Use augur subsample

.gitattributes

@@ -1,3 +1,8 @@
 # Allow Git to decide if file is text or binary
 # Always use LF line endings even on Windows.
 * text=auto eol=lf
+
+# This is a large generated file that, while text, it is not useful to
+# routinely show the diff of.  A diff can be forced as needed, e.g. with `git
+# diff --text`.
+/config/configfile.yaml -diff

CHANGELOG.md

@@ -4,4 +4,6 @@ We use this CHANGELOG to document breaking changes, new features, bug fixes, and
 
 ## 2026
 
+* TBD: The `filter` section in phylogenetic workflow configuration has been replaced by `subsample`/`custom_subsample` for subsampling, and `filter_for_f_antibody_escape` for initial quality filtering. **This is a breaking change**.
+    * NOTE: The workflow does not yet support proximal samples.
 * 11 August 2026: Phylogenetic workflow configuration is now validated against a strict schema. The workflow will error if your configuration has extraneous entries that were previously ignored.

README.md

@@ -46,7 +46,14 @@ Once you've run the build, you can view the results with:
 
 ## Configuration
 
-The default configuration is in [`config/configfile.yaml`](./config/configfile.yaml).
+The default configuration is generated by
+[scripts/generate_default_config.py](./scripts/generate_default_config.py). It
+can be run with Nextstrain CLI:
+
+```sh
+nextstrain shell . -c 'python scripts/generate_default_config.py'
+```
+
 The workflow is contained in the [Snakefile](Snakefile) with included
 [rules](workflow/snakemake_rules/). Each rule specifies its file inputs and outputs
 and pulls its parameters from the config. There is little redirection and each

config.schema.yaml

@@ -5,6 +5,13 @@ description: >-
   configuration file.
 
 $defs:
+  per_full_build_map: &per_full_build_map
+    type: object
+    additionalProperties: false
+    propertyNames:
+      title: Full build name
+      description: Full build name (e.g. 'a/genome/all-time')
+
   per_subtype_map: &per_subtype_map
     type: object
     additionalProperties: false
@@ -79,52 +86,19 @@ properties:
     type: string
   display_strain_field:
     type: string
-  filter:
-    type: object
-    additionalProperties: false
-    properties:
-      group_by:
-        type: string
-      min_coverage:
-        <<: *per_build_map
-        patternProperties:
-          "^.*$":
-            type: number
-      min_length:
-        <<: *per_build_map
-        patternProperties:
-          "^.*$":
-            type: integer
-      resolutions:
-        <<: *per_resolution_map
-        patternProperties:
-          "^.*$":
-            type: object
-            additionalProperties: false
-            properties:
-              min_date:
-                type: string
-              background_min_date:
-                type: string
-      subsample_max_sequences:
-        <<: *per_build_map
-        patternProperties:
-          "^.*$":
-            type: integer
-      exclude_where:
-        type: object
-        additionalProperties: false
-        properties:
-          recent:
-            type: array
-            items:
-              type: string
-          background:
-            type: array
-            items:
-              type: string
-      missing_data_threshold:
-        type: integer
+  subsample: &subsample_config
+    <<: *per_full_build_map
+    description: >-
+      Subsampling configuration. When using --configfile, it is recommended to
+      use 'custom_subsample' instead to ignore default subsampling configuration.
+    patternProperties:
+      "^.*$":
+        $ref: "https://nextstrain.org/schemas/augur/subsample-config-unaligned/v1"
+  custom_subsample:
+    <<: *subsample_config
+    description: >-
+      Custom subsampling configuration. When using --configfile, this is
+      recommended over 'subsample' to ignore default subsampling configuration.
   files:
     type: object
     additionalProperties: false
@@ -194,6 +168,33 @@ properties:
             type: string
           accession:
             type: string
+  filter_for_f_antibody_escape:
+    type: object
+    additionalProperties: false
+    properties:
+      group_by:
+        type: string
+      min_length:
+        <<: *per_build_map
+        patternProperties:
+          "^.*$":
+            type: integer
+      min_coverage:
+        <<: *per_build_map
+        patternProperties:
+          "^.*$":
+            type: number
+      resolutions:
+        <<: *per_resolution_map
+        patternProperties:
+          "^.*$":
+            type: object
+            additionalProperties: false
+            properties:
+              min_date:
+                type: string
+              background_min_date:
+                type: string
   f_dms_data:
     type: string
   f_dms_antibodies: