FN-7776: evaluate promptContribution.condition against effective plugin settings
Plugin prompt contributions declared a `condition` field in the SDK, but the host never evaluated it, so gated prompt content always rendered unconditionally.
- Add packages/core/src/plugin-prompt-condition.ts implementing a minimal, non-eval `settings["key"] === "value"` / `!==` condition grammar
- Wire condition evaluation into plugin-runner.ts / agent-instructions.ts / executor.ts / reviewer.ts / triage.ts / agent-heartbeat.ts so prompt contributions are filtered by effective plugin settings at each call site
- Extend plugin-types.ts and core index.ts/index.gate.ts to expose the new evaluator and condition typing
- Document the condition grammar in docs/PLUGIN_AUTHORING.md
- Add regression tests covering the evaluator and its wiring through plugin-runner and agent-instructions
- Add changeset (@runfusion/fusion minor, feature) describing the new gating behavior
Files changed:
.changeset/fn-7776-prompt-condition.md | 7 ++
docs/PLUGIN_AUTHORING.md | 13 ++-
.../src/__tests__/plugin-prompt-condition.test.ts | 90 ++++++++++++++++++++
packages/core/src/index.gate.ts | 6 ++
packages/core/src/index.ts | 6 ++
packages/core/src/plugin-prompt-condition.ts | 51 +++++++++++
packages/core/src/plugin-types.ts | 10 ++-
.../src/__tests__/agent-instructions.test.ts | 33 ++++++--
.../engine/src/__tests__/plugin-runner.test.ts | 98 +++++++++++++++++++++-
packages/engine/src/agent-heartbeat.ts | 2 +-
packages/engine/src/agent-instructions.ts | 6 +-
packages/engine/src/executor.ts | 28 +++++--
packages/engine/src/plugin-runner.ts | 64 ++++++++++++--
packages/engine/src/reviewer.ts | 2 +-
packages/engine/src/triage.ts | 2 +-
packages/plugin-sdk/src/index.ts | 4 +
16 files changed, 385 insertions(+), 37 deletions(-)
Fusion-Task-Id: FN-7776
Fusion-Task-Lineage: ba8dcd52-260a-4166-a712-f3dd39b81b15
Co-authored-by: Fusion (runfusion.ai) <noreply@runfusion.ai>
57c3d7ceb8