2026-02-02 - 2026-08-02

Overview

39 Active Pull Requests
54 Active Issues
Excluding merges, 6 authors have pushed 162 commits to master and 176 commits to all branches. On master, 594 files have changed and there have been 203171 additions and 28591 deletions.

36 Pull requests merged by 3 users

Merged #85 feat(agents): add offset-based pagination to file_read 2026-07-31 10:14:14 +00:00

Merged #84 feat(agents): surface timeout budget in tool schemas and errors 2026-07-31 08:31:16 +00:00

Merged #80 feat(graph): enforce USD budget at each agent invocation with pre-flight gate 2026-07-12 19:15:50 +00:00

Merged #81 feat(langgraph): implement real type:tool graph node execution via ToolAgent dispatch 2026-07-09 14:31:56 +00:00

Merged #74 feat(agents): add tool_agent_class parameter to AgentFactory and create_executor 2026-07-08 09:44:17 +00:00

Merged #72 fix(nodes): propagate ExecutionError from retry mechanism instead of swallowing it 2026-07-07 16:06:09 +00:00

Merged #70 feat(agents): add LLM agent retry mechanisms with exponential backoff 2026-07-03 15:21:51 +00:00

Merged #68 feat(agents): add tool-call support to LLMAgent.stream_message 2026-07-03 05:51:32 +00:00

Merged #66 fix(actors): llm token consumption undercounted 2026-07-01 14:44:39 +00:00

Merged #64 fix(agents): validate tool name against declared tools list before dispatch 2026-06-30 11:28:31 +00:00

Merged #62 feat(tool-loop): add token-budget awareness and tool output pruning 2026-06-26 17:41:56 +00:00

Merged #60 feat(agents): implement multi-turn tool-call loop and sandbox improvements 2026-06-23 11:59:40 +00:00

Merged #58 fix(llmagent): do not close shared cached httpx clients in cleanup() 2026-06-18 05:24:18 +00:00

Merged #52 docs(registry): add MkDocs API documentation and usage examples for Package Registry Client 2026-06-17 14:09:28 +00:00

Merged #50 test(robot): add end-to-end integration tests for email categorization actor graph 2026-06-16 08:28:49 +00:00

Merged #47 feat(registry): implement local namespace reference resolution 2026-06-12 16:21:57 +00:00

Merged #45 feat(streaming): add Executor.execute_stream() returning AsyncIterator[str] for token-by-token delivery 2026-06-12 12:29:49 +00:00

Merged #43 feat(registry): implement RegistryError hierarchy with typed exceptions 2026-06-11 20:23:43 +00:00

Merged #42 feat(registry): implement RegistryCache with LRU eviction and TTL 2026-06-11 19:35:22 +00:00

Merged #44 feat(execution-limits): add structured ExecutionError kind/reason fields; enforce all 5 execution limits in PureLangGraph 2026-06-11 11:05:30 +00:00

Merged #41 feat(ActorResult): implement ActorResult and NodeUsage types; capture per-node token counts from LangChain responses 2026-06-11 03:25:35 +00:00

Merged #35 feat(registry): extend TemplateType and integrate PackageReference into template system 2026-06-10 12:10:12 +00:00

Merged #37 feat(registry): implement ReferenceResolver with version alias resolution 2026-06-10 11:29:29 +00:00

Merged #36 feat(registry): implement Canonicalizer with NFC normalization and SHA-1 hashing 2026-06-10 10:58:39 +00:00

Merged #38 feat(create_executor): implement create_executor() factory and Executor.execute() returning ActorResult 2026-06-10 10:18:35 +00:00

Merged #40 fix(runtime): add input validation, credential safety, and proper error propagation 2026-06-09 15:20:55 +00:00

Merged #20 feat(credentials): refactor LLMAgent/AgentFactory for per-request credential injection and extended provider routing 2026-06-08 11:21:03 +00:00

Merged #31 feat(registry): add PackageType, PackageId, PackageReference, PackageContent core types 2026-06-06 18:32:47 +00:00

Merged #34 test(runtime): add BDD coverage tests for runtime Executor API 2026-06-05 23:05:07 +00:00

Merged #32 feat(registry): implement async RegistryClient using httpx 2026-06-05 22:27:54 +00:00

Merged #18 feat(validate_dict): expose public validate_dict(config_dict, platform_limits) API 2026-06-05 10:19:26 +00:00

Merged #21 chore(merge_configs): remove bot-introduced duplicate from runtime.py and restore canonical import 2026-06-05 06:17:14 +00:00

Merged #19 feat(merge_configs): expose public merge_configs(*dicts) API per §3.1 deep-merge algorithm 2026-06-03 15:31:41 +00:00

Merged #7 fix(compiler): thread actor-level system_prompt into graph node metadata 2026-05-22 07:08:20 +00:00

Merged #5 fix: sync doc with extraction scope, remove boundary violation, add ProviderRegistryPort 2026-05-22 03:25:52 +00:00

Merged #3 docs(my-actor.yaml): add an example actor 2026-05-20 17:56:55 +00:00

3 Pull requests proposed by 2 users

37 Issues closed from 4 users

Closed #91 Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 19:24:40 +00:00

Closed #90 Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 19:22:30 +00:00

Closed #83 feat(agents): add offset-based pagination to file_read 2026-07-31 10:14:15 +00:00

Closed #82 feat(agents): surface timeout budget in tool schemas and errors 2026-07-31 08:31:17 +00:00

Closed #76 Enforce USD budget at each agent invocation (incl. pruning): skip pruning when tripped, fail immediately with no retries at zero/negative balance 2026-07-12 19:15:50 +00:00

Closed #75 Implement real type: tool graph node execution by wiring NodeConfig.tool to ToolAgent._execute_tool 2026-07-09 14:31:57 +00:00

Closed #73 Add tool_agent_class parameter to AgentFactory and create_executor to support runtime-injected ToolAgent subclasses 2026-07-08 09:44:17 +00:00

Closed #71 ConnectionError retry exhaustion silently swallowed, producing empty response instead of propagating ExecutionError 2026-07-07 16:06:09 +00:00

Closed #69 LLM Agent Communication Retry Mechanisms with Exponential Backoff 2026-07-03 15:21:51 +00:00

Closed #67 Add tool-call support to LLMAgent.stream_message 2026-07-03 05:51:32 +00:00

Closed #65 bug(agents): LLM token consumption undercounted — pruning model calls untracked, earlier loop rounds overwritten 2026-07-01 14:44:39 +00:00

Closed #63 fix(agents): validate LLMAgent tool dispatch against declared tools list 2026-06-30 11:28:31 +00:00

Closed #61 feat(tool-loop): add token-budget awareness and tool output pruning 2026-06-26 17:41:56 +00:00

Closed #59 LLMAgent does not implement tool calling — tools configs silently ignored 2026-06-23 11:59:40 +00:00

Closed #57 LLMAgent.cleanup() closes shared cached httpx clients, breaking subsequent LLM requests 2026-06-18 05:24:18 +00:00

Closed #51 docs(registry): write MkDocs API documentation with examples for Package Registry Client (Epic #22) 2026-06-17 14:09:28 +00:00

Closed #30 test(robot): add end-to-end integration tests for email categorization actor graph 2026-06-16 08:28:49 +00:00

Closed #46 feat(registry): implement local: namespace reference resolution with filesystem + canonicalization 2026-06-12 16:21:57 +00:00

Closed #16 feat(streaming): add Executor.execute_stream() returning AsyncIterator[str] for token-by-token delivery 2026-06-12 12:29:49 +00:00

Closed #29 feat(registry): implement error hierarchy — RegistryError base + all 8 error types 2026-06-11 20:23:43 +00:00

Closed #28 feat(registry): implement client-side LRU cache with TTL and ID validation 2026-06-11 19:35:22 +00:00

Closed #15 feat(execution-limits): add structured ExecutionError kind/reason fields; enforce all 5 execution limits in PureLangGraph 2026-06-11 11:05:30 +00:00

Closed #14 feat(ActorResult): implement ActorResult and NodeUsage types; capture per-node token counts from LangChain responses 2026-06-11 03:25:35 +00:00

Closed #27 feat(registry): extend TemplateType and integrate PackageReference into template system 2026-06-10 12:10:12 +00:00

Closed #26 feat(registry): implement reference resolution — parse refs, version aliases, local scheme 2026-06-10 11:29:29 +00:00

Closed #25 feat(registry): implement canonicalization engine — NFC, key sorting, RFC-8785, SHA-1 2026-06-10 10:58:39 +00:00

Closed #13 feat(create_executor): implement create_executor() factory and Executor.execute() returning ActorResult 2026-06-10 10:18:35 +00:00

Closed #39 fix(runtime): add input validation, credential safety, and proper error propagation 2026-06-09 15:20:55 +00:00

Closed #12 feat(credentials): refactor LLMAgent/AgentFactory for per-request credential injection and extended provider routing 2026-06-08 11:21:03 +00:00

Closed #23 feat(registry): add core data types — PackageType, PackageId, PackageReference, PackageContent 2026-06-06 18:32:47 +00:00

Closed #33 test: Coverage increase 2026-06-05 23:05:07 +00:00

Closed #24 feat(registry): implement async HTTP client using httpx 2026-06-05 22:27:54 +00:00

Closed #10 feat(validate_dict): expose public validate_dict(config_dict, platform_limits) API 2026-06-05 10:19:26 +00:00

Closed #11 feat(merge_configs): expose public merge_configs(*dicts) API per §3.1 deep-merge algorithm 2026-06-05 06:17:14 +00:00

Closed #6 compile_actor() drops graph-level system_prompt — not threaded into CompiledActor 2026-05-22 07:08:20 +00:00

Closed #4 Design doc gaps and boundary violations in cleveractors-core 2026-05-22 03:25:52 +00:00

Closed #1 Following instructions in docs/index.md or README causes error. 2026-05-20 17:56:55 +00:00

54 Issues created by 4 users

Opened #1 Following instructions in docs/index.md or README causes error. 2026-05-18 22:27:48 +00:00

Opened #2 Clever Actors only accepts GRAPH actors, not LLM actors. 2026-05-19 00:49:44 +00:00

Opened #4 Design doc gaps and boundary violations in cleveractors-core 2026-05-21 05:51:43 +00:00

Opened #6 compile_actor() drops graph-level system_prompt — not threaded into CompiledActor 2026-05-21 08:50:00 +00:00

Opened #8 cleveractors.langgraph provides no StateGraph bridge — host applications must walk CompiledActor nodes manually 2026-05-22 06:58:31 +00:00

Opened #9 Align cleveractors-core to The Actor Configuration Standard v1.0.0 2026-05-27 07:44:46 +00:00

Opened #10 feat(validate_dict): expose public validate_dict(config_dict, platform_limits) API 2026-06-03 05:58:41 +00:00

Opened #11 feat(merge_configs): expose public merge_configs(*dicts) API per §3.1 deep-merge algorithm 2026-06-03 05:58:51 +00:00

Opened #12 feat(credentials): refactor LLMAgent/AgentFactory for per-request credential injection and extended provider routing 2026-06-03 05:59:08 +00:00

Opened #13 feat(create_executor): implement create_executor() factory and Executor.execute() returning ActorResult 2026-06-03 05:59:22 +00:00

Opened #14 feat(ActorResult): implement ActorResult and NodeUsage types; capture per-node token counts from LangChain responses 2026-06-03 05:59:42 +00:00

Opened #15 feat(execution-limits): add structured ExecutionError kind/reason fields; enforce all 5 execution limits in PureLangGraph 2026-06-03 06:00:01 +00:00

Opened #16 feat(streaming): add Executor.execute_stream() returning AsyncIterator[str] for token-by-token delivery 2026-06-03 06:00:17 +00:00

Opened #17 feat(public-api): expose all router-facing APIs at cleveractors package level; update README 2026-06-03 06:00:27 +00:00

Opened #22 Epic: Package Registry Client — Support Package Registry Standard v1.0.0 2026-06-05 17:33:15 +00:00

Opened #23 feat(registry): add core data types — PackageType, PackageId, PackageReference, PackageContent 2026-06-05 17:33:48 +00:00

Opened #24 feat(registry): implement async HTTP client using httpx 2026-06-05 17:33:56 +00:00

Opened #25 feat(registry): implement canonicalization engine — NFC, key sorting, RFC-8785, SHA-1 2026-06-05 17:34:02 +00:00

Opened #26 feat(registry): implement reference resolution — parse refs, version aliases, local scheme 2026-06-05 17:34:10 +00:00

Opened #27 feat(registry): extend TemplateType and integrate PackageReference into template system 2026-06-05 17:34:19 +00:00

Opened #28 feat(registry): implement client-side LRU cache with TTL and ID validation 2026-06-05 17:34:25 +00:00

Opened #30 test(robot): add end-to-end integration tests for email categorization actor graph 2026-06-05 17:34:42 +00:00

Opened #29 feat(registry): implement error hierarchy — RegistryError base + all 8 error types 2026-06-05 17:34:42 +00:00

Opened #33 test: Coverage increase 2026-06-05 20:56:36 +00:00

Opened #39 fix(runtime): add input validation, credential safety, and proper error propagation 2026-06-09 14:49:32 +00:00

Opened #46 feat(registry): implement local: namespace reference resolution with filesystem + canonicalization 2026-06-11 20:27:00 +00:00

Opened #49 refactor(application): move ReactiveCleverAgentsApp verbosity logging to child logger to stop mutating root logger 2026-06-12 17:38:29 +00:00

Opened #51 docs(registry): write MkDocs API documentation with examples for Package Registry Client (Epic #22) 2026-06-12 22:00:59 +00:00

Opened #53 Docs(README): Quickstart is incomplete and wrong. 2026-06-12 23:04:18 +00:00

Opened #54 Docs(README): "Using agents directly" has 2 problems. 2026-06-12 23:28:22 +00:00

Opened #55 DOCS(Readme.md): "LangGraph Workflows" have two problems. 2026-06-13 00:00:49 +00:00

Opened #56 DOCS(README.md): "Reactive stream routing" 2026-06-13 00:17:22 +00:00

Opened #57 LLMAgent.cleanup() closes shared cached httpx clients, breaking subsequent LLM requests 2026-06-17 16:44:36 +00:00

Opened #59 LLMAgent does not implement tool calling — tools configs silently ignored 2026-06-19 19:19:09 +00:00

Opened #61 feat(tool-loop): add token-budget awareness and tool output pruning 2026-06-23 11:23:09 +00:00

Opened #63 fix(agents): validate LLMAgent tool dispatch against declared tools list 2026-06-29 06:59:30 +00:00

Opened #65 bug(agents): LLM token consumption undercounted — pruning model calls untracked, earlier loop rounds overwritten 2026-06-30 11:21:57 +00:00

Opened #67 Add tool-call support to LLMAgent.stream_message 2026-07-02 06:42:57 +00:00

Opened #69 LLM Agent Communication Retry Mechanisms with Exponential Backoff 2026-07-02 17:36:36 +00:00

Opened #71 ConnectionError retry exhaustion silently swallowed, producing empty response instead of propagating ExecutionError 2026-07-06 17:21:13 +00:00

Opened #73 Add tool_agent_class parameter to AgentFactory and create_executor to support runtime-injected ToolAgent subclasses 2026-07-07 06:40:16 +00:00

Opened #75 Implement real type: tool graph node execution by wiring NodeConfig.tool to ToolAgent._execute_tool 2026-07-07 09:12:00 +00:00

Opened #76 Enforce USD budget at each agent invocation (incl. pruning): skip pruning when tripped, fail immediately with no retries at zero/negative balance 2026-07-07 10:06:46 +00:00

Opened #77 Epic: LLM Agent Runtime Stabilization — reliability, resource enforcement & correctness hardening 2026-07-07 10:20:52 +00:00

Opened #78 Invert default exception handling: stop swallowing by default; catch only recoverable exceptions and propagate the rest 2026-07-07 11:45:02 +00:00

Opened #82 feat(agents): surface timeout budget in tool schemas and errors 2026-07-30 15:30:16 +00:00

Opened #83 feat(agents): add offset-based pagination to file_read 2026-07-30 15:47:38 +00:00

Opened #86 fix(ci): benchmark_regression job intermittently hangs/times out and never signals real regressions correctly 2026-07-31 11:54:35 +00:00

Opened #88 feat(skills): add Skill package schema and agent-side skill loading support 2026-07-31 18:08:19 +00:00

Opened #89 Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 18:50:14 +00:00

Opened #90 Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 18:50:35 +00:00

Opened #91 Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 18:50:55 +00:00

Opened #92 TDD: Graph route with an edge to a non-existent target node executes partially then exits silently instead of failing config validation 2026-07-31 18:51:29 +00:00

Opened #93 Expose sandboxed read_file/write_file helpers to inline code (Python_exec) in unsafe mode 2026-07-31 19:26:18 +00:00