fix(cli): implement real actor execution and spec-required output panels in agents session tell #3473

Open
freemo wants to merge 2 commits from fix/session-tell-stub-missing-panels-and-actor-execution into master

2 Commits

Author SHA1 Message Date
controller-ci-rerun 939ae2092c chore: re-trigger CI [controller]
CI / lint (pull_request) Successful in 53s
CI / quality (pull_request) Successful in 55s
CI / typecheck (pull_request) Successful in 1m5s
CI / helm (pull_request) Successful in 27s
CI / security (pull_request) Successful in 1m5s
CI / build (pull_request) Successful in 30s
CI / e2e_tests (pull_request) Failing after 17m41s
CI / integration_tests (pull_request) Failing after 18m8s
CI / unit_tests (pull_request) Failing after 18m9s
CI / benchmark-publish (pull_request) Has been skipped
CI / docker (pull_request) Has been skipped
CI / benchmark-regression (pull_request) Failing after 39s
CI / coverage (pull_request) Failing after 15m48s
CI / status-check (pull_request) Has been cancelled
2026-06-18 10:58:29 -04:00
freemo e1ce238985 fix(cli): implement real actor execution and spec-required output panels in agents session tell
CI / lint (pull_request) Successful in 28s
CI / typecheck (pull_request) Successful in 47s
CI / quality (pull_request) Successful in 36s
CI / security (pull_request) Successful in 1m3s
CI / build (pull_request) Successful in 28s
CI / helm (pull_request) Successful in 24s
CI / unit_tests (pull_request) Failing after 6m48s
CI / docker (pull_request) Has been skipped
CI / coverage (pull_request) Successful in 10m36s
CI / e2e_tests (pull_request) Successful in 17m29s
CI / integration_tests (pull_request) Failing after 22m3s
CI / status-check (pull_request) Failing after 1s
CI / benchmark-publish (pull_request) Has been skipped
CI / benchmark-regression (pull_request) Successful in 57m15s
Replace stub actor execution in `agents session tell` with real LLM invocation
via the provider registry. Implement all four spec-required Rich output panels:
Plan Request, Commands Executed, Result, and Usage.

Key changes:
- Add `_invoke_actor_llm()` helper that invokes the configured LLM actor with
  session history as context, falling back gracefully if no provider is configured
- Implement non-streaming mode with four Rich panels per spec §"agents session tell"
- Implement streaming mode with Session panel, real-time token streaming, Usage panel,
  and "✓ OK Stream complete" success message
- Add `--format` option supporting json/yaml/plain output paths with structured data
- Update existing Behave tests to match new panel-based output
- Add new `session_tell_panels.feature` with comprehensive panel coverage scenarios
- Update Robot Framework helper to verify Plan Request panel instead of stub output
- Update coverage boost and uncovered branches step files to mock `service.get()`
  and `service.update_token_usage()` which are now called by the tell command

ISSUES CLOSED: #3430
2026-04-05 21:34:35 +00:00