MCPcopy Create free account

hub / github.com/Claw-AI-Lab/Claw-AI-Lab / functions

Functions3,044 in github.com/Claw-AI-Lab/Claw-AI-Lab

Methodhas_content
(self)
backend/agent/researchclaw/agents/code_searcher/pattern_extractor.py:54
Methodhas_critical_issues
(self)
backend/agent/researchclaw/templates/compiler.py:244
Methodhas_results
(self)
backend/agent/researchclaw/web/search.py:59
Methodhas_template_content
(self)
backend/agent/researchclaw/quality.py:65
Methodhas_token
(self)
backend/agent/researchclaw/agents/code_searcher/github_client.py:306
Methodhook
(module, inp, out)
assets/showcase/quantifying-hallucination/main.py:593
Methodhook
(module, inp, out)
assets/showcase/quantifying-hallucination/main.py:743
Methodhook
(_module, _inputs, output, idx=layer_idx)
assets/showcase/reproduce-phycustom/main.py:292
Methodintegrity_score
Fraction of verifiable citations that are verified (0.0–1.0).
backend/agent/researchclaw/literature/verify.py:98
Methodis_active
(self)
backend/agent/researchclaw/metaclaw_bridge/session.py:55
Methodis_git_repo
(self)
backend/agent/researchclaw/experiment/runner.py:98
Methodis_up
(self, name: str)
backend/agent/researchclaw/web/connectivity.py:39
Methodlessons_path
(self)
backend/agent/researchclaw/evolution.py:359
Methodload_wan_pipeline
(self)
assets/showcase/quantifying-hallucination/main.py:262
Methodlog_data
Log structured data (dict/list) as a separate JSON artifact.
backend/agent/researchclaw/pipeline/codegen/session.py:70
Methodlog_result
Log a structured result row (e.g., per-condition results).
assets/showcase/flowedit-wan21-t2v/codes/experiment_harness.py:83
Methodmatch_count
(self)
backend/agent/researchclaw/quality.py:69
Functionmock_execute_stage
(stage: Stage, **kwargs)
backend/agent/tests/test_rc_runner.py:73
Methodmock_execute_stage
(stage: Stage, **kwargs)
backend/agent/tests/test_rc_e2e_regression.py:253
Methodmock_execute_stage
(stage: Stage, **kwargs)
backend/agent/tests/test_rc_sentinel.py:75
Methodmock_raw_call
(model, messages, max_tokens, temperature, json_mode)
backend/agent/tests/test_rc_e2e_regression.py:181
Methodmock_search
(*a: Any, **kw: Any)
backend/agent/tests/test_rc_literature.py:508
Methodmock_urlopen
(req: Any, **kwargs: Any)
backend/agent/tests/test_rc_citation_verify.py:345
Methodmock_urlopen
(req, **kwargs)
backend/agent/tests/test_rc_e2e_regression.py:34
Functionmock_write_stage_to_kb
( kb_root: Path, stage_id: int, stage_name: str, run_id: str, artifact
backend/agent/tests/test_rc_runner.py:270
Methodname
(self)
backend/agent/researchclaw/pipeline/codegen/strategies/base.py:28
Methodname
(self)
backend/agent/researchclaw/pipeline/codegen/strategies/claw_agent.py:38
Methodname
(self)
backend/agent/researchclaw/pipeline/codegen/strategies/fallback.py:25
Methodok
(self)
backend/agent/researchclaw/experiment/validator.py:38
FunctiononKey
(e: React.KeyboardEvent)
frontend/src/components/ProjectPanel.tsx:135
Methodopen
(_path: Path)
backend/agent/tests/test_rc_executor.py:219
Methodorchestrate
Run the multi-agent workflow. Must be overridden.
backend/agent/researchclaw/agents/base.py:194
Functionparser
()
backend/agent/tests/test_metric_parser.py:18
Functionplot_pipeline_timeline
Horizontal bar chart showing execution time per stage.
backend/agent/researchclaw/experiment/visualize.py:517
Functionpm
()
backend/agent/tests/test_code_agent.py:82
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:511
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:531
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:581
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:611
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:648
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:801
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:854
Methodpredict
(self, sample: VideoSample)
assets/showcase/quantifying-hallucination/main.py:976
Methodpreflight
Check that acpx and the agent are available.
backend/agent/researchclaw/llm/acp_client.py:123
Functionprint_report
(run_dir: Path)
backend/agent/researchclaw/report.py:190
Functionprobe_all
Probe all endpoints concurrently and return a ConnectivityReport. Uses a thread pool so that unreachable endpoints (3s timeout each) are prob
backend/agent/researchclaw/web/connectivity.py:69
Functionprocess_request
(connection, request)
backend/services/agent_bridge.py:3319
Methodprogress
Fraction of time budget used (0.0 to 1.0).
backend/agent/researchclaw/experiment/harness_template.py:37
Methodprogress
Fraction of time budget used (0.0 to 1.0).
assets/showcase/flowedit-wan21-t2v/codes/experiment_harness.py:37
Methodproposed
Get conditions with 'proposed' role.
backend/agent/researchclaw/domains/experiment_schema.py:97
Methodquery_by_llm
Use LLM to semantically match cached results against a new experiment plan. Args: llm_chat_fn: callable(messages, system, json
backend/services/result_registry.py:115
Functionraising_executor
( _stage_dir: Path, _run_dir: Path, _config: RCConfig, _adapters: AdapterBundl
backend/agent/tests/test_rc_executor.py:563
Functionrc_config
(tmp_path: Path)
backend/agent/tests/test_rc_runner.py:18
Functionrc_config
(tmp_path: Path)
backend/agent/tests/test_rc_executor.py:41
Methodread
(self)
backend/agent/tests/test_rc_health.py:34
Methodread
(self)
backend/agent/tests/test_rc_e2e_regression.py:17
Functionreducer
(state: AppState, action: Action)
frontend/src/App.tsx:44
Methodreferences
Get conditions with 'reference' role (baselines).
backend/agent/researchclaw/domains/experiment_schema.py:92
Methodrequest_count
(self)
backend/agent/researchclaw/agents/code_searcher/github_client.py:302
Methodreturn_to_original_branch
Switch back to the branch that was active when the manager was created.
backend/agent/researchclaw/experiment/git_manager.py:88
Methodrun
(self, code: str, *, timeout_sec: int = 300)
backend/agent/researchclaw/experiment/sandbox.py:268
Functionrun_dir
(tmp_path: Path)
backend/agent/tests/test_rc_runner.py:42
Functionrun_dir
(tmp_path: Path)
backend/agent/tests/test_rc_sanitization.py:13
Functionrun_dir
(tmp_path: Path)
backend/agent/tests/test_rc_executor.py:79
Methodrun_dir
(self, tmp_path: Path)
backend/agent/tests/test_rc_executor.py:1814
Methodrun_loop
( self, initial_code: str, *, run_id: str, llm: _ChatClient | None = None )
backend/agent/researchclaw/experiment/runner.py:181
Methodrun_project
( self, project_dir: Path, *, entry_point: str = "main.py", timeout_se
backend/agent/researchclaw/experiment/sandbox.py:252
Methodrun_project
( self, project_dir: Path, *, entry_point: str = "main.py", timeout_se
backend/agent/researchclaw/experiment/colab_sandbox.py:155
Methodsave_history
(self, path: Path)
backend/agent/researchclaw/experiment/runner.py:283
Methodschedule_resume
(self, run_id: str, stage_id: int, reason: str)
backend/agent/researchclaw/adapters.py:23
Functionsearch_arxiv_advanced
Advanced arXiv search using field-specific queries. Example: search_arxiv_advanced(title="transformer", category="cs.LG")
backend/agent/researchclaw/literature/arxiv_client.py:261
Methodsearch_author
Search for an author on Google Scholar.
backend/agent/researchclaw/web/scholar.py:169
Methodsetup_method
(self)
backend/agent/tests/test_domain_detector.py:29
Methodsetup_method
(self)
backend/agent/tests/test_rc_literature.py:570
Methodside_effect
(*args, **kwargs)
backend/agent/tests/test_rc_hardware.py:194
Methodspawn
(self, name: str, command: tuple[str, ...])
backend/agent/researchclaw/adapters.py:35
Functionstage_dir
(tmp_path: Path)
backend/agent/tests/test_code_agent.py:75
Methodstep
Increment step counter. Call this once per experiment step.
backend/agent/researchclaw/experiment/harness_template.py:105
Methodsummary
(self)
backend/services/result_registry.py:170
Methodsummary
(self)
backend/services/agent_bridge.py:760
Methodtest_30_day_old_has_half_weight
(self)
backend/agent/tests/test_rc_evolution.py:78
Methodtest_90_day_old_returns_zero
(self)
backend/agent/tests/test_rc_evolution.py:83
Methodtest_ablation_trigger
When >= 4 conditions, an ablation figure should be added.
backend/agent/tests/test_decision_agent.py:191
Methodtest_abstract_empty
(self)
backend/agent/tests/test_rc_literature.py:726
Methodtest_abstract_reconstruction
(self)
backend/agent/tests/test_rc_literature.py:719
Methodtest_abstract_structure_block_exists
(self)
backend/agent/tests/test_rc_executor.py:2198
Functiontest_adapter_bundle_defaults_are_recording_types
()
backend/agent/tests/test_rc_adapters.py:16
Methodtest_adds_broader_queries
(self)
backend/agent/tests/test_rc_executor.py:1843
Methodtest_adds_survey_benchmark_variants
(self)
backend/agent/tests/test_rc_executor.py:1863
Functiontest_advance_rejects_unknown_transition_event_string
()
backend/agent/tests/test_rc_stages.py:247
Methodtest_agent_writes_attempt_directories
( self, stage_dir: Path, pm: PromptManager, )
backend/agent/tests/test_code_agent.py:461
Functiontest_all_23_stages_mapped
All 23 pipeline stages should have a mapping entry.
backend/agent/tests/test_metaclaw_bridge/test_stage_skill_map.py:10
Functiontest_all_adapters_start_with_empty_call_lists
()
backend/agent/tests/test_rc_adapters.py:84
Methodtest_all_aliases_resolve
(self)
backend/agent/tests/test_rc_templates.py:177
Methodtest_all_fields
(self)
backend/agent/tests/test_prompt_adapter.py:30
Methodtest_all_keys_missing
\\cite{missing1, missing2} should be entirely removed.
backend/agent/tests/test_v6_improvements.py:145
Methodtest_all_keys_valid
When all keys are valid, tex should remain unchanged (except whitespace).
backend/agent/tests/test_v6_improvements.py:153
Methodtest_all_loaded_domains_have_docker_mapping
All domain profiles should have a docker mapping.
backend/agent/tests/test_universal_codegen_integration.py:379
Methodtest_all_methods_return_empty
(self)
backend/agent/tests/test_prompt_adapter.py:63
Methodtest_all_phases_end_to_end
( self, stage_dir: Path, pm: PromptManager, )
backend/agent/tests/test_code_agent.py:426
← previousnext →1,601–1,700 of 3,044, ranked by callers