Agent & model refactor (#478)

* agent & model refactor with ASKPASS git auth, UI restructure, clerk v7

Made-with: Cursor

* fix stale agent/effort refs, add tests for askpass + model resolution

- reviewCleanup.ts: payload.agent -> payload.model, remove effort
- selectMode.ts PlanEdit: remove delegation/subagent/effort references
- pullfrog.yml.ts: update env vars (drop GOOGLE_API_KEY/CURSOR_API_KEY,
  add GOOGLE_GENERATIVE_AI_API_KEY/XAI_API_KEY/MOONSHOT_API_KEY/OPENCODE_API_KEY)
- FlagsSettings/RepoInstructionsSection: remove stale effort/timeout copy
- new: gitAuthServer.test.ts (10 tests — lifecycle, token delivery, tamper detection, script gen)
- new: agent.test.ts (4 tests — default opentoad, AGENT_OVERRIDE, invalid override)
- new: models.test.ts (19 tests — parseModel, resolution, registry invariants)
- update models.dev snapshot

Made-with: Cursor

* fix changed-agents.sh to filter legacy agent files from CI matrix

legacy agent files (claude.ts, codex.ts, etc.) are @ts-nocheck and not
exported from index.ts. changed-agents.sh now reads index.ts imports to
build the active agent set and treats changes to inactive files as
non-agent changes (opentoad canary only).

Made-with: Cursor

* remove MCP file tools, old agent harnesses, and obsolete security tests

ASKPASS-based git auth makes the old MCP file tool security layer unnecessary:
- token never in subprocess env, so symlink/gitattributes/hook attacks can't exfiltrate it
- agents now use native file tools (OpenCode builtin read/edit)

deleted:
- action/mcp/file.ts (file_read, file_write, file_edit, file_delete, list_directory)
- action/mcp/index.ts (dead re-export)
- agent harnesses: claude.ts, codex.ts, cursor.ts, gemini.ts, opencode.ts
- opencode-runner.ts (inlined into opentoad.ts)
- security tests that validated MCP file tool restrictions
- commented-out three-step review flow (~300 lines)
- sanitizeSchema/wrapSchema dead code from mcp/shared.ts
- OPENCODE_MODEL_MINI/MAX env vars (effort-level model overrides removed)

updated test prompts to use generic file ops instead of MCP tool names.
restored pkg-json-scripts + requirements-txt-attack (test --ignore-scripts defense).

Made-with: Cursor

* bump actions/checkout v4 → v6 (node 24)

node 20 actions deprecated june 2, 2026.

Made-with: Cursor

* temporarily disable fail-fast on agnostic tests to debug checkout@v6

Made-with: Cursor

* re-enable fail-fast on agnostic tests

Made-with: Cursor

* fix test token mismatch: mint OIDC tokens scoped to target repo

CI tests override GITHUB_REPOSITORY to pullfrog/test-repo but inherit
the runner's GITHUB_TOKEN (scoped to pullfrog/app), causing 401s on
every run-context fetch. Clear GITHUB_TOKEN in the test subprocess so
ensureGitHubToken() mints a properly scoped token via OIDC.

Also centralizes the default GITHUB_REPOSITORY in runAgentStreaming
instead of repeating it in every test file, and fixes preview-cleanup
to remove workers from all queues (not just name-matching ones).

Made-with: Cursor

* fix ensureGitHubToken to try OIDC when app credentials are absent

ensureGitHubToken only attempted token minting when GITHUB_APP_ID and
GITHUB_PRIVATE_KEY were set. In CI, OIDC is available but app creds
aren't exposed — so the guard prevented minting entirely.

Made-with: Cursor

* dead code cleanup: remove remnants of deleted agents, file tools, effort system

remove unused @anthropic-ai/claude-agent-sdk and @openai/codex-sdk deps,
orphaned file-tool security tests, dead GEMINI_MODEL passthrough, stale
opencode-runner wiki refs, deleted test file references, and MCP file tool
docs. rename docs/effort → docs/models. fix vitest setup: move dotenv to
globalSetup (runs once before forks instead of per-file, 19s → 200ms).

Made-with: Cursor

* address review feedback: remove dead code, update stale references

- remove AGENT_OVERRIDE (only opentoad exists)
- remove shellToolName plumbing (always restricted shell)
- bump action version to 0.0.179
- remove CURSOR_API_KEY from all workflows/configs
- remove OPENCODE_MODEL_MINI/MAX from workflows/docs
- delete wiki/effort.md, rewrite docs/effort.mdx as "Models"
- rewrite wiki/modes.md: orchestrator/subagent → single agent
- simplify flag system: drop builtin flag extraction (debug, effort,
  timeout, agent), keep custom flag replacement only
- reserve all legacy flag names to prevent custom flag conflicts

Made-with: Cursor

* regenerate lockfile after removing claude-agent-sdk and codex-sdk

Made-with: Cursor

* fix import ordering, add lockfile check to pre-push hook

Made-with: Cursor

* remove dead debug payload field, stale packageExtensions

Made-with: Cursor

* merge proc-sandbox and token-exfil into a single test

proc-sandbox and token-exfil were duplicative — both tested that
SANDBOX_TEST_TOKEN couldn't be exfiltrated. consolidated into
token-exfil with shell:restricted (which actually exercises filterEnv)
and the /proc attack vector hints from proc-sandbox.

Made-with: Cursor

* fix wiki adversarial.md to match actual tokenExfil validator

Made-with: Cursor

test/ci.test.ts

@@ -4,7 +4,9 @@ import { dirname, join } from "node:path";
 import { fileURLToPath } from "node:url";
 import { describe, expect, it } from "vitest";
 import { parse } from "yaml";
-import { agentsManifest, type WorkflowPermissions } from "../external.ts";
+import { agents } from "../agents/index.ts";
+import type { WorkflowPermissions } from "../external.ts";
+import { providers } from "../models.ts";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const actionDir = join(__dirname, "..");
@@ -31,9 +33,6 @@ const actionWorkflow = parse(
   readFileSync(join(actionDir, ".github/workflows/test.yml"), "utf-8")
 ) as Workflow;
 
-// read test names from .ts files in a test directory.
-// matches `name: "xxx"` at the start of a line (with indentation) to skip
-// inline validator check names like `{ name: "set_output", ... }`.
 function getTestNamesFromDir(dir: string): string[] {
   const dirPath = join(__dirname, dir);
   const files = readdirSync(dirPath).filter((f) => f.endsWith(".ts"));
@@ -54,23 +53,19 @@ function getEnvVarNames(job: WorkflowJob): string[] {
   return Object.keys(job.env ?? {}).sort();
 }
 
-const expectedAgents = Object.keys(agentsManifest).sort();
+const expectedAgents = Object.keys(agents).sort();
 const crossagentTests = getTestNamesFromDir("crossagent");
 const agnosticTests = getTestNamesFromDir("agnostic");
 const adhocTests = getTestNamesFromDir("adhoc");
 const dynamicAgentsExpression = "$" + "{{ fromJSON(needs.changes.outputs.agents) }}";
 
-// all API key names from all agents + GITHUB_TOKEN + model overrides
+// all provider API key names + GITHUB_TOKEN + model overrides
 const expectedAgentEnvVars = [
   "GITHUB_TOKEN",
-  ...new Set(Object.values(agentsManifest).flatMap((a) => a.apiKeyNames)),
-  "GEMINI_MODEL",
-  "OPENCODE_MODEL_MAX",
-  "OPENCODE_MODEL_MINI",
+  ...new Set(Object.values(providers).flatMap((p) => [...p.envVars])),
   "OPENCODE_MODEL",
 ].sort();
 
-// agnostic tests only run with claude
 const expectedAgnosticEnvVars = ["ANTHROPIC_API_KEY", "GITHUB_TOKEN"].sort();
 
 describe("ci workflow consistency", () => {
@@ -92,32 +87,40 @@ describe("ci workflow consistency", () => {
       expect(rootJob.strategy!.matrix.agent).toBe(dynamicAgentsExpression);
     });
 
-    it("changed-agents.sh falls back to claude when shared agent code changed", () => {
+    it("changed-agents.sh falls back to opentoad when shared agent code changed", () => {
       const input = JSON.stringify(["action/agents/shared.ts"]);
       const output = execFileSync("bash", [join(__dirname, "changed-agents.sh")], {
         input,
         encoding: "utf-8",
       });
-      expect(JSON.parse(output)).toEqual(["claude"]);
+      expect(JSON.parse(output)).toEqual(["opentoad"]);
     });
 
-    it("changed-agents.sh falls back to claude for non-agent action changes", () => {
+    it("changed-agents.sh falls back to opentoad for non-agent action changes", () => {
       const output = execFileSync("bash", [join(__dirname, "changed-agents.sh")], {
-        input: JSON.stringify(["action/mcp/delegate.ts"]),
+        input: JSON.stringify(["action/mcp/server.ts"]),
         encoding: "utf-8",
       });
-      expect(JSON.parse(output)).toEqual(["claude"]);
+      expect(JSON.parse(output)).toEqual(["opentoad"]);
     });
 
-    it("changed-agents.sh includes claude canary alongside changed agents", () => {
+    it("changed-agents.sh includes opentoad canary alongside changed agents", () => {
       const output = execFileSync("bash", [join(__dirname, "changed-agents.sh")], {
-        input: JSON.stringify(["action/agents/gemini.ts", "action/mcp/server.ts"]),
+        input: JSON.stringify(["action/agents/opentoad.ts", "action/mcp/server.ts"]),
         encoding: "utf-8",
       });
-      expect(JSON.parse(output)).toEqual(["claude", "gemini"]);
+      expect(JSON.parse(output)).toEqual(["opentoad"]);
     });
 
-    it("action agent matrix matches agentsManifest", () => {
+    it("changed-agents.sh treats legacy agent files as non-agent changes", () => {
+      const output = execFileSync("bash", [join(__dirname, "changed-agents.sh")], {
+        input: JSON.stringify(["action/agents/claude.ts", "action/agents/gemini.ts"]),
+        encoding: "utf-8",
+      });
+      expect(JSON.parse(output)).toEqual(["opentoad"]);
+    });
+
+    it("action agent matrix matches agents map", () => {
       expect([...actionJob.strategy!.matrix.agent].sort()).toEqual(expectedAgents);
     });
 
@@ -141,7 +144,7 @@ describe("ci workflow consistency", () => {
       expect(getEnvVarNames(rootJob)).toEqual(getEnvVarNames(actionJob));
     });
 
-    it("env vars cover all agent API keys", () => {
+    it("env vars cover all provider API keys", () => {
       expect(getEnvVarNames(rootJob)).toEqual(expectedAgentEnvVars);
     });
 
@@ -175,7 +178,7 @@ describe("ci workflow consistency", () => {
       expect(getEnvVarNames(rootJob)).toEqual(getEnvVarNames(actionJob));
     });
 
-    it("env vars are correct for claude-only tests", () => {
+    it("env vars are correct for agnostic tests", () => {
       expect(getEnvVarNames(rootJob)).toEqual(expectedAgnosticEnvVars);
     });