Merge pull request #121 from PyAutoLabs/feature/memory-wiki-glob

Memory faculty: discover sub-wikis under PyAutoMemory's new wiki/ layout

Author: Jammy2211

agents/faculties/memory/AGENTS.md

@@ -29,7 +29,7 @@ memory.sh "delaunay regularization prior work"
 - **No indexes, no embeddings, no new infra** — grep + the wikis' own
   structure, the same as a careful human session, kept deterministic.
 - **No layout coupling** — sub-wikis are discovered at query time
-  (`*_wiki/` directories); when Memory grows a wiki, the faculty sees it with
+  (`wiki/<domain>/`, plus legacy root `*_wiki/`); when Memory grows a wiki, the faculty sees it with
   no edits (the standing "do not couple to Memory's internal layout" rule).
 - Operational history stays Mind's: `complete.md` is *read* here as a recall
   surface, but the boundary prose in ORGANISM.md is unchanged.

agents/faculties/memory/_memory.py

@@ -32,7 +32,11 @@ def terms_of(query: str) -> list[str]:
 def surfaces(memory: Path | None, assistant: Path | None, mind: Path | None):
     """Yield (surface-name, root, md-file) triples, discovered at query time."""
     if memory and memory.is_dir():
-        for wiki in sorted(memory.glob("*_wiki")):
+        # wiki/<domain>/ is the current layout; root-level *_wiki/ is the
+        # pre-2026-07 layout, kept for older checkouts and forks.
+        wikis = sorted(d for d in memory.glob("wiki/*") if d.is_dir())
+        wikis += sorted(memory.glob("*_wiki"))
+        for wiki in wikis:
             for f in wiki.rglob("*.md"):
                 yield f"PyAutoMemory/{wiki.name}", memory, f
     if assistant and assistant.is_dir():

skills/sampler_pipeline/reference.md

@@ -113,7 +113,7 @@ table.
   the candidate on lensing use cases via `autolens_profiling` — the
   `/profile_likelihood` skill drives the sweep machinery; A100/HPC runs go
   through that repo's conventions.
-- Record durable findings in `PyAutoMemory/methods_wiki/concepts/
+- Record durable findings in `PyAutoMemory/wiki/methods/concepts/
   sampler-benchmarks.md` (internal; never cited in public output).
 
 ## Stage 3 — promotion: the PyAutoFit implementation