[chore] Add Claude harness on E2B sandbox#5053
Draft
junaway wants to merge 1 commit into
Draft
Conversation
…al modes) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
dosubot
Bot
added
the
size:L
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
There was a problem hiding this comment.
Pull request overview
Adds the missing “Claude harness × E2B sandbox” support in the runner by wiring Claude-specific E2B asset provisioning (including a strict allow-list credential upload path), extending the run plan with an explicit isClaude flag, and adding unit tests + design docs to complete the harness×sandbox matrix.
Changes:
- Add
isClaudetoRunPlanand propagate it through E2B execution paths. - Implement Claude-on-E2B credential provisioning via an allow-listed upload of
.credentials.jsoninto the sandbox. - Add unit tests covering E2B run planning, orchestration wiring, and Claude asset upload behavior; add accompanying design docs.
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 14 comments.
Show a summary per file
| File | Description |
|---|---|
| services/runner/src/engines/sandbox_agent/run-plan.ts | Adds isClaude flag to the run plan. |
| services/runner/src/engines/sandbox_agent/e2b.ts | Implements allow-listed Claude credential upload + prepareE2BClaudeAssets. |
| services/runner/src/engines/sandbox_agent.ts | Wires prepareE2BClaudeAssets into the E2B run path. |
| services/runner/tests/unit/sandbox-agent-e2b-assets.test.ts | New unit tests for Claude-on-E2B asset provisioning and allow-list behavior. |
| services/runner/tests/unit/sandbox-agent-e2b-run-plan.test.ts | Unit tests for isClaude/isE2B plan derivation and refusal cases. |
| services/runner/tests/unit/sandbox-agent-orchestration.test.ts | Orchestration-level tests ensuring E2B Claude asset prep is invoked and teardown happens. |
| docs/design/agent-workflows/projects/add-claude-e2b/tasks.md | Task checklist for the Claude-on-E2B work. |
| docs/design/agent-workflows/projects/add-claude-e2b/specs.md | Spec document describing the intended TS changes and credential flow. |
| docs/design/agent-workflows/projects/add-claude-e2b/research.md | Research/investigation notes and rationale for the changes. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| * | ||
| * Run: pnpm test (or: pnpm exec vitest run tests/unit/sandbox-agent-e2b-assets.test.ts) | ||
| */ | ||
| import { afterEach, beforeEach, describe, it, vi } from "vitest"; |
|
|
||
| describe("Claude-on-E2B orchestration", () => { | ||
| it("calls prepareE2BClaudeAssets (injected) and prepareE2BPiAssets (injected) on E2B", async () => { | ||
| const { calls, deps } = fakeHarness({ cwd: "/root/work/agenta-e2b-fake" }); |
Comment on lines
+128
to
+129
| const localDir = process.env.CLAUDE_CONFIG_DIR || join(process.env.HOME ?? "", ".claude"); | ||
| if (!existsSync(localDir)) return; |
Comment on lines
+10
to
+14
| - [x] `workspace.ts`: extend `PrepareWorkspaceInput.plan` with `isE2b`; change `if (plan.isDaytona)` | ||
| to `if (plan.isDaytona || plan.isE2b)` so E2B uses the sandbox fs API. | ||
| - [x] `e2b.ts`: add `prepareE2bClaudeAssets` — uploads `~/.claude/` on `runtime_provided` credential | ||
| mode; export `PrepareE2bClaudeAssetsInput`. | ||
| - [x] `sandbox_agent.ts`: import and call `prepareE2bClaudeAssets` in the E2B block; add it to |
Comment on lines
+97
to
+107
| - Managed key never written to the sandbox filesystem (env-only, same as Pi-on-E2B). | ||
| - Own-login upload is gated by `shouldUploadOwnLogin` (same function as Pi), so it never fires | ||
| when a resolved key is present. | ||
| - Restricted-network refusal already in `buildRunPlan` — unchanged. | ||
| - `autoPause: true` + `timeoutMs` backstop already in `buildE2bCreate` — unchanged. | ||
|
|
||
| ## Foundation seam | ||
|
|
||
| When the non-Pi remote-bootstrap generalization lands, the `prepareE2bClaudeAssets` function | ||
| folds into a generic `prepareE2bHarnessAssets(plan)` dispatcher. The `isDaytona || isE2b` | ||
| workspace arm is already the generalized form. |
Comment on lines
+60
to
+69
| | Gap | Fix | | ||
| |---|---| | ||
| | `prepareWorkspace` falls through to local for E2B | Extend `PrepareWorkspaceInput` plan type with `isE2b`; add `isDaytona \|\| isE2b` arm that uses the sandbox fs API. The Daytona and E2B arms are identical in shape (both use `sandbox.mkdirFs` / `sandbox.writeFsFile`). | | ||
| | `prepareE2bPiAssets` returns early for Claude | Add `prepareE2bClaudeAssets` that uploads the Claude own-login from `~/.claude/` if `credentialMode === "runtime_provided"` (same gate as Pi's auth.json path). Wire it in `sandbox_agent.ts` next to the Pi call. | | ||
|
|
||
| ## Credential modes | ||
|
|
||
| - `credentialMode="env"`: `ANTHROPIC_API_KEY` arrives in `plan.secrets`, merged into `env` before | ||
| `buildSandboxProvider`, and carried into the sandbox through `buildE2bCreate({}, secrets).envs`. | ||
| No file upload needed. |
Comment on lines
+91
to
+95
| - `prepareWorkspace` E2B arm → folds onto a single `isDaytona || isE2b` branch (already done here). | ||
| - `prepareE2bClaudeAssets` own-login upload → folds onto a generic `prepareE2bHarnessAssets` | ||
| that dispatches by `acpAgent`. The Pi arm stays separate (pi-specific: extension, skills-in-pi-dir, | ||
| system-prompt). | ||
| - `buildE2bCreate` envs param already carries arbitrary secrets → no change needed. |
Comment on lines
+26
to
+42
| ## e2b.ts — add prepareE2bClaudeAssets | ||
|
|
||
| New export: | ||
|
|
||
| ```typescript | ||
| export interface PrepareE2bClaudeAssetsInput { | ||
| sandbox: any; | ||
| plan: Pick<RunPlan, "isClaude" | "credentialMode">; | ||
| log?: Log; | ||
| } | ||
|
|
||
| export async function prepareE2bClaudeAssets({ | ||
| sandbox, | ||
| plan, | ||
| log = () => {}, | ||
| }: PrepareE2bClaudeAssetsInput): Promise<void> | ||
| ``` |
Comment on lines
+60
to
+71
| ## sandbox_agent.ts — wire prepareE2bClaudeAssets | ||
|
|
||
| In the E2B asset-prep block (currently only `prepareE2bPiAssets`): | ||
|
|
||
| ```typescript | ||
| } else if (plan.isE2b) { | ||
| await (deps.prepareE2bPiAssets ?? prepareE2bPiAssets)({ sandbox, plan, log: logger }); | ||
| await (deps.prepareE2bClaudeAssets ?? prepareE2bClaudeAssets)({ sandbox, plan, log: logger }); | ||
| } | ||
| ``` | ||
|
|
||
| `SandboxAgentDeps` gains `prepareE2bClaudeAssets?: typeof prepareE2bClaudeAssets`. |
Comment on lines
+83
to
+93
| ``` | ||
| credentialMode="env": | ||
| ANTHROPIC_API_KEY in plan.secrets | ||
| → merged into env by sandbox_agent.ts | ||
| → carried into sandbox by buildE2bCreate({}, secrets).envs | ||
| (no file upload) | ||
|
|
||
| credentialMode="runtime_provided": | ||
| prepareE2bClaudeAssets uploads ~/.claude/ into /root/.claude/ in the sandbox | ||
| (best-effort; same pattern as Pi auth.json upload) | ||
| ``` |
This was referenced Jul 4, 2026
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Context
Claude worked locally and, in a sibling PR, on Daytona. E2B needed its own Claude auth-provisioning path, completing Claude's row of the harness x sandbox matrix.
Changes
Adds Claude harnessFiles provisioning and auth upload in
e2b.ts, following the same allow-list discipline as the Daytona branch: uploads exactly.credentials.json(never a directory scan) fromCLAUDE_CONFIG_DIR || ~/.claude, to the E2B-side Claude dir (default/root/.claude, overridable). Both managed and self-managed credential modes are supported.Tests / notes
sandbox-agent-e2b-assets.test.ts,sandbox-agent-e2b-run-plan.test.ts,sandbox-agent-orchestration.test.ts.chore/add-sandbox-e2b, notbig-agents— this is the last of the 12 harness x sandbox cells, completing the full matrix.chore/add-remote-tools-gateuntil the relay-client shim lands.