Compact request event history in role prompts

[rica-v3]

Summary

• Add global prompt_context configuration with defaults enabled: true, recent_events: 8, and max_events: 16.
• Project long request histories for model prompts by keeping the recent tail and backfilling the newest older evidence for roles missing from that tail.
• Apply the shared projection to normal role tasks, contract repairs, research decisions, and version-controller prompts.
• Add a content-free compaction notice with total/included/omitted counts and the canonical request-record path.
• Document compaction, backfill, an exact input/output example, rollback, and telemetry comparison guidance outside the README.

Behavior and boundaries

• Persisted .teams_runtime/requests/<request_id>.json records are unchanged and retain every event.
• Selected events are copied without payload truncation, summarization, or mutation.
• Deep Research payload shaping and session rollover are unchanged.
• Config changes require role-service restart.
• Rollback is prompt_context.enabled: false, which restores full event-history prompt inclusion.

Selection policy

1. Include the final recent_events entries by list position.
2. Seed roles already represented in that tail.
3. Scan older events newest-first.
4. Add the newest qualifying evidence for each missing role until max_events is reached.
5. Render selected events in their original chronological order.

Role evidence is a role_report in type or legacy event_type, or an event with non-empty payload.role and payload.status. Identity uses payload.role, then actor.

Validation

• python -m unittest discover -s teams_runtime/tests (769 tests passed)
• python -m unittest teams_runtime.tests.test_prompt_context (9 tests passed)
• python -m compileall -q teams_runtime
• git diff --check
• Synthetic 100-event prompt remains at or below 16 events and 30% of the disabled-policy prompt size.

Tracks #2.

[Copilot]

Pull request overview

This PR introduces a configurable prompt-time projection of persisted request event history to keep model prompts bounded while preserving full audit history on disk. It adds a shared selection/backfill algorithm (recent tail + newest missing role evidence), propagates configuration through runtimes, and documents how to validate and measure the impact via telemetry.

Changes:

• Add global prompt_context runtime configuration (default enabled, recent_events=8, max_events=16) and validation during config load/scaffold.
• Introduce shared/prompt_context.py to project request event histories for prompts and render a content-free compaction notice.
• Apply the projection + notice to normal role prompts, contract repair prompts, and the research decision prompt; propagate config through TeamService to model-facing runtimes; add dedicated unit tests and documentation.

Reviewed changes

Copilot reviewed 15 out of 15 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
workflows/roles/research.py	Projects request history for the research decision prompt and emits a compaction notice + runtime log line when applicable.
workflows/orchestration/team_service.py	Propagates prompt_context config into all model-facing runtimes created by TeamService.
runtime/base_runtime.py	Centralizes request projection + compaction logging and injects the notice + projected request record into normal and repair prompts.
runtime/research_runtime.py	Passes the runtime prompt_context_config through to the research decision prompt builder.
shared/prompt_context.py	Implements the projection/backfill algorithm and renders the content-free compaction notice.
shared/models.py	Adds PromptContextRuntimeConfig and wires it into TeamRuntimeConfig.
shared/config.py	Loads/validates prompt_context from team_runtime.yaml (type checks, positivity, and max_events >= recent_events).
templates/scaffold/team_runtime.yaml	Adds default prompt_context section to new scaffolds.
tests/test_prompt_context.py	Adds focused unit tests for projection/backfill behavior, prompt integration, config defaults/validation, and TeamService propagation.
models.py	Re-exports PromptContextRuntimeConfig via the compatibility module.
docs/configuration_guide.md	Documents prompt_context configuration, algorithm, and a worked example.
docs/specification.md	Updates config specification and adds prompt projection policy description.
docs/operations_guide.md	Updates operational description of prompt request records to reflect bounded projection and canonical history path.
docs/telemetry.md	Adds guidance for measuring prompt compaction impact using telemetry and runtime logs.
docs/implementation.md	Documents ownership/location of the new prompt-context projection module.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.