FE-698: On more context pack + spec for agent CLI v1

[lunelson]

No description provided.

[lunelson]

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

• FE-705: Plan agent capability CLI frontier #127
• FE-698: On more context pack + spec for agent CLI v1 #114 👈 (View in Graphite)
• FE-698: Prompt/context scenario substrate foundation #111
• FE-698: Agent mutation audit; tool surface design #104
• FE-698: Design/spec/plan augmentation #103
• FE-698: Scenario runner + observer scenario composition #102
• FE-698: Prompt registry + observer context-pack foundation #101
• FE-698: Prompt/context substrate planning #98
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[cursor]

PR Summary

Low Risk
Low risk: adds a new proposal-only reconciliation scenario, prompt asset, and tests without changing existing runtime flows or mutating capabilities.

Overview
Adds a new proposal-only reconciliation prompt scenario that renders open reconciliation_need items with source/target intent anchors, status/kind, and optional reasons.

Extends the scenario/context-pack types to include reconciliation, wires it into the prompt loader via a new reconciliation-system.md asset, and updates the scenario runner to emit deterministic no-provider probe artifacts with read-only capabilities. Unit tests cover both context-pack rendering and scenario artifact construction, and planning docs are updated to record the completed slice.

^{Reviewed by Cursor Bugbot for commit 582e418. Bugbot is set up for automated code reviews on this repo. Configure here.}

[augmentcode]

🤖 Augment PR Summary

Summary: Adds a proposal-only “reconciliation” prompt/context scenario to help plan how to address open reconciliation needs without mutating intent-graph truth.

Changes:

• Introduced buildReconciliationContextPack / renderReconciliationContextPack to render objectives, open reconciliation_need entries (with source/target anchors), and an explicit proposal boundary.
• Wired the new scenario through src/server/context-pack.ts, src/server/prompt-loader.ts (new reconciliation.system prompt), and src/server/scenario-runner.ts (new scenario definition + default read-only capabilities).
• Added tests covering deterministic reconciliation context rendering and probe artifact generation.
• Updated spec/plan docs to capture agent-native CLI design considerations and record the reconciliation context-pack slice completion.

Technical Notes: Reconciliation artifacts remain no-provider/proposal-only by default and expose only read-only capabilities (e.g., scenario.render, intentGraph.validateEdge).

_{🤖 Was this summary useful? React with 👍 or 👎}

[augmentcode]

Review completed. 1 suggestion posted.

Comment augment review to trigger a new review at any time.

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 76fabef. Configure here.}