## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Agents can run inside sandboxed environments like E2B, or on remote
hosts via SSH
> - The cursor adapter needs to resolve `cursor-agent` inside sandbox
environments where it's installed in `~/.local/bin`
> - But when using the default `agent` command on a sandbox target, the
adapter didn't know to look in `~/.local/bin/cursor-agent`, causing
"command not found" failures
> - Additionally, repeated SSH runs failed because `git checkout` during
workspace sync conflicted with leftover `.paperclip-runtime` files from
previous runs
> - This PR adds sandbox-aware command resolution for cursor and fixes
the SSH workspace sync conflict
> - The benefit is cursor works in E2B sandboxes out of the box, and
repeated SSH runs don't fail on workspace sync
## What Changed
- `cursor-local`: Added `prepareCursorSandboxCommand` — on sandbox
targets, reads the remote `$HOME`, prepends `~/.local/bin` to PATH, and
prefers `~/.local/bin/cursor-agent` when the default command is
requested; tightened the sandbox command probe to validate the binary
exists before launching; preserves explicit custom command overrides
- `adapter-utils/ssh.ts`: Added `--force` to git checkout in SSH
workspace sync to handle `.paperclip-runtime` untracked file conflicts
from previous runs
## Verification
- `pnpm test` — all existing and new tests pass, including cursor
sandbox probe, sandbox execution, and custom command override tests
- `pnpm typecheck` — clean
- Manual: configure an E2B environment, run a cursor-local task, verify
it resolves cursor-agent from the sandbox install path
## Risks
- Low-medium. The `--force` flag on git checkout could discard
uncommitted changes in the remote workspace, but the workspace is
managed by Paperclip and should not contain user edits.
## Model Used
Codex GPT 5.4 high via Paperclip.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Agents run inside environments (local, SSH, E2B sandbox)
> - Operators need to configure and manage these environments
> - But environment settings were buried inside the general company
settings page, making them hard to find
> - Additionally, when testing an agent from the configuration form, the
test always ran locally regardless of which environment was selected
> - This PR moves environments into a dedicated top-level company
settings section and wires the "Test Environment" button to run inside
the selected environment
> - The benefit is operators can find and manage environments more
easily, and the test button now validates the actual environment the
agent will use
## What Changed
- Added a dedicated `CompanyEnvironments` settings page with its own
route and sidebar entry
- Updated `CompanySettingsSidebar` and `CompanySettingsNav` to include
the new environments section
- Modified the agent test route (`POST /agents/:id/test`) to accept an
optional `environmentId` parameter
- Updated all adapter `test.ts` handlers to resolve and use the
specified execution target environment
- Added `resolveTestExecutionTarget` to `execution-target.ts` for remote
environment test resolution with cwd fallback
- Moved the "Test Environment" button and its feedback display into the
`NewAgent` page footer for better UX flow
## Verification
- `pnpm test` — all existing and new tests pass
- `pnpm typecheck` — clean
- Manual: navigate to Company Settings, confirm "Environments" appears
as a top-level section
- Manual: configure an agent with a non-local environment, click "Test
Environment", confirm the test runs inside that environment
## Risks
- Low risk. UI-only routing change for the settings page. The
test-in-environment change adds an optional parameter with a local
fallback, so existing behavior is preserved when no environment is
specified.
## Model Used
Codex GPT 5.4 high via Paperclip.
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
- Update stale doc comment in index.ts to reflect direct ~/.gemini/skills/
injection instead of tmpdir approach
- Remove bare GEMINI_API_KEY/GOOGLE_API_KEY from auth regex to prevent
false positives when those strings appear in assistant output
- Align hello probe sandbox/approvalMode flags with execute.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The Gemini CLI supports OAuth login via `gemini auth login` which stores
credentials locally without setting any env vars. The previous warn-level
check on missing GEMINI_API_KEY caused false alarms when CLI-based OAuth
was used. The hello probe that follows is the real auth authority — if
auth is actually broken, it will catch it and report appropriately.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Incorporate improvements from PR #13 and #105 into the gemini-local adapter:
- Add detectGeminiAuthRequired() for runtime auth failure detection with
errorCode: "gemini_auth_required" on execution results
- Add isGeminiTurnLimitResult() to detect exit code 53 / turn_limit status
and clear session to prevent stuck sessions on next heartbeat
- Add describeGeminiFailure() for structured error messages from parsed
result events including errors array extraction
- Return parsed resultEvent in resultJson instead of raw stdout/stderr
- Add isRetry guard to prevent stale session ID fallback after retry
- Replace boolean yolo with approvalMode string (default/auto_edit/yolo)
with backwards-compatible config.yolo fallback
- Add sandbox config option (--sandbox / --sandbox=none)
- Add GOOGLE_GENAI_USE_GCA auth detection in environment test
- Consolidate auth detection regex into shared detectGeminiAuthRequired()
- Add gemini-2.0-flash and gemini-2.0-flash-lite model IDs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Isolate skills injection using a temporary directory mapped via
GEMINI_CLI_HOME, mirroring the claude-local sandbox approach
instead of polluting the global ~/.gemini/skills directory.
- Update the environment probe to use `--output-format stream-json`
so the payload matches the downstream parseGeminiJsonl parser.
- Deduplicate `firstNonEmptyLine` helper by extracting it to a
shared `utils.ts` module.
- Clean up orphaned internal exports and update adapter documentation.
