Shadow hire (trial agent) before promotion
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 35/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- electron, typescript
- Domain
- ai-infra-agents
Research direction
Start by reading the parent issue #117 and related issues #138 and #128 for the broader spec; the payload does not name implementation files or tests. The scope describes shadow runs across the next N tasks and a comparison view, but the required design and entry points are not identified. Done means runs cannot affect real workspaces or external systems, and the view shows diffs, tests, tokens, and verdicts with Promote and Discard options.
Written by the indexing model from the issue text.
Description
Part of #117 · beat-Paperclip spec id E24
- Priority: p2
- Labels: type:feature, area:agents, area:sandbox
- Relates to: #138, #117 (#128)
- Scope: A proposed hire or a model switch runs in shadow on the next N tasks in a sandbox, next to the incumbent. None of its output is applied. After N tasks, Muster shows scores from receipts and review, with "Promote" and "Discard".
- Acceptance:
- Shadow runs never write to the real workspace or external systems.
- The comparison view lists diffs, tests, tokens and verdicts.
Source: Paperclip issue/discussion research (docs, GitHub issues, live instance).
- Dominant language
- TypeScript
- Stars
- 3
- Forks
- 0
- Avg merge
- 17h 33m
- Merged PRs (30d)
- 163
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from musterhq/muster-code
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
musterhq/muster-code#866 ·
Maintainers usually reply within 1 day
-
p2 type:feature
Difficulty 5/5 Over a week Newbie friendliness 35/100
musterhq/muster-code#843 · 1 comment ·
Maintainers usually reply within 1 day
-
p1 type:feature
Difficulty 5/5 Over a week Newbie friendliness 25/100
musterhq/muster-code#840 ·
Maintainers usually reply within 1 day
-
p1 type:feature
Difficulty 5/5 Over a week Newbie friendliness 30/100
musterhq/muster-code#829 ·
Maintainers usually reply within 1 day
-
type:bug
Difficulty 3/5 1-2 days Newbie friendliness 70/100
musterhq/muster-code#815 ·
Maintainers usually reply within 1 day
All issues in musterhq/muster-code
Similar issues
-
[analytics-core] getQueryParams does not decode `+` as space and truncates values containing `=`Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
amplitude/Amplitude-TypeScript#2179 · 1 comment ·
Maintainers usually reply within 2 days
-
ci good first issue severity: low
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
TMHSDigital/GH-Arcade#111 ·
-
AsnIntegerConverter.toASN coerces strings with +value, rounding integers outside safe-integer rangeOpen
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
PeculiarVentures/asn1-schema#189 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 4 days
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100