freemo/cleveragents-core
0
0
Fork 0
forked from cleveragents/cleveragents-core
Code Pull Requests Activity
1,442 Commits 352 Branches 3 Tags
task/ci-matrix-strategy-python-versions
Commit Graph

1442 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
brent.edwards f48eb5a05f feat(cli): add interactive repl 
Implement `agents repl` command providing an interactive read-eval-print
loop that dispatches to existing CLI commands without the `agents` prefix.

Features:
- Command dispatch via existing Typer app
- readline history with --no-history opt-out (default: ~/.cleveragents/history)
- Tab-completion for all CLI commands and built-in commands
- !! last-command repetition
- Prompt context from CLEVERAGENTS_PROJECT / CLEVERAGENTS_PLAN env vars
- Ctrl+C (continue) and Ctrl+D (exit) signal handling
- Multi-line input with \ continuation
- :help and :exit/:quit built-in commands

Test coverage:
- 15 Behave scenarios (features/repl.feature)
- 10 Robot Framework smoke tests (robot/repl_smoke.robot)
- ASV benchmark suite (benchmarks/repl_bench.py)
- All nox sessions pass: lint, typecheck, unit_tests, integration_tests
- Coverage: 97.2% (threshold: 97%)
 2026-02-23 03:11:12 +00:00
freemo 18b7cf8107 Docs: daily update to implementation plan 2026-02-22 17:12:54 -05:00
freemo e24c7bf731 Fix: Fixed lint again 2026-02-22 16:15:49 -05:00
freemo 41ca082022 Tests: Improved coverage to get us back above 97% 2026-02-22 15:29:41 -05:00
freemo 92c83ecc7e Fix: Fixed linting errors 2026-02-22 14:18:24 -05:00
freemo a0000afc72 fix: update Robot helper and CLI to use target_decision_id, fix lint import order 
- robot/helper_correction_model.py: decision_id -> target_decision_id in all
  request_correction calls; update validate_guidance test to accept empty
  guidance (M4.2 allows it); remove unused ValidationError import
- robot/correction_model.robot: update Validate Empty Guidance doc string
- src/cleveragents/cli/commands/plan.py: decision_id -> target_decision_id
- src/cleveragents/cli/main.py: fix import ordering (invariant before lsp)
 2026-02-22 18:47:41 +00:00
freemo 029f09db1c fix: update M4.1 scenarios for M4.2 allowing empty/whitespace guidance in request_correction 2026-02-22 17:56:18 +00:00
freemo 8182ac2917 fix: update M4.1 tests for M4.2 CorrectionRequest empty guidance now allowed 2026-02-22 17:41:10 +00:00
freemo 50e5bd6f9b fix: update M4.1 step file to use target_decision_id matching M4.2 CorrectionService API 2026-02-22 17:38:43 +00:00
freemo 787ee5d0dd fix: rename ACP 'a ValueError should be raised' step to avoid AmbiguousStep with LSP step 2026-02-22 17:22:52 +00:00
freemo f1f68804ed fix: rename 'I try to get correction' step to 'correction flow' prefix to avoid AmbiguousStep 2026-02-22 17:15:51 +00:00
freemo 2097a548d8 docs: mark M1.2, M4.2, M6.1 checklist items as complete (PRs #149, #147, #148) 2026-02-22 17:11:22 +00:00
freemo dd3c70665e Merge remote-tracking branch 'origin/feature/m6-acp-stubs' into feature/jeff-combined-day14-batch2 2026-02-22 17:05:00 +00:00
freemo ee67ecb7cb merge: resolve M4.1+M4.2 conflicts (M4.2 supersedes M4.1 models/service) 2026-02-22 17:04:03 +00:00
freemo e2fa756be4 merge: resolve M1.2 conflict in services/__init__.py 2026-02-22 16:54:36 +00:00
freemo 9371992525 Merge remote-tracking branch 'origin/feature/m5-automation-profiles' into feature/jeff-combined-day14-batch2 2026-02-22 16:50:42 +00:00
freemo 5946dcc636 merge: resolve M3.5+M4.1 conflict in services/__init__.py 2026-02-22 16:49:56 +00:00
freemo 62605bc6f8 merge: resolve M2.7+M3.5 conflict in cli/main.py 2026-02-22 16:46:07 +00:00
freemo dc2a42889a Merge remote-tracking branch 'origin/feature/m2-lsp-stubs' into feature/jeff-combined-day14-batch2 2026-02-22 16:43:52 +00:00
freemo 33a5adcfee feat(M4.2): Correction service with revert/append BFS + dry-run 
Adds CorrectionRequest, CorrectionResult, CorrectionMode,
CorrectionPatch, CorrectionDryRunReport, CorrectionNotFoundError,
and CorrectionConflictError domain models.

Implements CorrectionService with BFS-based revert (marks decisions
as rolled back and restores via inverse changes) and append mode
(spawns a child correction plan).  Includes request_correction()
with dry-run support and dispatch_correction() convenience method.

33 Behave scenarios, 8 Robot smoke tests, ASV benchmark suite,
and reference documentation.

Ref: Day-14 Rebaseline – M4.2 Decision-correction flows [Jeff]
 2026-02-22 16:40:06 +00:00
freemo a2da043cbd feat(M1.2): PlanExecutionContext, RuntimeExecuteActor, and runtime mode 
Adds PlanExecutionContext carrying plan metadata and delegating
changeset ops to ChangeSetStore.  RuntimeExecuteResult captures
execution output (changeset_id, tool_call_count, sandbox_refs,
decision_ids_processed, execution_duration_ms).

RuntimeExecuteActor dispatches StrategyDecision lists through
ToolRunner with full changeset capture and optional streaming
callbacks.  PlanExecutor gains execution_context param with
has_runtime / changeset_store / execution_context properties
and _run_execute_with_runtime / _run_execute_with_stub split.

31 Behave scenarios, 5 Robot smoke tests, ASV benchmark suite,
and reference documentation.

Ref: Day-14 Rebaseline – M1.2 Plan-execute runtime wiring [Jeff]
 2026-02-22 15:13:43 +00:00
freemo 7153050211 feat(M6.1): ACP facade stubs with transport, events, and versioning 
Adds cleveragents.acp package with seven modules: models (AcpMessage,
AcpEnvelope, AcpCapability, AcpPeerInfo), errors (AcpError hierarchy),
facade (AcpFacade with register/discover/send/receive), transport
(AcpTransportBase, LoopbackTransport), events (AcpEventBus),
and versioning (AcpVersion with compatible_with check).

44 Behave scenarios, 5 Robot smoke tests, ASV benchmark suite,
and reference documentation.

Ref: Day-14 Rebaseline – M6.1 ACP-facade stubs [Jeff]
 2026-02-22 15:02:19 +00:00
freemo 67bd287a6c feat(correction): add correction model and CLI hooks 2026-02-22 11:07:35 +00:00
freemo cbb985627d feat(automation): add automation profiles and guards 2026-02-22 10:19:43 +00:00
freemo 50316e97be feat(lsp): add registry and runtime stubs 2026-02-22 10:15:25 +00:00
freemo 2d4b330f75 feat(invariant): add invariant models and enforcement 2026-02-22 09:23:35 +00:00
freemo c6d831b5ff feat(actor): add tool-calling runtime for execution actors 2026-02-22 08:31:45 +00:00
freemo e40dd75478 Docs: Fixed broken navigation menu on mobile 2026-02-22 01:15:07 -05:00
freemo 431f827ac4 Docs: Added implementation timeline to specification, seperate from the implementation plan itself. 2026-02-22 01:15:03 -05:00
freemo ca1c341b18 Tests: Significantly improved coverage of the unit tests 2026-02-22 00:43:08 -05:00
freemo e3aa0984bb Docs: Updated implementation plan to include missing v2 actor functionality 2026-02-21 21:44:18 -05:00
freemo e28f9a8597 Docs: Add resource DAG operational semantics, tool reachability, cross-mechanism coordination, container, and LSP resource type ADRs (036-040) 
- ADR-036: Resource DAG Operational Semantics (10 purposes, sandbox boundary algebra)
- ADR-037: Tool Reachability and Access Projection (transitive reach, read/write routing)
- ADR-038: Cross-Mechanism Sandbox Coordination (coherence, write-then-sync, lazy materialization)
- ADR-039: Container and Execution Environment Resource Types (9 engine-agnostic types)
- ADR-040: Language Server Protocol Resource Types (lsp-server, lsp-workspace, lsp-document)
- Updated specification.md with 7 new subsections for operational semantics
- Updated resource_dag.md reference doc with operational semantics section
- Updated ADR-008, ADR-011, ADR-015, ADR-027 with cross-references
- Resolved merge conflicts from cherry-pick renumbering (033-037 -> 036-040)
- Fixed all stale display-text references across all files
 2026-02-21 19:51:28 -05:00
freemo b4c73505d8 Docs: Fixed some contradictions and ambiguity in the specification document 2026-02-21 18:04:15 -05:00
freemo a3f4fba659 Docs: Clarified purpose of LSP server in specification 2026-02-21 18:04:12 -05:00
freemo 571d476493 Docs: Added decision tree recording and other details to the doc along with related ADR 2026-02-21 18:04:07 -05:00
CoreRasurae d37cfbe769 test(robot): fix failing integration tests related to safe.directory config and git version 2026-02-21 18:11:31 +00:00
CoreRasurae c5990904fb test(robot): Disable tests that depend on code blocks 
Code blocks exec()/eval()/compile() where removed as part of m4-security-eval
 2026-02-21 16:32:11 +00:00
CoreRasurae e3ddf6c868 fix(security): remove eval-based config parsing 2026-02-21 16:32:03 +00:00
CoreRasurae ca6dbd4576 feat(skill): add skill registry persistence 2026-02-21 16:30:40 +00:00
CoreRasurae 975fbba070 feat(skill): add git operation skills 2026-02-21 16:30:33 +00:00
CoreRasurae 8a219286d6 feat(change): add ChangeSet models and invocation tracker 2026-02-21 16:27:40 +00:00
freemo 8892a810ff Docs: Updated implementation plan 2026-02-21 10:37:00 -05:00
freemo 34a9672e7f Chore: Fixed bad formatting 2026-02-21 10:23:33 -05:00
freemo 2980b14e7b test: boost combined branch coverage to 97% with additional behave scenarios 
Add ~60 new behave scenarios across output rendering, tool router, file ops,
and skill search features targeting uncovered lines and branches. Key additions:
- ElementHandle validation guards (empty id, type, negative index, None args)
- Handle close/context-manager edge cases
- Table list-row and batch-row coverage
- Color/box-draw/JSON/YAML materializer edge cases
- Format selection paths (detect capabilities, explicit flag, empty format)
- Session ColumnDef, double-close guard, force-close open handles
- Tool router schema export and provider format scenarios
- File ops edge cases and search stat-failure/glob-include tests

All nox checks pass: lint, typecheck (0 errors), unit_tests (4730 scenarios),
coverage_report (97.0% >= 97% threshold).
 2026-02-21 10:23:33 -05:00
freemo 2881b0cf7a fix(test): resolve ambiguous behave step in combined branch merge 2026-02-21 10:23:33 -05:00
freemo 5bdca88eca feat(change): add tool router for providers 2026-02-21 10:23:31 -05:00
freemo 9f2e7e88b0 feat(plan): add diff review and apply integration 
Add PlanApplyService with diff(), artifacts(), persist_apply_summary(),
handle_merge_failure(), and guard_empty_changeset() methods.

- plan diff: renders changeset in rich/plain/json/yaml formats
- plan artifacts: shows plan metadata, changeset summary, sandbox refs
- persist_apply_summary: stores files_changed/validations_run in plan metadata
- handle_merge_failure: transitions plan to error state with conflict details
- guard_empty_changeset: blocks apply on empty changeset (--allow-empty override)

CLI: plan diff and plan artifacts commands with --format flag.
Tests: 20 Behave scenarios, 8 Robot integration tests, 4 ASV benchmarks.
Docs: docs/reference/plan_apply.md with CLI reference.

Implements D0b.apply from the implementation plan.
 2026-02-21 10:22:18 -05:00
freemo 1df21e6a64 feat(cli): add output rendering framework with materialization strategies 2026-02-21 10:19:45 -05:00
freemo eae18c7578 feat(skill): add directory and search skills 2026-02-21 10:18:26 -05:00
freemo 582af29a24 feat(skill): add file operation skills 2026-02-21 10:18:26 -05:00