": { "@octokit/types": "^16.0.0" } }, "sha512-KMQIfq5sOPpkQYajXHwnhjCC0slzCNScLHs9JafXc4RAJI+9f+jNDlBNaIMTvazOPLgb4BnlhGJOTbnN0wIjPw=="],

-    "@octokit/rest/@octokit/core/@octokit/request-error": ["@octokit/request-error@6.1.8", "", { "dependencies": { "@octokit/types": "^14.0.0" } }, "sha512-WEi/R0Jmq+IJKydWlKDmryPcmdYSVjL3ekaiEL1L9eo1sUnqMJ+grqmC9cjk7CA7+b2/T397tO5d8YLOH3qYpQ=="],
+    "@octokit/rest/@octokit/core/@octokit/types": ["@octokit/types@16.0.0", "", { "dependencies": { "@octokit/openapi-types": "^27.0.0" } }, "sha512-sKq+9r1Mm4efXW1FCk7hFSeJo4QKreL/tTbR0rz/qx/r1Oa2VV83LTA/H/MuCOX7uCIJmQVRKBcbmWoySjAnSg=="],

-    "@octokit/rest/@octokit/core/before-after-hook": ["before-after-hook@3.0.2", "", {}, "sha512-Nik3Sc0ncrMK4UUdXQmAnRtzmNQTAAXmXIopizwZ1W1t8QmfJj+zL4OA2I7XPTPW5z5TDqv4hRo/JzouDJnX3A=="],
+    "@octokit/rest/@octokit/core/before-after-hook": ["before-after-hook@4.0.0", "", {}, "sha512-q6tR3RPqIB1pMiTRMFcZwuG5T8vwp+vUvEG0vuI6B+Rikh5BfPp2fQ82c925FOs+b0lcFQ8CFrL+KbilfZFhOQ=="],

-    "@octokit/rest/@octokit/plugin-paginate-rest/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
+    "@octokit/rest/@octokit/core/universal-user-agent": ["universal-user-agent@7.0.3", "", {}, "sha512-TmnEAEAsBJVZM/AADELsK76llnwcf9vMKuPz8JflO1frO8Lchitr0fNaN9d+Ap0BjKtqWqd/J17qeDnXh8CL2A=="],

-    "@octokit/rest/@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@13.10.0", "", { "dependencies": { "@octokit/openapi-types": "^24.2.0" } }, "sha512-ifLaO34EbbPj0Xgro4G5lP5asESjwHracYJvVaPIyXMuiuXLlhic3S47cBdTb+jfODkTE5YtGCLt3Ay3+J97sA=="],
+    "@octokit/rest/@octokit/plugin-paginate-rest/@octokit/types": ["@octokit/types@16.0.0", "", { "dependencies": { "@octokit/openapi-types": "^27.0.0" } }, "sha512-sKq+9r1Mm4efXW1FCk7hFSeJo4QKreL/tTbR0rz/qx/r1Oa2VV83LTA/H/MuCOX7uCIJmQVRKBcbmWoySjAnSg=="],
+
+    "@octokit/rest/@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@16.0.0", "", { "dependencies": { "@octokit/openapi-types": "^27.0.0" } }, "sha512-sKq+9r1Mm4efXW1FCk7hFSeJo4QKreL/tTbR0rz/qx/r1Oa2VV83LTA/H/MuCOX7uCIJmQVRKBcbmWoySjAnSg=="],

    "accepts/mime-types/mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],

@@ -367,12 +384,20 @@

    "type-is/mime-types/mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],

-    "@octokit/plugin-request-log/@octokit/core/@octokit/request/@octokit/endpoint": ["@octokit/endpoint@10.1.4", "", { "dependencies": { "@octokit/types": "^14.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-OlYOlZIsfEVZm5HCSR8aSg02T2lbUWOsCQoPKfTXJwDzcHQBrVBGdGXb89dv2Kw2ToZaRtudp8O3ZIYoaOjKlA=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/request/@octokit/endpoint": ["@octokit/endpoint@11.0.3", "", { "dependencies": { "@octokit/types": "^16.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-FWFlNxghg4HrXkD3ifYbS/IdL/mDHjh9QcsNyhQjN8dplUoZbejsdpmuqdA76nxj2xoWPs7p8uX2SNr9rYu0Ag=="],

-    "@octokit/rest/@octokit/core/@octokit/request/@octokit/endpoint": ["@octokit/endpoint@10.1.4", "", { "dependencies": { "@octokit/types": "^14.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-OlYOlZIsfEVZm5HCSR8aSg02T2lbUWOsCQoPKfTXJwDzcHQBrVBGdGXb89dv2Kw2ToZaRtudp8O3ZIYoaOjKlA=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/request/content-type": ["content-type@2.0.0", "", {}, "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ=="],

-    "@octokit/rest/@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
+    "@octokit/plugin-request-log/@octokit/core/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@27.0.0", "", {}, "sha512-whrdktVs1h6gtR+09+QsNk2+FO+49j6ga1c55YZudfEG+oKJVvJLQi3zkOm5JjiUXAagWK2tI2kTGKJ2Ys7MGA=="],

-    "@octokit/rest/@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@24.2.0", "", {}, "sha512-9sIH3nSUttelJSXUrmGzl7QUBFul0/mB8HRYl3fOlgHbIWG+WnYDXU3v/2zMtAvuzZ/ed00Ei6on975FhBfzrg=="],
+    "@octokit/rest/@octokit/core/@octokit/request/@octokit/endpoint": ["@octokit/endpoint@11.0.3", "", { "dependencies": { "@octokit/types": "^16.0.0", "universal-user-agent": "^7.0.2" } }, "sha512-FWFlNxghg4HrXkD3ifYbS/IdL/mDHjh9QcsNyhQjN8dplUoZbejsdpmuqdA76nxj2xoWPs7p8uX2SNr9rYu0Ag=="],
+
+    "@octokit/rest/@octokit/core/@octokit/request/content-type": ["content-type@2.0.0", "", {}, "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ=="],
+
+    "@octokit/rest/@octokit/core/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@27.0.0", "", {}, "sha512-whrdktVs1h6gtR+09+QsNk2+FO+49j6ga1c55YZudfEG+oKJVvJLQi3zkOm5JjiUXAagWK2tI2kTGKJ2Ys7MGA=="],
+
+    "@octokit/rest/@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@27.0.0", "", {}, "sha512-whrdktVs1h6gtR+09+QsNk2+FO+49j6ga1c55YZudfEG+oKJVvJLQi3zkOm5JjiUXAagWK2tI2kTGKJ2Ys7MGA=="],
+
+    "@octokit/rest/@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@27.0.0", "", {}, "sha512-whrdktVs1h6gtR+09+QsNk2+FO+49j6ga1c55YZudfEG+oKJVvJLQi3zkOm5JjiUXAagWK2tI2kTGKJ2Ys7MGA=="],
  }
 }
@@ -0,0 +1,67 @@
+# Example: schema-validated PR review verdict via `claude_args` + `structured_output`.
+#
+# Instead of having the agent write its verdict to a file, this asks Claude for a
+# result that conforms to a JSON Schema and reads it back from the action output.
+# The default-installed Claude CLI (2.1.160) supports `--json-schema`; the
+# action reads the schema file below and passes it to the CLI inline, so the
+# file-path form works out of the box (see README → "Structured output"). If
+# you consume this action through a pre-baked runner image
+# (path_to_claude_code_executable), that image's CLI must still support the
+# `--json-schema` flag.
+
+name: Claude PR Review (structured output)
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+
+jobs:
+  review:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      # The schema the verdict must conform to. Using a file (rather than an
+      # inline string) keeps the value free of spaces and `$` characters, so a
+      # schema with $ref/$defs survives shell tokenization intact.
+      - name: Write review schema
+        shell: bash
+        run: |
+          mkdir -p .gitea
+          cat > .gitea/review-schema.json <<'JSON'
+          {
+            "type": "object",
+            "additionalProperties": false,
+            "required": ["decision", "summary"],
+            "properties": {
+              "decision": { "type": "string", "enum": ["approve", "request_changes", "comment"] },
+              "summary": { "type": "string" }
+            }
+          }
+          JSON
+
+      - name: Run Claude review
+        id: review
+        uses: ryan/claude-code-gitea-action@gitea
+        with:
+          gitea_token: ${{ secrets.GITEA_TOKEN }}
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          direct_prompt: |
+            Review the changes in this pull request and return your verdict
+            strictly matching the provided JSON schema.
+          claude_args: --json-schema ${{ github.workspace }}/.gitea/review-schema.json
+
+      - name: Act on the verdict
+        shell: bash
+        env:
+          VERDICT: ${{ steps.review.outputs.structured_output }}
+        run: |
+          echo "Decision: $(echo "$VERDICT" | jq -r '.decision')"
+          echo "Summary:  $(echo "$VERDICT" | jq -r '.summary')"
@@ -17,12 +17,14 @@
    "@octokit/rest": "^22.0.0",
    "@octokit/webhooks-types": "^7.6.1",
    "node-fetch": "^3.3.2",
+    "shell-quote": "^1.8.1",
    "zod": "^3.24.4"
  },
  "devDependencies": {
    "@types/bun": "1.2.11",
    "@types/node": "^20.0.0",
    "@types/node-fetch": "^2.6.12",
+    "@types/shell-quote": "^1.7.5",
    "prettier": "3.5.3",
    "typescript": "^5.8.3"
  }