firegoat 0.11.0 → 0.12.0

package/README.md

@@ -82,14 +82,33 @@ tests:
 npx firegoat eval --var SHA=$(git rev-parse HEAD)
 ```
 
+### Env vars for the agent: a home dir per run, a feature flag
+
+```yaml
+env:
+  ACME_HOME: "/tmp/acme-{{run.id}}-{{run.n}}"   # sessions/config never collide across runs
+  ACME_TELEMETRY: "off"
+tests:
+  - name: login
+    prompt: Log in to acme with the CLI and print the current user.
+    end_goal: The agent completes acme's login flow and prints the user.
+    env:
+      ACME_BETA_LOGIN: "1"                        # this test only, on top of env:
+    checks:
+      - run: ls "$ACME_HOME"/sessions | grep -q .
+```
+
+`env:` goes to the agent, and to `workdir_setup` and checks of the same run, so checks see the same values. Placeholders: `{{vars.KEY}}`, `{{run.id}}` (the eval's run id), `{{run.n}}` (1..runs), `{{run.workdir}}`, `{{test.name}}`. `setup` runs once, before any run: it gets only the top-level entries that use nothing but `{{vars.*}}` and `{{run.id}}`. Values are strings (quote numbers). `PATH`, `CLAUDE_CONFIG_DIR` and `FIREGOAT_*` are firegoat's and can't be set.
+
 ## What eval does
 
 - claude runs on its own login (or `ANTHROPIC_API_KEY`, if set) with `CLAUDE_CONFIG_DIR=.firegoat/.claude` and `--setting-sources "" --strict-mcp-config --disable-slash-commands`: none of your settings, CLAUDE.md, plugins, skills or MCP servers. claude saves its session there, in its own format.
 - No sandbox: the agent's folder is inside `.firegoat/runs/`, and it can reach the rest of your machine. In `.firegoat/`, git ignores `runs/` and `.claude/`; keep test fixtures (scripts, sample data) in `.firegoat/fixtures/` and commit them with `firegoat.yaml`.
+- The agent gets your environment plus `env:`, never `vars:`. Vars that npm/npx set for firegoat itself (`npm_config_*`, `npm_lifecycle_*`, `npm_package_*`, `npm_execpath`, `npm_node_execpath`, `npm_command`, `INIT_CWD`) are removed from every env firegoat starts (agent, setup, workdir_setup, checks): `npx -y firegoat` sets `npm_config_yes=true`, which would make the agent's `npm init` / `npx create-*` skip their prompts. Set one under `env:` to keep it.
 - Script checks run in the agent's folder afterwards and set the exit code. `end_goal` is not graded by firegoat: it's for you, or your coding agent, to judge from `run.json`, the session and the folder.
 - Output per run, in `.firegoat/runs/<runId>/<test>/<n>/`: `transcript.txt` (each tool call with its command and short output, the final answer, files made; checks get it as `$FIREGOAT_TRANSCRIPT`), `run.json` (status, prompt, end_goal, check results, paths), `work/`, logs. Read the transcript to judge `end_goal`; claude's full session file is ~50x larger. `summary.json` covers the whole eval; `--json` prints it.
 
-`firegoat.yaml` keys: `runs`, `setup`, `workdir_setup`, `vars`, and `tests` (`name`, `prompt`, `end_goal`, `checks`, `timeout`). Unknown keys are errors. Full reference: `npx firegoat init --help`.
+`firegoat.yaml` keys: `runs`, `setup`, `workdir_setup`, `vars`, `env`, and `tests` (`name`, `prompt`, `end_goal`, `checks`, `timeout`, `env`). Unknown keys are errors. Full reference: `npx firegoat init --help`.
 
 Want a plain `npm i acme-sdk` to get your build, with no hint in the prompt? See [`examples/local-npm-registry`](examples/local-npm-registry/README.md).
 

package/dist/cli.js

@@ -6947,7 +6947,7 @@ var require_public_api = __commonJS(function(exports) {
 // package.json
 var package_default = {
   name: "firegoat",
-  version: "0.11.0",
+  version: "0.12.0",
   repository: {
     type: "git",
     url: "git+https://github.com/firegoat-ai/firegoat-cli.git"
@@ -7072,11 +7072,19 @@ function parseConfig(text) {
   }
   if (!isRecord(raw))
     fail("(root)", "must be a mapping");
-  onlyKeys(raw, "(root)", ["runs", "setup", "workdir_setup", "vars", "tests"]);
+  onlyKeys(raw, "(root)", [
+    "runs",
+    "setup",
+    "workdir_setup",
+    "vars",
+    "env",
+    "tests"
+  ]);
   const runs = posInt(raw.runs, "runs", 1);
   const setup = commands(raw.setup, "setup");
   const workdirSetup = commands(raw.workdir_setup, "workdir_setup");
   const vars = parseVars(raw.vars);
+  const env = parseEnv(raw.env, "env");
   if (!Array.isArray(raw.tests) || raw.tests.length === 0)
     fail("tests", "must be a non-empty list");
   const names = new Set;
@@ -7084,7 +7092,7 @@ function parseConfig(text) {
     const p = `tests[${i}]`;
     if (!isRecord(t))
       fail(p, "must be a mapping");
-    onlyKeys(t, p, ["name", "prompt", "end_goal", "checks", "timeout"]);
+    onlyKeys(t, p, ["name", "prompt", "end_goal", "checks", "timeout", "env"]);
     const name = str(t.name, `${p}.name`);
     if (!NAME.test(name))
       fail(`${p}.name`, "may only contain letters, digits, '.', '_' and '-'");
@@ -7107,7 +7115,8 @@ function parseConfig(text) {
       prompt: str(t.prompt, `${p}.prompt`),
       end_goal: str(t.end_goal, `${p}.end_goal`),
       checks,
-      timeout: posInt(t.timeout, `${p}.timeout`, DEFAULT_TIMEOUT)
+      timeout: posInt(t.timeout, `${p}.timeout`, DEFAULT_TIMEOUT),
+      env: { ...env, ...parseEnv(t.env, `${p}.env`) }
     };
   });
   return {
@@ -7115,6 +7124,7 @@ function parseConfig(text) {
     setup,
     workdirSetup,
     vars,
+    env,
     tests
   };
 }
@@ -7144,6 +7154,54 @@ function parseVars(raw) {
   }
   return out;
 }
+var RESERVED_ENV = new Set([
+  "PATH",
+  "CLAUDE_CONFIG_DIR",
+  "CLAUDE_SECURESTORAGE_CONFIG_DIR"
+]);
+var RUN_PLACEHOLDERS = ["run.id", "run.n", "run.workdir", "test.name"];
+var EVAL_PLACEHOLDERS = ["run.id"];
+var ANY_PLACEHOLDER = /\{\{\s*([^{}]*?)\s*\}\}/g;
+function parseEnv(raw, path) {
+  if (raw === undefined)
+    return {};
+  if (!isRecord(raw))
+    fail(path, "must be a mapping of NAME to value");
+  const out = {};
+  for (const [k, v] of Object.entries(raw)) {
+    const p = `${path}.${k}`;
+    if (!VAR_KEY.test(k))
+      fail(p, "name must be letters, digits and _, not starting with a digit");
+    if (RESERVED_ENV.has(k) || k.startsWith("FIREGOAT_"))
+      fail(p, "is set by firegoat and cannot be overridden (reserved: PATH, CLAUDE_CONFIG_DIR, CLAUDE_SECURESTORAGE_CONFIG_DIR, FIREGOAT_*)");
+    if (typeof v !== "string")
+      fail(p, "must be a string (quote numbers and booleans)");
+    for (const m of v.matchAll(ANY_PLACEHOLDER)) {
+      const name = m[1];
+      if (!/^vars\.[A-Za-z0-9_]+$/.test(name) && !RUN_PLACEHOLDERS.includes(name))
+        fail(p, `unknown placeholder ${m[0]} (allowed: {{vars.KEY}}, ${RUN_PLACEHOLDERS.map((n) => `{{${n}}}`).join(", ")})`);
+    }
+    out[k] = v;
+  }
+  return out;
+}
+function isEvalLevel(value) {
+  return [...value.matchAll(ANY_PLACEHOLDER)].every((m) => {
+    const name = m[1];
+    return name.startsWith("vars.") || EVAL_PLACEHOLDERS.includes(name);
+  });
+}
+function renderEnv(env, vars, run) {
+  const out = {};
+  for (const [k, v] of Object.entries(env))
+    out[k] = v.replace(ANY_PLACEHOLDER, (whole, name) => {
+      const filled = name.startsWith("vars.") ? vars[name.slice("vars.".length)] : run[name];
+      if (filled === undefined)
+        throw new ConfigError(`env.${k}: no value for ${whole}`);
+      return filled;
+    });
+  return out;
+}
 var PLACEHOLDER = /\{\{\s*vars\.([A-Za-z0-9_]+)\s*\}\}/g;
 function varRefs(text) {
   return [...text.matchAll(PLACEHOLDER)].map((m) => m[1]);
@@ -7186,9 +7244,14 @@ var CLAUDE_FLAGS = [
   "",
   "--disable-slash-commands"
 ];
-function claudeEnv(configDir) {
+var NPM_INJECTED = /^(npm_config_|npm_lifecycle_|npm_package_)|^(npm_execpath|npm_node_execpath|npm_command|INIT_CWD)$/;
+function hostEnv() {
+  return Object.fromEntries(Object.entries(process.env).filter(([k]) => !NPM_INJECTED.test(k)));
+}
+function claudeEnv(configDir, env = {}) {
   return {
-    ...process.env,
+    ...hostEnv(),
+    ...env,
     CLAUDE_CONFIG_DIR: configDir,
     CLAUDE_SECURESTORAGE_CONFIG_DIR: ""
   };
@@ -7404,6 +7467,12 @@ firegoat.yaml reference:
   workdir_setup: <sh> | [...] in each fresh folder before the agent starts
   vars: {KEY: value}          defaults for {{vars.KEY}} in prompts and checks;
                               --var KEY=value overrides
+  env: {NAME: value}          env vars for the agent, and for workdir_setup and
+                              checks of the same run; values are strings and can
+                              use {{vars.KEY}}, {{run.id}}, {{run.n}},
+                              {{run.workdir}}, {{test.name}}. setup gets only the
+                              entries that use nothing but {{vars.*}}/{{run.id}}.
+                              PATH, CLAUDE_CONFIG_DIR and FIREGOAT_* are reserved.
   tests:
     - name: quickstart        letters, digits, '.', '_', '-'; unique
       prompt: ...             what a user would ask the agent; one concrete outcome
@@ -7412,6 +7481,7 @@ firegoat.yaml reference:
       checks:                 optional shell commands, run in the agent's folder
         - run: ...            afterwards; exit 0 = pass; they set eval's exit code
       timeout: 600            optional, seconds
+      env: {NAME: value}      optional, on top of the top-level env:
 
   Unknown keys are errors. Keep helper files out of firegoat.yaml: put them in
   .firegoat/fixtures/ and copy them in setup or workdir_setup. setup, workdir_setup and checks get the vars as env vars,
@@ -7420,6 +7490,11 @@ firegoat.yaml reference:
   each output), and
   $FIREGOAT_SESSION (claude's full session file, JSON lines).
 
+  The agent never gets vars, only env:. The vars npm/npx set for firegoat itself
+  (npm_config_*, npm_lifecycle_*, npm_package_*, npm_execpath, npm_node_execpath,
+  npm_command, INIT_CWD; e.g. npm_config_yes=true from npx -y) are removed from
+  every env firegoat starts, unless env: sets them.
+
 Example:
   setup: npm pack --pack-destination "$FIREGOAT_OUT"
   workdir_setup: npm init -y >/dev/null && npm install "$FIREGOAT_OUT"/*.tgz
@@ -7942,7 +8017,13 @@ async function runOne(opts) {
 `);
     return r;
   };
-  const stepEnv = { ...opts.stepEnv, FIREGOAT_WORKDIR: workdir };
+  const env = renderEnv(test.env, opts.vars, {
+    "run.id": opts.runId,
+    "run.n": String(n),
+    "run.workdir": workdir,
+    "test.name": test.name
+  });
+  const stepEnv = { ...opts.stepEnv, ...env, FIREGOAT_WORKDIR: workdir };
   if (opts.workdirSetup.length > 0) {
     const error = await runSteps({
       what: "workdir_setup",
@@ -7959,7 +8040,7 @@ async function runOne(opts) {
     bin: opts.claudeBin,
     prompt: r.prompt,
     cwd: workdir,
-    env: { ...claudeEnv(opts.configDir), PATH: opts.stepEnv.PATH },
+    env: { ...claudeEnv(opts.configDir, env), PATH: opts.stepEnv.PATH },
     stderr,
     timeoutMs: test.timeout * 1000,
     onEvent: opts.onEvent
@@ -8044,7 +8125,11 @@ async function evalCommand(args, root) {
   const runs = opts.runs ?? config.runs;
   const vars = { ...config.vars, ...opts.vars };
   const missing = [
-    ...new Set(tests.flatMap((t) => [t.prompt, ...t.checks.map((c) => c.run)]).flatMap(varRefs).filter((k) => !(k in vars)))
+    ...new Set(tests.flatMap((t) => [
+      t.prompt,
+      ...t.checks.map((c) => c.run),
+      ...Object.values(t.env)
+    ]).flatMap(varRefs).filter((k) => !(k in vars)))
   ];
   if (missing.length > 0)
     return fatal(EXIT.usage, `no value for ${missing.map((k) => `{{vars.${k}}}`).join(", ")}: pass --var ${missing[0]}=... or set it under vars: in firegoat.yaml`);
@@ -8067,7 +8152,7 @@ async function evalCommand(args, root) {
   const out = join4(runDir, "out");
   mkdirSync2(out, { recursive: true });
   const stepEnv = {
-    ...process.env,
+    ...hostEnv(),
     ...vars,
     FIREGOAT_OUT: out,
     PATH: [out, process.env.PATH ?? ""].join(delimiter2)
@@ -8085,7 +8170,10 @@ async function evalCommand(args, root) {
       what: "setup",
       commands: config.setup,
       cwd: root,
-      env: stepEnv,
+      env: {
+        ...stepEnv,
+        ...renderEnv(Object.fromEntries(Object.entries(config.env).filter(([, v]) => isEvalLevel(v))), vars, { "run.id": runId })
+      },
       logPath: join4(runDir, "setup.txt")
     });
     const secs = Math.round((Date.now() - setupStarted) / 1000);
@@ -8117,6 +8205,7 @@ async function evalCommand(args, root) {
         },
         test,
         n,
+        runId,
         runDir,
         claudeBin: claudePath,
         configDir,
@@ -8195,6 +8284,12 @@ runs: 1
 # setup runs in this folder, so: setup: cp -R .firegoat/fixtures/. "$FIREGOAT_OUT"
 # then e.g. workdir_setup: cp "$FIREGOAT_OUT/wizard.mjs" .
 
+# Optional: env vars for the agent (and for workdir_setup and checks of the same
+# run). The agent gets none of vars:, only these. Placeholders: {{vars.KEY}},
+# {{run.id}}, {{run.n}}, {{run.workdir}}, {{test.name}}. A test can add its own env:.
+# env:
+#   MYTOOL_HOME: "/tmp/mytool-{{run.id}}-{{run.n}}"
+
 tests:
   - name: quickstart
     # What a user would ask their agent. Edit this.

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "firegoat",
-	"version": "0.11.0",
+	"version": "0.12.0",
 	"repository": {
 		"type": "git",
 		"url": "git+https://github.com/firegoat-ai/firegoat-cli.git"