Standardize algorithm parameter names from `algo`/`method` to `algorithm`

[Copilot]

Functions used inconsistent parameter names for algorithm selection: some used algo, others algorithm, and many used method. This standardizes all algorithm-selection parameters to algorithm.

Changes

Renamed parameters with lifecycle deprecation:

• algo → algorithm: page_rank(), feedback_arc_set(), feedback_vertex_set()
• method → algorithm: sample_tree(), sample_degseq(), realize_degseq(), realize_bipartite_degseq()

Preserved method for non-algorithm parameters:

• Comparison methods: compare(), similarity()
• Isomorphism methods: isomorphic(), subgraph_isomorphic()
• Layout methods: layout.merge(), merge_coords()

Implementation:

• Updated Stimulus YAML configuration for code generation
• Added workaround for Stimulus parameter renaming in DEPS-based conditionals
• Regenerated R/aaa-auto.R and src/rinterface.c

Example

# New (recommended)
page_rank(g, algorithm = "prpack")
sample_tree(100, algorithm = "lerw")
sample_degseq(degs, algorithm = "configuration")

# Old (deprecated, but still works)
page_rank(g, algo = "prpack")  # Warning: use `algorithm` instead
sample_tree(100, method = "lerw")  # Warning: use `algorithm` instead

Backward Compatibility

Old parameter names continue to work with soft deprecation warnings via lifecycle::deprecate_warn().

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Consistency in parameter names: algo vs algorithm vs method</issue_title> <issue_description>At this moment, some functions use algorithm as a parameter names (e.g. shortest_paths, sample_pa, etc.), some others use algo (e.g. page_rank, feedback_arc_set, etc.), and yet others use method (e.g. sample_degseq, sample_tree, etc.). The naming should be made consistent across functions.</issue_description>

Comments on the Issue (you are @copilot in this section)

@maelle Relevant lifecycle doc: https://lifecycle.r-lib.org/articles/communicate.html#renaming-an-argument

• Fixes igraph/rigraph#526

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.