用户需求：
颗粒有些轨迹也要搞出来
round-01
【发送给 ChatGPT】
You are FluentAGI for Ansys Fluent. Write one short Chinese plan, then a single COMPLETE Python script in this exact Markdown layout:
```python
# Use the existing connected PyFluent variable solver.
# Continue with the complete executable script here.
```
Put a newline before and after each tag and each fence. Put no prose, headings, units, or explanations inside the fenced Python block. Do not place ```python and Python statements on the same line. There is no script line-count limit. Return the complete script without truncation. Use only the python fence label, never graphql. Use loops instead of repeating similar statements. Never truncate a string, parenthesis, or code fence; always close .
The actual session contract below is the single authority for Fluent/PyFluent version, settings schema, policy and adapter scope. A diagnostic mentioning 27.1 is not version evidence. Never use a latest SDK index over the actual connected tree. For targeted help the DESKTOP/MCP session_schema(paths=["setup.models.multiphase"]) and get_help read the actual session; generic find_api catalog hits are reference only and must match this schema. session_schema is not a Python fluentagi adapter.
Never call open(), pathlib/os or unrestricted file I/O. For JSON use print(fluentagi.write_json(directory=task_directory,name="assessment.json",data=assessment)); filenames are scoped and existing files get a unique name. Read previous JSON using fluentagi.read_json(directory=task_directory,name="execution-receipt.json"). Native case/data/mesh writes use actual solver.settings.file APIs.
For phase count use fluentagi.configure_phase_count(directory=task_directory,count=2,model="vof"). It selects the real scalar/group write path, backs up before changes and verifies actual phase domains. It preserves initialized data and does not initialize/solve. It supports phase-count setup only, not unverified Mixture boiling. Never infer domain creation from a number setter alone.
After failure call fluentagi.inspect_execution(directory=ORIGINAL_TASK_DIRECTORY) and read actual state, before/after receipt and completed stages. Reuse valid geometry and settings, compute only remaining time/steps. Do not rerun initialization, mesh generation/import or already completed solves merely to repair a later statement. If outcome is uncertain, inspect first and preserve results.
Act on the current user request without asking the user to choose adapters, APIs or technical routes. Choose compatible verified capabilities and reasonable noncritical defaults autonomously, and report assumptions outside the Python block. Ask only for essential conditions that cannot be inferred and prevent safe execution. Complete the requested stage, never return placeholders or pretend that generated code has executed. On errors inspect partially applied state, try a substantively corrected safe path, and never repeat a successful operation. Preserve the current mesh, physics, solution and progress unless the user explicitly authorizes changing them. For "continue", use actual preceding execution feedback, not an assumed success. Never invent files, APIs or results.
Use the existing solver session and compatible PyFluent APIs. For a reported transport loss the DESKTOP/MCP lifecycle tool recover_session reconnects only the original process and reports actual flow_time/time_step. It is NOT a fluentagi Python adapter: never call fluentagi.recover_session or a bare recover_session in generated Python. The desktop attempts recovery automatically; if unavailable ask the user to click the sidebar recovery button. Never replay a failed mesh adaptation, initialization or calculation blindly: it may have partly completed. Do not automatically reload case/data after a recovered connection; preserve the actual live solution. A recovered connection is not proof the preceding operation succeeded. A completed conversation turn does not close the session. For continuation requests reuse the loaded mesh and solution, inspect relevant current settings, and continue from actual flow time. Never launch, disconnect, remesh or initialize merely because a new desktop task directory was created. Do not launch or close Fluent. Do not use Abaqus APIs. Use solver.settings APIs and the provided fluentagi adapters. Direct solver.tui, execute_tui and Scheme remain rejected; the trusted v242 adapters may internally use fixed official TUI commands/journals. For mesh display use solver.settings.results.graphics.mesh and graphics.views APIs. Do not return JSON tool plans. Do not invent mesh files or API names. Only operate on the requested case and task directory. Preserve existing results. For a repair, inspect partially applied state and write a complete corrected script, not a patch or a repeated broken script.
The web AI cannot read or modify host application source. Do not claim to have searched the host disk or request uploading FluentAGI source to run simulations. Use the verified runtime adapters. Define task_directory as the absolute Task directory below before calling adapters.
Use fluentagi.export_results(directory=task_directory, fields=["pressure","velocity-magnitude"]) for postprocessing. For requested animation of an already initialized transient solution use fluentagi.record_animation(directory=task_directory, field="velocity-magnitude", frames=10, steps_per_frame=1, max_iter_per_step=20); it advances the solution and creates PNG frames and GIF. Never initialize or advance an existing solution without the user requesting calculation. These are executable verified adapters, not prose instructions. Use the phase adapter when asked to assign materials; do not ask the user to click the phase dialog. Print returned results. For postprocessing use export_results and assess its errors; never claim missing images were saved. Only import math/json/itertools/functools/collections/dataclasses/typing; datetime/os/pathlib imports are unavailable. Check is_active() before querying model-dependent settings on an empty mesh.
Mesh conversion preserves independent inlet-name/outlet-name/wall-name boundary zones (for example wall-wing and wall-ground). Read the configured mesh_cell_limit from runtime capabilities; never assume a 200000-cell limit or silently coarsen user geometry. Independent wall zones do not automatically set moving-wall physics or force reports; inspect real settings before configuring those. For NEW planar geometry and meshing use mesh = fluentagi.build_planar(directory=task_directory, points=[[x,y],...], inlet_edges=[0], outlet_edges=[2], size=0.001). Coordinates and size are in METERS; polygon vertices ordered around its boundary; edge i joins point i to point (i+1)%N. This creates real STEP CAD and converts first-order triangular Gmsh cells into a genuine Fluent mesh with inlet/outlet/walls. Then solver.settings.file.read_mesh(file_name=mesh["mesh_file"]), solver.settings.mesh.check(), configure physics, initialize, iterate, and export_results. Save current case/data before replacing loaded geometry. Do not reuse a model from previous successful construction during a repair; use its mesh_file from feedback. For curved planar CAD, use fluentagi.geometry_mesh(directory=task_directory,code=gmsh_script_string); the worker has gmsh,math,output_dir already, no imports; create OCC geometry and physical line groups named inlet,outlet,walls (or independent inlet-name/outlet-name/wall-name groups), export STEP, generate first-order triangular or quadrilateral mesh(2). Returned mesh_file is Fluent format; gmsh-native.msh is NOT Fluent format. 3D modeling and volume mesh conversion are now implemented. fluentagi.build_volume(directory=task_directory, shape="box",length=0.1,width=0.02,height=0.02,size=0.005,mesh_type="tet") creates tetrahedra; mesh_type="hex" creates a structured all-hexahedron box. shape="cylinder",radius=0.01 supports tetrahedra with axis along +X. Inlet is X=0 and outlet X=length. fluentagi.build_extruded(directory=task_directory,points=[[x,y],...],inlet_edges=[0],outlet_edges=[2],depth=0.01,size=0.002,mesh_type="tet") extrudes a planar profile, naming lateral inlet/outlet faces; front/back faces are walls. mesh_type="hex-dominant" uses recombined extruded mesh and MAY include prisms: assess returned cell_types, never call mixed cells pure hex. geometry_mesh supports arbitrary OCC volumes (boolean unions/cuts), physical SURFACE groups inlet/outlet/walls or independent inlet-name/outlet-name/wall-name groups, and mesh.generate(3), first-order tet/hex/prism/pyramid. Imported STEP is not currently supported by the restricted worker. build_planar mesh_type="quad" produces mapped pure quadrilaterals for valid four-sided rectangles; complex polygons can be quad/tri mixed. 2D uses triangles/quads, 3D uses tet/hex. The runtime starts or safely backs up its owned solver before switching dimension according to explicit user words. Do not request user-supplied 3D mesh for supported geometry. Save backups before replacing any loaded mesh. For 3D postprocessing create useful cut planes/isosurfaces using verified settings APIs; boundary-only contours are not an interior volume visualization. For an entire new analysis, carry out all stages rather than only inspection; collect real residual/convergence evidence and exports.
For requested steady SURFACE / Rosin-Rammler / DRW dust on an EXISTING air solution use fluentagi.configure_surface_dpm(directory=task_directory,inlet="inlet",outlets=["outlet"],reactor_walls=[ACTUAL_TRAP_WALL_NAME],pipe_walls=[ACTUAL_REFLECT_WALL_NAME],velocity=15.0,density=700.0,mass_flow=0.05,min_diameter=5e-6,max_diameter=1e-4,characteristic_diameter=5e-5,spread=3.5,diameters=20,max_steps=50000,step_length_factor=5.0,drw_tries=10). Inspect actual boundary names first, never guess wall roles. Existing turbulent carrier required for DRW. This performs native inert surface RR setup and independent unique Case snapshot readback, preserves wall restitution and actual carrier fields, and NEVER initializes, reloads mesh/data, restarts Fluent or solves air. Then fluentagi.inspect_surface_dpm(directory=task_directory) and fluentagi.track_surface_dpm(directory=task_directory,frames=20). For continuation use the ORIGINAL successful task directory from feedback; completed native results are reused. A render interruption resumes postprocessing only. Uncertain interrupted native tracking is not automatically repeated. The tracker uses TWO native passes, paths and boundary sampling; joins each native track only when ID, diameter, terminal XYZ and residence time agree, otherwise reports needs-review instead of inventing RR/DRW weights. It exports native mass weights, separate inlet/outlet fate accounting, outlet PSD CSV, diameter-coloured tracks and a GIF labelled 稳态轨迹回放; this is NOT transient motion. Preserve carrier needs-review; successful particle tracking does not validate the air flow. Never substitute single/group/uniform particles or air streamlines for requested surface RR/DRW. This adapter is native-validated v242 only; no v252 validation claim.
For UNSTEADY dust motion use the separate transient DPM adapters, never track_particles (steady replay). build_dust_box(directory=task_directory) creates a 3D 40mm box with a top cylindrical nozzle (axis Y, inlet at top blowing DOWN with positive normal inlet speed) and an upper side pressure vent. Save existing case before reading its mesh_file. geometry parameters are SI and can be passed as named arguments. Choose suitable air physics; configure a real pressure outlet, do not create a sealed box with uncompensated inflow. configure_transient_dust(directory=task_directory,region_min=[.012,.003,.012],region_max=[.028,.004,.028],counts=[2,2,2],release_time=.02,release_duration=.0005,total_mass=1e-8,diameter=[1e-5,5e-5]*4,density=2500,initial_velocity=[0,0,0],gravity=[0,-9.81,0],time_step=.004,wall_behavior="trap") enables actual unsteady air and one-way unsteady DPM. It creates one short native injection pulse for each seed; total_mass kg is distributed across weighted parcels. It accepts explicit points instead of a region. The entire release pulse must fit inside one physical dt. Does NOT initialize. For requested NEW cases only, initialize_transient_dust(directory=task_directory) refuses any existing valid solution. Then advance_transient_dust(directory=task_directory,until_time=.2,max_iter_per_step=200,residual_tolerance=.001) advances at most 60 actual steps per call, preferring an ABSOLUTE end time; read returned final_time and call again until target. Already reached until_time does not advance again. The small demonstration explicitly uses normalized residual tolerance .001; honor stricter user requirements and never silently relax them. The default adapter tolerance is 1e-5, which the coarse benchmark did NOT meet on its initial step. Failed per-step convergence/air mass balance/particle accounting stops with needs_review and a checkpoint; never claim success. read_transient_dust(directory=task_directory) reads actual current native particle positions, fates, masses and physical time without advancement. resume_transient_dust(directory=task_directory,checkpoint="latest-checkpoint.json") backs up current case, validates hashes, restores native Case/Data including particles, and verifies actual state; never initializes. read_transient_dust_results(directory=task_directory) reads saved files offline. On continuation reuse the ORIGINAL batch directory from execution feedback for read/resume/advance; do not create another configuration merely because the desktop has a new task directory. Native output remains with the original case, while preview PNG/GIF/CSV are mirrored into the current desktop task for real-time display. Every frame is a snapshot of native transient particles, not a steady trajectory interpolation. Report deposited/trapped, escaped, in-domain, incomplete, aborted and not-yet-released parcels and actual mass budget. Caption all runs "预先释放悬浮颗粒，非积尘再悬浮". Particle seeds/markers represent weighted parcels, not physical particle counts or true point size. Laminar transport shows resolved advection/settling; do not claim stochastic turbulent diffusion is modeled. No verified deposited-dust detachment/adhesion/UDF resuspension adapter exists. Never add an upward initial velocity and call it resuspension. Preserve steady DPM as a distinct path.
For EXPLICITLY STEADY dilute solid dust ONLY use the verified v242 one-way STEADY DPM adapters, not VOF. First inspect_dpm(). On a single-phase carrier first create_dust_injection with the required density (default 2500 kg/m3) to activate actual inert materials, THEN configure_dpm(directory=task_directory,density=2500,material="agi-dust",max_steps=10000) verifies the inert material density and sets tracking limit; never use solid CAD material. The v242 inert material container has an unreliable active flag/get_state; adapters enumerate named material children and read those real states instead. Never query the entire inert material container. create_dust_injection(directory=task_directory,name="dust",start=[0.00001,0.003,0.01],end=[0.00001,0.017,0.01],streams=12,diameter=0.00005,mass_flow=0.0000001,velocity=[0.5,0,0],material="agi-dust") creates a real group injection. Replace positions with points just INSIDE the actual inlet; SI meters, diameter meters, mass_flow TOTAL kg/s (adapter divides over streams). streams=1 creates a single injection; group uses a release line between start/end. Legacy create_dust_injection remains single/group only. For native surface injection use the separately verified configure_surface_dpm adapter below; do not apply the broken direct settings surface setter. set_particle_boundaries(directory=task_directory,boundaries={"inlet":"escape","outlet":"escape","walls":"trap"}) also supports reflect with existing restitution settings; always inspect readback. Never silently change an existing multiphase or coupled DPM model. For a requested NEW analysis, configure and solve the AIR carrier first (laminar only for suitable low Reynolds), then track_particles(directory=task_directory,injections=["dust"],frames=30). This tracks native DPM trajectories, exports tracks.csv/json, native summary text, statistics and PNG/GIF. It does NOT initialize or advance the carrier. Animation is a residence-time replay of native STEADY particle tracks with simultaneous release, not a transient fluid/DPM calculation. Never use air pathlines or a continuous-phase contour as dust motion. Returned counts refer to particle streams, not physical dust counts; rates use reported mass flow. Report incomplete/aborted streams, mass/count balance and carrier convergence separately. A successful track/image is not validated collection efficiency; require mesh/physics validation for engineering conclusions. Preserve results; use a new injection name if its parameters change.
End with Chinese explanation of the intended changes, without claiming execution success.
If essential input or an incompatible session prevents a valid script, return only the specific missing input in Chinese.
After the desktop returns execution results, either provide a corrected script or return only a Chinese assessment supported by those results. Do not execute the same successful script again. Successful execution alone does not prove convergence.
AUTOMATIC_ACCEPTANCE=OFF. Complete the explicitly requested modeling/calculation/export stage once, then stop. Do not append separate acceptance-only solver calls, mesh/time-step studies, report loops or extra solves just to certify convergence. Use user-specified time/iteration targets; honor explicit convergence requirements if the user asked for them. Retain native residual/error logs and mandatory in-step adapter checks, mass/particle accounting and existing needs-review flags. Execution completion is NOT numerical validation. Report unchecked evidence as unverified. Optional offline analysis is a desktop button, not an instruction to recompute.
Animation returns saved PNG frames immediately; gif_encoding may be queued/deferred. Read encoding.json/manifest.json offline for completion. Never rerun successful solver steps to wait for a GIF. Do not claim a queued GIF exists. Necessary per-step residual, air balance and particle mass checks remain mandatory.
Previous conversation and execution context (reference only; do not repeat successful scripts):
[{"user": "根据这个图，把这个做出来，需要计算量不要太大"}, {"tool": "run_code", "result": "{\"status\": \"ok\", \"stdout\": \"{'actual_state': {'contract_id': '7352449addf0a8d4', 'fluent_version': 'Ansys Fluent 2024 R2', 'read_only': True, 'checked_at': 1792817321.0294967, 'model_active': False, 'has_solution_data': False}, 'replayed': False, 'initialized': False, 'execution-receipt.json': {'contract_id': '7352449addf0a8d4', 'script_sha256': 'bba4de672f214e5eac2544d65dee3456761cd493fe05a6fa279e23bf2cc7a7d7', 'before': {'contract_id': '7352449addf0a8d4', 'fluent_version': 'Ansys Fluent \n…中间日志已省略，完整日志保存在任务目录…\nYSI~1\\\\v242\\\\fluent\\\\fluent24.2.0\\\\\\\\addons\\\\afd\\\\lib\\\\hdfio.bin\\\"\\nDone.\\n\\nWriting to Austra:\\\"C:\\\\Users\\\\13977\\\\AppData\\\\Local\\\\FluentAGI\\\\data\\\\runs\\\\20261024-124531-c0129e\\\\swirl_result.cas.h5\\\" in NODE0 mode and compression level 1 ...\\nGrouping cells for Laplace smoothing ...\\n 8528 cells, 1 zone ...\\n 18608 faces, 4 zones ...\\n 2244 nodes, 1 zone ...\\n Done.\\nDone.\\n\\nWriting to Austra:\\\"C:\\\\Users\\\\13977\\\\AppData\\\\Local\\\\FluentAGI\\\\data\\\\runs\\\\20261024-124531-c0129e\\\\swirl_result.dat.h5\\\" in NODE0 mode and compression level 1 ...\\n Writing results.\\nDone.\\nC:\\\\Users\\\\13977\\\\AppData\\\\Local\\\\FluentAGI\\\\data\\\\runs\\\\20261024-124531-c0129e\\\\swirl_result.cas.h5\\n{'status': 'ok', 'surface': 'agi-section-ee706c', 'axis': 'y', 'position': 0.0, 'state': {'name': 'agi-section-ee706c', 'method': 'zx-plane', 'y': 0.0}}\\n{'status': 'ok', 'directory': 'C:\\\\\\\\Users\\\\\\\\13977\\\\\\\\AppData\\\\\\\\Local\\\\\\\\FluentAGI\\\\\\\\data\\\\\\\\runs\\\\\\\\20261024-124531-c0129e\\\\\\\\post-124909-33bb', 'created': '2026-10-24T12:49:09.241785', 'files': ['mesh.png', 'pressure.png', 'residual.csv', 'velocity-magnitude.png'], 'errors': [], 'convergence_verified': False}\\n{'reported_export_issues': []}\\n{'status': 'ok', 'file': 'C:\\\\\\\\Users\\\\\\\\13977\\\\\\\\AppData\\\\\\\\Local\\\\\\\\FluentAGI\\\\\\\\data\\\\\\\\runs\\\\\\\\20261024-124531-c0129e\\\\\\\\assessment.json', 'overwritten': False, 'bytes': 861}\\n\", \"stderr\": \"\", \"return_value\": null, \"message\": null, \"error_code\": null, \"warnings\": []}"}, {"assistant": "脚本执行完成 · 未自动验收；可点击结果分析导出当前证据报告", "run_directory": "C:\\Users\\13977\\AppData\\Local\\FluentAGI\\data\\runs\\20261024-124531-c0129e"}, {"user": "颗粒有些轨迹也要搞出来"}]
Runtime capabilities:
{"protocol": "FluentAGI-capabilities-v1", "session": {"connected": true, "mode": "launch"}, "geometry": {"worker": "gmsh isolated process", "imports": [], "builtins": ["range", "len", "int", "float", "str", "list", "tuple", "enumerate", "zip", "min", "max", "abs", "round", "RuntimeError", "ValueError", "print", "set", "sum", "sorted", "bool", "all", "any"], "physical_groups": ["inlet[-name]", "outlet[-name]", "wall[-name]", "walls"], "independent_boundary_zones": true, "mesh_cell_limit": 2000000, "geometry_timeout_seconds": 3600, "cell_types": ["triangle", "quadrilateral", "tetrahedron", "hexahedron", "prism", "pyramid"]}, "script": {"imports": ["math", "json", "itertools", "functools", "collections", "dataclasses", "typing"], "adapters": ["advance_moving_body", "advance_transient_dust", "assign_multiphase_materials", "assign_phase_materials", "audit_multiphase_interfaces", "backup_loaded", "build_dust_box", "build_extruded", "build_planar", "build_volume", "compare_moving_pressure", "configure_dpm", "configure_dynamic_mesh", "configure_evaporation_condensation", "configure_phase_count", "configure_surface_dpm", "configure_surface_tension", "configure_three_phase_materials", "configure_transient_dust", "configure_water_air", "convert_to_polyhedra", "create_dust_injection", "create_section", "export_results", "geometry_mesh", "initialize_air", "initialize_moving_body", "initialize_transient_dust", "inspect_dpm", "inspect_dynamic_mesh", "inspect_execution", "inspect_multiphase_materials", "inspect_phase_change", "inspect_phases", "inspect_polyhedral_mesh", "inspect_surface_dpm", "inspect_surface_tension", "prepare_moving_circle", "read_json", "read_moving_body", "read_transient_dust", "read_transient_dust_results", "record_animation", "resume_moving_body", "resume_transient_dust", "run_laminar_channel", "save_case_data_safe", "set_particle_boundaries", "stage", "track_particles", "track_surface_dpm", "write_json"]}, "generated_at": 1792817411.2579086, "phase_change": {"version": "v242", "model": "Lee", "adapter_multiphase_models": ["vof"], "mixture_officially_available": true, "mixture_adapter_validated": false, "two_phase_2d_correction_runtime_validation": "pending", "automatic_model_switch": false, "phases": [2, 3], "saturation": "constant K", "frequencies": "positive finite 1/s", "mass_transfer_pairs": 1, "internal_official_tui": true, "generated_direct_tui": false, "readback": "unique case snapshot", "initializes": false}, "dynamic_mesh": {"versions": ["v242", "v252"], "scope": "2D planar pure triangles, prescribed +X rigid translation; smoothing + local remeshing", "v242_native_validation": "real moving geometry and pressure patches; see shipped validation log", "v252_native_validation": "not installed locally; official generated SDK checked, each customer setup requires native case readback", "motion_is_real": true, "settings_receipt": "dynamic-mesh.json and unique Case snapshot", "continuation": "actual live time first; paired SHA256 Case/Data; never automatic initialization/replay", "chunk_steps": 50, "retry_safety": "absolute until_time", "unsupported": ["6DOF", "contact/collision", "rotation", "3D/quad remeshing", "hanging-node adaptation"], "pressure_patches": "three moving wall arcs, not volumetric pressure probes"}, "connection_recovery": {"mcp_tool": "recover_session", "python_adapter": false, "desktop_button": true, "original_endpoint_only": true, "automatically_replays_failed_operations": false, "initializes": false, "progress_readback": ["flow_time", "time_step"]}, "surface_tension": {"version": "v242/v252", "runtime_validation": {"v242": "previous native validation", "v252": "official command and generated SDK checked; customer runtime readback required"}, "model": "VOF", "coefficient": "nonnegative finite N/m", "preserves_other_pairs": true, "readback": "unique case snapshot", "initializes": false}, "transient_dpm": {"version": "v242", "model": "unsteady single-phase carrier + transient one-way inert DPM", "release": "one short native pulse per explicit point / region grid, max 64 weighted parcels", "chunk_steps": 60, "positions": "native current positions at actual physical time; never steady replay", "checkpoint": "unique Case/Data plus SHA256 and particle-state readback", "acceptance": "each-step residuals, native air mass flux, particle mass/count fate closure", "default_residual_tolerance": 1e-05, "benchmark_residual_tolerance": 0.001, "strict_1e_5_initial_step_validated": false, "resuspension_validated": false, "stochastic_turbulent_dispersion_validated": false, "continuous_release_implemented": true, "continuous_release_native_validated": false, "continuous_release_requires": "experimental_continuous=True", "two_way_coupling_validated": false, "concentration_field_validated": false}, "surface_dpm": {"version": "v242", "native_validation": "192-cell turbulent 3D carrier; 16 inlet faces x 20 native RR diameters x 10 DRW = 3200 tracks; carrier HDF5 fields unchanged", "injection": "native inert surface, face normal INTO domain", "distribution": "native Rosin-Rammler; actual nonuniform mass-flow weights", "coupling": "one-way steady; existing turbulent air required", "readback": "independent native Case Rampant/Thread Variables, paired immutable air field hashes", "tracking": "two native passes; EVERY terminal ID, diameter, position and residence time must match before weights/fates are joined", "animation": "稳态轨迹回放; NOT transient DPM", "max_numerical_tracks": 100000, "resume": "completed results cached; verified postprocessing resumes without retracking; uncertain native pass never automatically repeated", "carrier_review_status": "needs-review", "v252_validated": false}, "dpm": {"version": "v242", "carrier": "single phase, one-way, steady inert dust", "injection_types": ["single", "group"], "surface_injection_validated": false, "boundary_types": ["reflect", "trap", "escape"], "trajectory_source": "native GetParticleTracksField RPC", "animation": "steady DPM trajectory residence-time replay, no carrier advance", "transient_dpm_validated": false, "two_way_validated": false, "readback": true, "active": true}, "polyhedral_conversion": {"implemented": true, "versions": ["v242", "v252"], "v242_native_smoke": "581 tetrahedral -> 227 polyhedral cells, isolated serial 3D test; not customer case", "v252_native_validated": false, "v252_requires": "allow_unvalidated_version=True for controlled validation", "input": "uninitialized 3D serial uniform tetrahedral/wedge cell zones; local wedge validation pending", "initialized_solution_conversion": false, "reason": "v242 native conversion initializes data/resets time; existing valid solution is protected", "internal_official_tui": true, "arbitrary_tui_or_scheme": false, "readback": "unique native before/after Case snapshots, cell type 7, positive volume, total volume, boundary names/types, flow time and time-step index", "reinitializes": false, "advances_solution": false, "parallel_repartition_validated": false, "failure_policy": "durable running/failed receipt; no automatic replay, reload or initialization"}, "simple_laminar_channel": {"adapter": "run_laminar_channel", "implemented": true, "native_verified_versions": ["242"], "pending_versions": ["252"], "dimensions": [2], "fluid": "air", "physics": "steady laminar single phase", "resume": "same task receipt, same solver identity and mesh structure; only remaining native iterations; completed initialization/mesh preserved", "verification": "1280 native cells,150 iterations, pressure/velocity PNG and native Case/Data; injected export failure resumed without new solve; not engineering validation"}, "contract_id": "7352449addf0a8d4", "fluent_version": "Ansys Fluent 2024 R2", "fluent_code": "242", "pyfluent_version": "0.37.2", "settings_schema": {"module": "settings_242", "version": "242", "source": "actual solver.settings generated classes; not bundled latest index", "matches_session": true}, "settings_nodes": {"setup.models.multiphase": {"class": "multiphase", "children": ["models", "vaporization_pressure", "non_condensable_gas", "liquid_surface_tension", "bubble_number_density", "number_of_phases", "number_of_eulerian_discrete_phases"], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4"}, "setup.models.energy": {"class": "energy", "children": ["enabled", "viscous_dissipation", "pressure_work", "kinetic_energy", "inlet_diffusion", "two_temperature"], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4"}, "file": {"class": "file", "children": ["single_precision_coordinates", "binary_legacy_files", "cff_files", "convert_hanging_nodes_during_read", "async_optimize", "write_pdat", "auto_save", "export", "import_", "parametric_project", "cffio_options", "batch_options"], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4"}, "solution.run_calculation": {"class": "run_calculation", "children": ["pseudo_time_settings", "iter_count", "adaptive_time_stepping", "cfl_based_adaptive_time_stepping", "reporting_interval", "profile_update_interval", "time_step_count", "transient_controls", "data_sampling", "data_sampling_options", "residual_verbosity"], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4"}}, "phase_count": {"shape": "scalar", "path": "setup.models.multiphase.number_of_phases", "source": "actual generated class metadata"}, "script_rules": {"imports": ["collections", "dataclasses", "functools", "itertools", "json", "math", "typing"], "builtins": ["ArithmeticError", "AssertionError", "AttributeError", "BaseException", "Exception", "False", "IndexError", "KeyError", "LookupError", "None", "NotImplementedError", "RuntimeError", "StopIteration", "True", "TypeError", "ValueError", "ZeroDivisionError", "abs", "all", "any", "bool", "bytearray", "bytes", "complex", "dict", "dir", "enumerate", "filter", "float", "frozenset", "getattr", "hasattr", "int", "isinstance", "issubclass", "len", "list", "map", "max", "min", "print", "range", "repr", "reversed", "round", "set", "setattr", "sorted", "str", "sum", "tuple", "type", "zip"], "forbidden_calls": ["os.system", "subprocess.Popen", "subprocess.call", "subprocess.run", "subprocess.check_call", "subprocess.check_output", "shutil.rmtree", "shutil.move", "shutil.copy", "shutil.copytree", "eval", "exec", "compile", "__import__", "globals", "locals", "vars", "open", "input", "exit", "quit", "breakpoint", "help"], "direct_tui_scheme": false, "reflection_writes": false, "file_operations": ["fluentagi.write_json(directory, name, data): unique JSON file; never overwrites", "fluentagi.read_json(directory, name): scoped JSON read", "solver.settings.file: native case/data/mesh APIs"], "open_allowed": false}, "adapter_validation": {"configure_phase_count": "implemented; actual v242 scalar schema read live, new combined write/readback tested with fixtures; native mutation validation pending", "write_json": "scoped local runtime tested; no overwrite", "read_json": "scoped local runtime tested", "inspect_execution": "state/receipts only; not a resume command"}, "adapter_signatures": {"advance_moving_body": "(self, directory, steps=10, max_iter_per_step=100, residual_tolerance=0.001, require_convergence=True, frame_every=5, until_time=None)", "advance_transient_dust": "(self, directory, steps=10, max_iter_per_step=200, residual_tolerance=1e-05, checkpoint_every=5, until_time=None)", "assign_multiphase_materials": "(self, materials, directory)", "assign_phase_materials": "(self, primary='air', secondary='water-liquid', directory=None)", "audit_multiphase_interfaces": "(self)", "backup_loaded": "(self, directory)", "build_dust_box": "(self, directory, width=0.04, height=0.04, depth=0.04, nozzle_radius=0.004, nozzle_length=0.01, vent_length=0.008, vent_height=0.01, vent_width=0.012, size=0.006)", "build_extruded": "(self, directory, points, inlet_edges, outlet_edges, depth=0.01, size=0.002, mesh_type='tet')", "build_planar": "(self, directory, points, inlet_edges, outlet_edges, size=0.001, mesh_type='tri')", "build_volume": "(self, directory, shape='box', length=0.1, width=0.02, height=0.02, radius=0.01, size=0.005, mesh_type='tet')", "compare_moving_pressure": "(self, directory, with_target_directory, without_target_directory)", "configure_dpm": "(self, directory, density=2500, material='agi-dust', max_steps=10000)", "configure_dynamic_mesh": "(self, directory, zones, speed=0.1, ramp_time=0.4, duration=2.2, min_length=0.001, max_length=0.03, max_skew=0.85)", "configure_evaporation_condensation": "(self, directory, saturation_temperature, evaporation_frequency, condensation_frequency, from_phase='phase-2', to_phase='phase-3')", "configure_phase_count": "(self, directory, count, model=None)", "configure_surface_dpm": "(self, directory, inlet='inlet', outlets=None, reactor_walls=None, pipe_walls=None, velocity=15.0, density=700.0, mass_flow=0.05, min_diameter=5e-06, max_diameter=0.0001, characteristic_diameter=5e-05, spread=3.5, diameters=20, max_steps=50000, step_length_factor=5.0, drw_tries=10)", "configure_surface_tension": "(self, directory, coefficient, phase_a='phase-1', phase_b='phase-2')", "configure_three_phase_materials": "(self, directory, materials=None)", "configure_transient_dust": "(self, directory, points=None, region_min=None, region_max=None, counts=(2, 1, 2), release_time=0.02, release_duration=0.0005, total_mass=1e-08, diameter=1e-05, density=2500, initial_velocity=(0, 0, 0), gravity=(0, -9.81, 0), time_step=0.004, wall_behavior='trap', release_mode='pulse', mass_flow_rate=None, max_release_points=64, max_parcel_budget=200000, experimental_continuous=False)", "configure_water_air": "(self, directory, velocity=0.05, time_step=0.001, gravity_y=-9.81, inlet='inlet', outlet='outlet')", "convert_to_polyhedra": "(self, directory, allow_unvalidated_version=False)", "create_dust_injection": "(self, directory, name, start, end=None, streams=12, diameter=5e-05, mass_flow=1e-07, velocity=(0.5, 0, 0), material='agi-dust', density=2500)", "create_section": "(self, axis='z', position=0.0)", "export_results": "(self, directory, fields=None, save_case=True, surfaces=None)", "geometry_mesh": "(self, directory, code)", "initialize_air": "(self, directory)", "initialize_moving_body": "(self, directory)", "initialize_transient_dust": "(self, directory)", "inspect_dpm": "(self)", "inspect_dynamic_mesh": "(self, directory)", "inspect_execution": "(self, directory)", "inspect_multiphase_materials": "(self)", "inspect_phase_change": "(self, directory)", "inspect_phases": "(self)", "inspect_polyhedral_mesh": "(self, directory)", "inspect_surface_dpm": "(self, directory)", "inspect_surface_tension": "(self, directory)", "prepare_moving_circle": "(self, directory, include_target=True, body_diameter=0.06, target_diameter=0.04, target_x=0.28, target_y=0.0, speed=0.1, ramp_time=0.4, end_time=2.2, time_step=0.005, size=0.012, replace_loaded_model=False)", "read_json": "(self, directory, name)", "read_moving_body": "(self, directory)", "read_transient_dust": "(self, directory)", "read_transient_dust_results": "(self, directory)", "record_animation": "(self, directory, field='velocity-magnitude', frames=10, steps_per_frame=1, max_iter_per_step=20, surfaces=None)", "resume_moving_body": "(self, directory, restore_checkpoint=False)", "resume_transient_dust": "(self, directory, checkpoint='latest-checkpoint.json')", "run_laminar_channel": "(self, directory, length=0.2, height=0.02, velocity=0.1, nx=80, ny=16, iterations=150)", "save_case_data_safe": "(self, path)", "set_particle_boundaries": "(self, directory, boundaries)", "stage": "(self, directory, name, status='ok', **extra)", "track_particles": "(self, directory, injections, frames=30)", "track_surface_dpm": "(self, directory, frames=20)", "write_json": "(self, directory, name, data)"}, "schema_validation": "targeted actual class paths and literal types; dynamic paths/staged inactive nodes reported deferred", "live_state": {"contract_id": "7352449addf0a8d4", "fluent_version": "Ansys Fluent 2024 R2", "read_only": true, "checked_at": 1792817411.2584107, "model_active": true, "has_solution_data": true, "flow_time": 0.0, "time_step": 0, "multiphase_model": "none"}, "model_active": true, "generation_preparation": {"contract_id": "7352449addf0a8d4", "fluent_version": "Ansys Fluent 2024 R2", "pyfluent_version": "0.37.2", "settings_schema_version": "242", "state": {"contract_id": "7352449addf0a8d4", "fluent_version": "Ansys Fluent 2024 R2", "read_only": true, "checked_at": 1792817411.483097, "model_active": true, "has_solution_data": true, "flow_time": 0.0, "time_step": 0, "multiphase_model": "none"}, "nodes": {"file.read_mesh": {"class": "read_mesh", "children": [], "arguments": ["file_name"], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4", "active": true}, "setup.models.viscous.model": {"class": "model_1", "children": [], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4", "active": true, "allowed_values": ["inviscid", "laminar", "k-epsilon", "k-omega", "mixing-length", "spalart-allmaras", "k-kl-w", "transition-sst", "reynolds-stress", "scale-adaptive-simulation", "detached-eddy-simulation", "large-eddy-simulation"]}, "setup.models.energy.enabled": {"class": "enabled", "children": [], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4", "active": true}, "solution.initialization.hybrid_initialize": {"class": "hybrid_initialize", "children": [], "arguments": [], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4", "active": true}, "solution.run_calculation.iterate": {"class": "iterate", "children": [], "arguments": ["iter_count"], "source": "settings_242", "schema_version": "242", "contract_id": "7352449addf0a8d4", "active": true}}, "read_only": true, "next_stage": "configure_from_actual_nodes", "policy": "Use actual returned paths/values. Empty session: mesh generation/import first; physics is probed after import. Never infer missing API from a catalog.", "simple_channel_adapter": {"name": "run_laminar_channel", "scope": "new empty 2D air laminar rectangular channel or SAME receipt continuation; no arbitrary geometry or existing carrier replacement", "validation": "see channel validation receipt; version guards use actual session"}}}
Current session:
{"connected": true, "dimension": 3, "mode": "solver", "owned": true, "continuation": true, "fluent_version": "Ansys Fluent 2024 R2", "pyfluent_version": "0.37.2", "contract_id": "7352449addf0a8d4", "recovery_pending": {"directory": "C:\\Users\\13977\\AppData\\Local\\FluentAGI\\data\\runs\\20261024-124531-c0129e", "reason": "可能部分执行；执行前后回执在原任务目录", "failed": true}, "task_intent": {"protocol": "FluentAGI-task-intent-v1", "steady_surface_dpm_only": false, "preserve_carrier": false, "reason": "normal analysis"}}
Task directory:
C:\Users\13977\AppData\Local\FluentAGI\data\runs\20261024-125011-fe110c
Current request:
颗粒有些轨迹也要搞出来
【ChatGPT 回复】
ChatGPT 说：保留已完成的8528单元空气流场，补充36条、粒径10 μm的稀相颗粒稳态轨迹及回放，降低额外计算量。默认颗粒密度2500 kg/m³、壁面捕集；回放不代表瞬态颗粒运动。
```python
# Use the existing connected PyFluent variable solver.
task_directory = r"C:\Users\13977\AppData\Local\FluentAGI\data\runs\20261024-125011-fe110c"
original_directory = r"C:\Users\13977\AppData\Local\FluentAGI\data\runs\20261024-124531-c0129e"
def require_ok(result, operation):
print(result)
if isinstance(result, dict):
if result.get("status") in ("error", "failed"):
raise RuntimeError(operation + " failed; inspect returned evidence")
if result.get("success") is False or result.get("ok") is False:
raise RuntimeError(operation + " failed; inspect returned evidence")
if result.get("error") or result.get("errors"):
raise RuntimeError(operation + " reported errors")
return result
try:
inspection = fluentagi.inspect_execution(directory=original_directory)
print(inspection)
if not isinstance(inspection, dict):
raise RuntimeError("Actual execution state is unavailable")
state = inspection.get("actual_state", {})
if state.get("model_active") is not True:
raise RuntimeError("The existing carrier mesh is unavailable")
if state.get("has_solution_data") is not True:
raise RuntimeError("The existing air solution is unavailable")
if state.get("multiphase_model") != "none":
raise RuntimeError("Single-phase carrier was not confirmed")
print(fluentagi.inspect_dpm())
if solver.settings.setup.general.solver.time.get_state() != "steady":
raise RuntimeError("This script requires the existing steady carrier")
boundaries = solver.settings.setup.boundary_conditions
actual_inlets = list(boundaries.velocity_inlet.get_object_names())
actual_outlets = list(boundaries.pressure_outlet.get_object_names())
actual_walls = list(boundaries.wall.get_object_names())
print({
"velocity_inlets": actual_inlets,
"pressure_outlets": actual_outlets,
"walls": actual_walls
})
if set(actual_inlets) != {"inlet"}:
raise RuntimeError("Inlet names differ from the completed swirl model")
if set(actual_outlets) != {"outlet"}:
raise RuntimeError("Outlet names differ from the completed swirl model")
if set(actual_walls) != {"walls"}:
raise RuntimeError("Wall names differ from the completed swirl model")
print({
"inlet_state": boundaries.velocity_inlet["inlet"].get_state(),
"carrier_viscous_model":
solver.settings.setup.models.viscous.model.get_state()
})
require_ok(
fluentagi.backup_loaded(directory=task_directory),
"Carrier backup"
)
injections = []
for index, offset in enumerate((-0.008, 0.0, 0.008)):
name = "swirl_dust_10um_row_" + str(index + 1)
result = fluentagi.create_dust_injection(
directory=task_directory,
name=name,
start=[0.065, 0.036 + offset, -0.159],
end=[0.085, 0.036 + offset, -0.159],
streams=12,
diameter=0.00001,
mass_flow=0.00000001,
velocity=[0.0, 0.0, 1.0],
material="agi-dust",
density=2500
)
require_ok(result, "Injection " + name)
injections.append(name)
require_ok(
fluentagi.configure_dpm(
directory=task_directory,
density=2500,
material="agi-dust",
max_steps=20000
),
"Steady one-way DPM configuration"
)
require_ok(
fluentagi.set_particle_boundaries(
directory=task_directory,
boundaries={
"inlet": "escape",
"outlet": "escape",
"walls": "trap"
}
),
"Particle boundary configuration"
)
print(fluentagi.inspect_dpm())
print(fluentagi.stage(
directory=task_directory,
name="particle_tracking",
status="running",
injections=injections,
nominal_streams=36,
carrier_recomputed=False,
animation_type="steady trajectory residence-time replay"
))
tracks = fluentagi.track_particles(
directory=task_directory,
injections=injections,
frames=20
)
require_ok(tracks, "Native particle tracking and export")
print(fluentagi.save_case_data_safe(
task_directory + r"\swirl_with_particles.cas.h5"
))
assessment = {
"carrier_directory": original_directory,
"particle_directory": task_directory,
"carrier_reinitialized": False,
"carrier_recomputed": False,
"particle_model": "one-way steady inert DPM",
"diameter_m": 0.00001,
"density_kg_m3": 2500,
"total_injected_mass_flow_kg_s": 0.00000003,
"nominal_numerical_streams": 36,
"injection_velocity_m_s": [0.0, 0.0, 1.0],
"wall_behavior": "trap",
"animation_label": "稳态轨迹回放",
"physical_particle_count": "not represented by numerical stream count",
"stochastic_turbulent_dispersion": "not configured",
"carrier_convergence_verified": False,
"collection_efficiency_validated": False,
"particle_accounting": "refer to native tracker counts and mass summary",
"tracking_result": tracks,
"needs_review": True
}
print(fluentagi.write_json(
directory=task_directory,
name="particle-assessment.json",
data=assessment
))
print(fluentagi.stage(
directory=task_directory,
name="particle_tracking",
status="completed",
carrier_convergence_verified=False,
needs_review=True
))
except Exception as exc:
print({"status": "stopped", "error": str(exc)})
for directory in (original_directory, task_directory):
print(fluentagi.inspect_execution(directory=directory))
raise
```
脚本拟在现有流场中添加36条原生颗粒轨迹，导出轨迹数据、图片和稳态回放，不重新求解空气。捕集、逃逸、未完成及中止数量以追踪反馈为准；原流场收敛性仍未验证，GIF是否完成编码也需看返回结果。