fix(sandbox-bridge): allow the agent-hire skill's routes through the callback bridge (#8978)

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Managed agents run inside a sandbox and reach the Paperclip server
only through the sandbox callback bridge, which forwards a fixed route
allowlist (`DEFAULT_SANDBOX_CALLBACK_BRIDGE_ROUTE_ALLOWLIST`)
> - The `paperclip-create-agent` skill instructs an agent to call
adapter/icon discovery endpoints, compare existing agent configurations,
submit a hire request, and link the resulting approval to its source
issue
> - None of those routes were on the bridge allowlist, so a sandboxed
agent following the skill correctly hit `Route not allowed` on every
call — including the hire `POST` itself — making hiring impossible from
inside a sandbox
> - This pull request adds the six routes the skill uses to the bridge
allowlist, while keeping direct agent creation (`POST
/api/companies/:id/agents`) denied
> - The benefit is that hiring works end-to-end for sandboxed agents
through the approval-gated `agent-hires` path, without widening the
bridge beyond what the skill needs

## Linked Issues or Issue Description

No public issue exists; describing the bug in-PR (bug template fields):

- **What happened:** A managed agent running in a sandbox followed the
`paperclip-create-agent` skill and got `Route not allowed` from the
callback bridge on every endpoint the skill documents — adapter
discovery (`/llms/agent-configuration.txt`,
`/llms/agent-configuration/:adapterType.txt`, `/llms/agent-icons.txt`),
config comparison (`GET /api/companies/:id/agent-configurations`), the
hire submission (`POST /api/companies/:id/agent-hires`), and approval
linking (`POST /api/issues/:id/approvals`).
- **Expected behavior:** An agent with hiring permission can complete
the hire flow from inside a sandbox; the bridge forwards the skill's
routes and the server enforces authorization (`canCreateAgents`).
- **Impact:** Hiring by sandboxed agents was fully broken — the failure
is in the transport allowlist, not permissions, so no configuration
could work around it.

Related: #8981 (companion fix making the `paperclip-create-agent` skill
available to agents that can hire; supersedes #8823). The two changes
serve the same end-to-end hire flow but are independently mergeable —
this PR is purely the bridge transport allowlist.

Supersedes #8853.

## What Changed

- `packages/adapter-utils/src/sandbox-callback-bridge.ts`: add six
routes used by the `paperclip-create-agent` skill to
`DEFAULT_SANDBOX_CALLBACK_BRIDGE_ROUTE_ALLOWLIST` (three `GET /llms/...`
discovery routes, `GET .../agent-configurations`, `POST
.../agent-hires`, `POST /api/issues/:id/approvals`), with a comment
documenting why direct agent creation stays denied
- `packages/adapter-utils/src/sandbox-callback-bridge.test.ts`: assert
the six routes are allowed, and add negative cases proving the regexes
do not over-match (no `POST .../agents`, no non-`.txt` or arbitrary
`/llms` files, no `agent-hires` sub-resources)

## Verification

- `npx vitest run
packages/adapter-utils/src/sandbox-callback-bridge.test.ts` — 13/13
tests pass locally
- `npx tsc --noEmit -p packages/adapter-utils` — clean
- Manual: run a managed agent in a sandbox, invoke the
`paperclip-create-agent` skill, and confirm the discovery calls, hire
`POST`, and approval linking all pass through the bridge; `POST
/api/companies/:id/agents` still returns `Route not allowed`

## Risks

- Low risk: additive allowlist entries only; anchored regexes with
`[^/]+` segments prevent over-matching (covered by tests)
- The bridge allowlist bounds surface area but does not replace
server-side authorization — the hire `POST` remains approval-gated and
permission-checked (`canCreateAgents`) on the server

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- Claude (Anthropic) — Fable 5 (`claude-fable-5`), extended thinking,
agentic tool use via Claude Code; original diff authored with Claude
Opus 4.8 (1M context)

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

packages/adapter-utils/src/sandbox-callback-bridge.test.ts

@@ -1252,6 +1252,13 @@ describe("sandbox callback bridge", () => {
       { method: "GET", path: "/api/companies/co-1/approvals" },
       { method: "GET", path: "/api/companies/co-1/routines" },
       { method: "GET", path: "/api/companies/co-1/skills" },
+      // Hire skill (paperclip-create-agent): discovery + submit + issue linking
+      { method: "GET", path: "/llms/agent-configuration.txt" },
+      { method: "GET", path: "/llms/agent-configuration/claude_local.txt" },
+      { method: "GET", path: "/llms/agent-icons.txt" },
+      { method: "GET", path: "/api/companies/co-1/agent-configurations" },
+      { method: "POST", path: "/api/companies/co-1/agent-hires" },
+      { method: "POST", path: "/api/issues/issue-1/approvals" },
       { method: "GET", path: "/api/projects/proj-1" },
       { method: "GET", path: "/api/goals/goal-1" },
       { method: "GET", path: "/api/issues/issue-1" },
@@ -1308,6 +1315,12 @@ describe("sandbox callback bridge", () => {
       // grows new actions later.
       { method: "POST", path: "/api/execution-workspaces/ws-1/runtime-services/delete" },
       { method: "POST", path: "/api/companies/co-1/agents" },
+      // The hire allowlist must not over-match: only the exact .txt discovery
+      // files, only agent-hires (not /agents), and no sub-resources beyond it.
+      { method: "GET", path: "/llms/agent-configuration" },
+      { method: "GET", path: "/llms/secrets.txt" },
+      { method: "POST", path: "/api/companies/co-1/agent-hires/ap-1" },
+      { method: "POST", path: "/api/issues/issue-1/approvals/ap-1" },
       { method: "POST", path: "/api/agents/agent-1/pause" },
       { method: "POST", path: "/api/agents/agent-1/terminate" },
       { method: "POST", path: "/api/agents/agent-1/keys" },

packages/adapter-utils/src/sandbox-callback-bridge.ts

@@ -127,6 +127,18 @@ export const DEFAULT_SANDBOX_CALLBACK_BRIDGE_ROUTE_ALLOWLIST: readonly SandboxCa
   // Subtasks / delegation
   { method: "POST", path: /^\/api\/companies\/[^/]+\/issues$/ },
 
+  // Hiring (paperclip-create-agent skill): adapter/icon discovery, comparing
+  // existing agent configs, submitting the hire request, and linking the
+  // resulting approval to its source issue. Direct agent creation
+  // (POST /api/companies/:id/agents) stays denied — hires must go through the
+  // approval-gated agent-hires endpoint, which the server still permission-checks.
+  { method: "GET", path: /^\/llms\/agent-configuration\.txt$/ },
+  { method: "GET", path: /^\/llms\/agent-configuration\/[^/]+\.txt$/ },
+  { method: "GET", path: /^\/llms\/agent-icons\.txt$/ },
+  { method: "GET", path: /^\/api\/companies\/[^/]+\/agent-configurations$/ },
+  { method: "POST", path: /^\/api\/companies\/[^/]+\/agent-hires$/ },
+  { method: "POST", path: /^\/api\/issues\/[^/]+\/approvals$/ },
+
   // Approvals (request, read, comment)
   { method: "GET", path: /^\/api\/approvals\/[^/]+$/ },
   { method: "GET", path: /^\/api\/approvals\/[^/]+\/issues$/ },