Marketplace: publish DevKit 1.1.5

[Ayleovelle]

Summary

• Refresh plugins/2718lab-devkit from the published production v1.1.5 release artifact.
• Preserve the marketplace branch history and the existing .agents/plugins/marketplace.json local-source pointer and installation/authentication policy.
• Keep the primary 112-file package boundary; do not add the 16 legacy skills from the broader marketplace allowlist.

Provenance and verification

• Source implementation PR: Fast Lane: add model-neutral routing plans #27
• Source merge: 405c204af8cec1b58352b02f88e8a106d435b083
• Published release: v1.1.5 (non-draft, non-prerelease)
• Annotated tag peel: 405c204af8cec1b58352b02f88e8a106d435b083
• Release ZIP SHA-256: 8b154f0fa17ff61ece06eb0ac180534a221b5b08f0506f07d64baee483c7ce99
• Downloaded ZIP, published checksum sidecar, and deterministic build from the exact merge tree all matched that digest.
• Formal ZIP, exact main tree, and staged marketplace tree matched byte-for-byte and mode-for-mode for all 112 files.
• Path-set result: 0 missing, 0 extra, 0 mismatched; plugin version is 1.1.5.
• Marketplace manifest contract validated and remained unchanged.

Summary by Sourcery

Publish DevKit 1.1.5 with model-neutral Fast Lane routing while preserving legacy plan compatibility and execution-safety boundaries.

New Features:

• Add model-neutral Fast Lane request, decomposition plan, assignment, and model-selection record schemas for coordinator-driven routing.
• Expose APIs to prepare requests, record exact model selections, and validate selection records without granting dispatch authority.

Enhancements:

• Preserve exact legacy request-v1/work-package-v2 and plan-v2 replay behavior while enforcing version-compatible request and package pairings.
• Document coordinator-owned model selection, current dispatch-tool metadata, explicit route intents, and safe worker effort constraints.

Build:

• Bump the DevKit MCP package version to 1.1.5 and refresh its lockfile.

Documentation:

• Update the Fast Lane routing manual and contract to describe model-neutral routing and legacy compatibility.

[sourcery-ai]

Sorry @Ayleovelle, you've used your own review budget of 250,000 diff characters for the last 7 days.

You can request another review in 6 days and 8 hours by commenting @sourcery-ai review. Upgrade to get a review now.

[sourcery-ai]

Reviewer's Guide

This PR refreshes the marketplace DevKit package to the verified production v1.1.5 artifact, adding a model-neutral Fast Lane request/plan workflow with strict schema pairing, coordinator-owned model selection, hash-bound validation, and preserved legacy replay semantics, while retaining the existing marketplace boundary and policy contracts.

Sequence diagram for model-neutral Fast Lane planning and selection

sequenceDiagram
    participant Coordinator
    participant DevKit as DevKit Fast Lane
    participant Dispatch as collaboration.spawn_agent

    Coordinator->>DevKit: prepare_model_neutral_fast_lane_request(request)
    DevKit-->>Coordinator: fast-lane-request-v2 + work-package-v3
    Coordinator->>DevKit: compile_fast_lane(request-v2)
    DevKit-->>Coordinator: fast-lane-plan-v3
    Note over Coordinator,DevKit: Assignments remain plan_only and unselected
    Coordinator->>DevKit: record_model_selection(assignment, model_id, reasoning_effort, selection_reason)
    DevKit-->>Coordinator: model-selection-record-v1
    Coordinator->>Dispatch: Dispatch selected model and effort
    Dispatch-->>Coordinator: Dispatch result

Loading

File-Level Changes

Change	Details	Files
Introduce a model-neutral Fast Lane request and planning path while preserving legacy v1/v2 replay behavior.	Add request-v2/work-package-v3 and plan-v3 schema handling with strict version pairing. Translate legacy decomposition output into route requirements without exposing model brands. Generate coordinator-owned, unselected model choices gated by dispatch-tool metadata. Bind explicit model selections to assignment and requirement hashes without granting execution authority.	plugins/2718lab-devkit/mcp-tools/devkit_fastlane/scripts/team_efficiency.py plugins/2718lab-devkit/mcp-tools/devkit_fastlane/__init__.py
Strengthen validation and safety boundaries for the new model-selection workflow.	Validate route intents, route requirements, model-selection state, selection records, assignment identities, and version-specific plan contracts. Preserve plan-only, unclaimed, non-dispatched execution state and reject silent fallback for explicit intents. Expose conversion and selection APIs for callers.	plugins/2718lab-devkit/mcp-tools/devkit_fastlane/scripts/team_efficiency.py plugins/2718lab-devkit/mcp-tools/devkit_fastlane/__init__.py
Document the new model-neutral Fast Lane contract and its coexistence with legacy contracts.	Describe request-v2 preparation, coordinator selection, dispatch metadata ownership, and explicit-intent behavior. Clarify that legacy request-v1/plan-v2 records remain byte- and semantically stable. Update CLI/MCP behavior and schema terminology for plan-v2 versus plan-v3.	plugins/2718lab-devkit/mcp-tools/devkit_fastlane/FASTLANE_CONTRACT.md plugins/2718lab-devkit/skills/fast-lane-routing/SKILL.md
Publish the plugin as DevKit version 1.1.5.	Update the MCP package version from 1.1.4 to 1.1.5. Refresh the lockfile and plugin metadata as part of the production release artifact.	plugins/2718lab-devkit/mcp-tools/pyproject.toml plugins/2718lab-devkit/mcp-tools/uv.lock plugins/2718lab-devkit/.codex-plugin/plugin.json

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.