Fluent Sim

fluent-sim

This skill is the Fluent-specific operating guide. Choose the control path that fits the task, then load only the references needed for that path.

Choose The Control Path

Use sim when the task needs a persistent runtime or live observation. Use a direct PyFluent script when a one-shot batch program is clearer. Use file-side helpers when the question is about artifacts already on disk.

Live Sim Session

After connecting, inspect:

bashCopy code
uv run sim inspect session.versions
uv run sim inspect session.health
uv run sim inspect session.summary

The session.versions payload selects the active overlays. Always read base/, then the active sdk/<active_sdk_layer>/, then the active solver/<active_solver_layer>/ when present. Later layers override earlier files with the same name. Require version_source: active_runtime before applying release-specific guidance; installed-version discovery alone does not prove which Fluent release the session launched or attached to.

Expected SDK layer directories are:

• sdk/0.38/ for PyFluent 0.38.x
• sdk/0.37/ for PyFluent 0.37.x

Useful live inspect targets:

• session.summary
• session.health
• session.versions
• last.result
• workflow.summary
• field.catalog / fluent.field.catalog
• fluent.models.summary
• fluent.boundaries.summary
• fluent.case.summary
• fluent.mesh.summary
• fluent.files

Use uv run sim exec snippets with the injected session, solver, or meshing object. Keep snippets small enough that last.result can prove the current state before the next step.

Direct PyFluent Script

For direct scripts, own the launch and teardown explicitly:

pythonCopy code
from ansys.fluent.core import launch_fluent

solver = launch_fluent(mode="solver", ui_mode="no_gui", precision="double")
try:
    solver.settings.file.read_case(file_name="case.cas.h5")
    solver.solution.initialization.hybrid_initialize()
    solver.solution.run_calculation.iterate(iter_count=10)
finally:
    solver.exit()

This path is a good fit when the result can be produced in one deterministic program and you do not need a live agent-visible session between steps.

For direct PyFluent scripts, launch the session normally with PyFluent and do not rely on sim-injected variables.

Long-running execution and recovery

Keep bounded Fluent work in the foreground when it fits the active tool-call budget. Use a native journal, direct PyFluent script, or background process only when the solve is expected to outlive that budget, must continue across agent turns, or the user explicitly asks for background execution. Keep live sessions for incremental setup and inspection; use a settled script or journal for a repeatable long solve.

For a long run, use absolute transcript/log and case/data output paths so the agent can inspect progress and results later. Do not require a fixed directory tree, a job manifest, or sim-cli when the direct Fluent or PyFluent path is sufficient.

A shell or tool timeout ends that observation call; it does not prove Fluent stopped. Before retrying or stopping, check the Fluent/PyFluent process, transcript tail, monitor output, and case/data timestamps. Confirm process ownership from the executable, full command line, start time, and working or output paths. Never terminate every fluent, ansys, or cortex process by name.

Use resume only when a usable .cas/.dat(.h5) pair, autosave, or another Fluent-native checkpoint can actually continue the calculation. Without one, describe the action as a restart rather than promising generic resume behavior. Keep direct PyFluent scripts responsible for their own launch and teardown.

File-Side Artifact Review

Before launching Fluent, inventory what is already present:

• .cas / .cas.h5: case setup
• .dat / .dat.h5: solution data
• .msh / .msh.h5: mesh input
• .trn / .jou: transcript and journal evidence
• .pdf / .fla: flamelet and PDF table artifacts
• .csv / .png / .json: exported reports, figures, and structured output

Use this path for quick triage, output extraction, and deciding whether a live session is necessary.

Layered References

For PyFluent API questions, start with the active sdk/ overlay. For Fluent physics, meshing, UDF, or solver-model questions, use doc-search/ against the local Ansys documentation tree rather than guessing names or defaults.

Live Sim Session Constraints

These constraints apply only after sim has already created a live Fluent session:

1. Do not call pyfluent.launch_fluent() inside a uv run sim exec snippet. Use the injected session, solver, or meshing object.
2. Do not switch between meshing and solver mode by assumption. The mode is selected at connect time unless a Fluent workflow explicitly returns a solver object.
3. Confirm each stateful step before sending the next dependent step. Fluent meshing and solver workflows are order-sensitive.
4. Use GUI actuation only for surfaces the SDK cannot reach. Prefer solver.settings.*, session.tui.*, and meshing.workflow.* for reproducible work.

Flamelet And PDF Table Workflows

For partially premixed steady-diffusion flamelet workflows, load:

• base/reference/task_templates.md - Template 5
• base/reference/runtime_patterns.md - staged flamelet/PDF dependency chain
• base/reference/acceptance_checklists.md - Checklist 5
• base/snippets/setup_partially_premixed_flamelet.py
• base/snippets/write_pdf_table.py
• base/snippets/read_case_pdf_data.py
• base/snippets/inspect_reacting_bc_scalars.py

Short version: import CHEMKIN as flamelet-mixture, generate flamelets and the PDF table, persist the table with write_pdf_cmd(...), and restart or postprocess with read_case -> read_pdf -> read_data.

Source

Canonical repository: svd-ai-lab/sim-plugin-fluent. Skill path: src/sim_plugin_fluent/_skills/fluent.