cortex: de-duplicate projects.yaml and reject duplicate project keys (#50)

REFERENCE.md

@@ -106,7 +106,9 @@ writes nothing.
 
 The science body map. **Code, not ledger** — `sync_cli` and `local_path` are
 paths a conductor executes under. Real YAML read with `yaml.safe_load`; the
-shape is validated by `cortex.py`:
+shape is validated by `cortex.py`. A project key may appear only once — since
+`yaml.safe_load` silently keeps the last of a repeated key, `cortex.py check`
+scans the raw column-0 keys and reports every duplicate with its line numbers:
 
 | Field | Value | Notes |
 |---|---|---|

projects.yaml

@@ -288,323 +288,3 @@ euclid_sersics:
   partition: ral
   status: retired
   note: "retired 2026-09-25: retire euclid_sersics as well"
-
-analytic_gaussian:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/analytic_gaussian
-  ral_root: /mnt/ral/jnightin/analytic_gaussian
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, status, submit, push-submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autofit_assistant
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "born 2026-09-09 as the graphical-ep campaign's phase-1 keystone at ensemble scale; benchmark model with a closed-form posterior, borrowed from autofit_workspace_test scripts/graphical (PR #92 lineage); CPU-only, no dataset (every draw is simulated in memory from its seed); remote none until the human runs gh repo create PyAutoLabs/analytic_gaussian --private"
-
-ep_toy_gaussian:
-  remote: PyAutoLabs/ep_toy_gaussian
-  local_path: /mnt/c/Users/Jammy/Science/ep_toy_gaussian
-  ral_root: /mnt/ral/jnightin/ep_toy_gaussian
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, status, submit, push-submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autofit_assistant
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "born 2026-09-10 as the graphical-ep campaign's confidence test on the PyAutoFit#1405 collapse toy at N=50: joint BlackJAX NUTS vs EP x3 on identical data; model and EP settings verbatim from complete/2026/07 ep_toy_diagnostic; CPU-only, data simulated in memory from its seed; remote PyAutoLabs/ep_toy_gaussian (private) created 2026-09-10"
-
-# --------------------------------------------------------------------------- #
-# dormant — git repos only. The non-git trees (subhalo, euclid_group, z_*) are
-# storage, not projects, and aris_PJ011646 is an assistant clone; none get a
-# row. `ral_root` is the planned path and `sync_verbs` is unverified on every
-# row below — each note says so.
-# --------------------------------------------------------------------------- #
-profiling:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/profiling
-  ral_root: /mnt/ral/jnightin/profiling
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "2026-05 checkpointed sweep harness, PyAutoNSS venv; name collides with autolens_profiling; ral_root planned, sync_verbs unverified"
-
-cowls_diana:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/cowls_diana
-  ral_root: /mnt/ral/jnightin/cowls_diana
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "local git, no remote; ral_root planned, sync_verbs unverified"
-
-subhalo_simulations:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/subhalo_simulations
-  ral_root: /mnt/ral/jnightin/subhalo_simulations
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "git init, zero commits, 21 GB; ral_root planned, sync_verbs unverified"
-
-slope_hierarchy:
-  remote: Jammy2211/slope_hierarchy
-  local_path: /mnt/c/Users/Jammy/Science/z_projects_complete/slope_hierarchy
-  ral_root: /mnt/ral/jnightin/slope_hierarchy
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: retired
-  note: "retired 2026-09-08: wrapped up 2026-07-22 at N=5; succeeded by slope_hierarchy_scale; tree vaulted under z_projects_complete/"
-
-slope_hierarchy_scale:
-  remote: PyAutoLabs/slope_hierarchy_scale
-  local_path: /mnt/c/Users/Jammy/Science/slope_hierarchy_scale
-  ral_root: /mnt/ral/jnightin/slope_hierarchy_scale
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, sync, status, submit, push-submit, jobs, tail, check]
-  ledger: wiki/project/state.md
-  assistant: autolens_assistant
-  witness_file: results/**/*.json
-  partition: both
-  status: active
-  note: "born 2026-09-08 as graphical-ep phase 3, code borrowed from slope_hierarchy (vaulted under z_projects_complete/); private remote created 2026-09-08"
-
-pj011646:
-  remote: Jammy2211/PJ011646
-  local_path: /mnt/c/Users/Jammy/Science/PJ011646
-  ral_root: /mnt/ral/jnightin/PJ011646
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "personal remote, recorded as a fact — not a PyAutoLabs repo; ral_root planned, sync_verbs unverified"
-
-concr:
-  remote: Jammy2211/cosmology_and_cancer
-  local_path: /mnt/c/Users/Jammy/Science/concr
-  ral_root: /mnt/ral/jnightin/concr
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "personal remote Jammy2211/cosmology_and_cancer, recorded as a fact; ral_root planned, sync_verbs unverified"
-
-ic50_workspace:
-  remote: Jammy2211/ic50_workspace
-  local_path: /mnt/c/Users/Jammy/Science/ic50_workspace
-  ral_root: /mnt/ral/jnightin/ic50_workspace
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, push-data-init, pull-full, status, submit, push-submit, jobs, sacct, cancel, wait-and-pull, tail, du, check, clear-logs]
-  ledger: NOTES.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "personal remote, recorded as a fact — not a PyAutoLabs repo; activated 2026-09-09 for graphical-ep phase 4, ral_root created and first runs submitted; NOTES.md predates the graphical/HPC work and needs a refresh"
-
-autolens_inference:
-  remote: PyAutoLabs/autolens_inference
-  local_path: /home/jammy/Code/PyAutoLabs/lens/autolens_inference
-  ral_root: /mnt/ral/jnightin/autolens_inference
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull, logs, status, submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autolens_assistant
-  witness_file: results/**/*.json
-  partition: both
-  status: active
-  note: "born 2026-09-10 as the from-scratch restart of inference_programme (retired PyAutoCortex#22); nothing inherited; phase 1 = birth (PyAutoMind#399), first task slam_hst_base"
-
-analytic_gaussian:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/analytic_gaussian
-  ral_root: /mnt/ral/jnightin/analytic_gaussian
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, status, submit, push-submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autofit_assistant
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "born 2026-09-09 as the graphical-ep campaign's phase-1 keystone at ensemble scale; benchmark model with a closed-form posterior, borrowed from autofit_workspace_test scripts/graphical (PR #92 lineage); CPU-only, no dataset (every draw is simulated in memory from its seed); remote none until the human runs gh repo create PyAutoLabs/analytic_gaussian --private"
-
-ep_toy_gaussian:
-  remote: PyAutoLabs/ep_toy_gaussian
-  local_path: /mnt/c/Users/Jammy/Science/ep_toy_gaussian
-  ral_root: /mnt/ral/jnightin/ep_toy_gaussian
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, status, submit, push-submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autofit_assistant
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "born 2026-09-10 as the graphical-ep campaign's confidence test on the PyAutoFit#1405 collapse toy at N=50: joint BlackJAX NUTS vs EP x3 on identical data; model and EP settings verbatim from complete/2026/07 ep_toy_diagnostic; CPU-only, data simulated in memory from its seed; remote PyAutoLabs/ep_toy_gaussian (private) created 2026-09-10"
-
-# --------------------------------------------------------------------------- #
-# dormant — git repos only. The non-git trees (subhalo, euclid_group, z_*) are
-# storage, not projects, and aris_PJ011646 is an assistant clone; none get a
-# row. `ral_root` is the planned path and `sync_verbs` is unverified on every
-# row below — each note says so.
-# --------------------------------------------------------------------------- #
-profiling:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/profiling
-  ral_root: /mnt/ral/jnightin/profiling
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "2026-05 checkpointed sweep harness, PyAutoNSS venv; name collides with autolens_profiling; ral_root planned, sync_verbs unverified"
-
-cowls_diana:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/cowls_diana
-  ral_root: /mnt/ral/jnightin/cowls_diana
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "local git, no remote; ral_root planned, sync_verbs unverified"
-
-subhalo_simulations:
-  remote: none
-  local_path: /mnt/c/Users/Jammy/Science/subhalo_simulations
-  ral_root: /mnt/ral/jnightin/subhalo_simulations
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "git init, zero commits, 21 GB; ral_root planned, sync_verbs unverified"
-
-slope_hierarchy:
-  remote: Jammy2211/slope_hierarchy
-  local_path: /mnt/c/Users/Jammy/Science/z_projects_complete/slope_hierarchy
-  ral_root: /mnt/ral/jnightin/slope_hierarchy
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: retired
-  note: "retired 2026-09-08: wrapped up 2026-07-22 at N=5; succeeded by slope_hierarchy_scale; tree vaulted under z_projects_complete/"
-
-slope_hierarchy_scale:
-  remote: PyAutoLabs/slope_hierarchy_scale
-  local_path: /mnt/c/Users/Jammy/Science/slope_hierarchy_scale
-  ral_root: /mnt/ral/jnightin/slope_hierarchy_scale
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, sync, status, submit, push-submit, jobs, tail, check]
-  ledger: wiki/project/state.md
-  assistant: autolens_assistant
-  witness_file: results/**/*.json
-  partition: both
-  status: active
-  note: "born 2026-09-08 as graphical-ep phase 3, code borrowed from slope_hierarchy (vaulted under z_projects_complete/); private remote created 2026-09-08"
-
-pj011646:
-  remote: Jammy2211/PJ011646
-  local_path: /mnt/c/Users/Jammy/Science/PJ011646
-  ral_root: /mnt/ral/jnightin/PJ011646
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "personal remote, recorded as a fact — not a PyAutoLabs repo; ral_root planned, sync_verbs unverified"
-
-concr:
-  remote: Jammy2211/cosmology_and_cancer
-  local_path: /mnt/c/Users/Jammy/Science/concr
-  ral_root: /mnt/ral/jnightin/concr
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull]
-  ledger: README.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: both
-  status: dormant
-  note: "personal remote Jammy2211/cosmology_and_cancer, recorded as a fact; ral_root planned, sync_verbs unverified"
-
-ic50_workspace:
-  remote: Jammy2211/ic50_workspace
-  local_path: /mnt/c/Users/Jammy/Science/ic50_workspace
-  ral_root: /mnt/ral/jnightin/ic50_workspace
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [push, pull, logs, sync, push-data-init, pull-full, status, submit, push-submit, jobs, sacct, cancel, wait-and-pull, tail, du, check, clear-logs]
-  ledger: NOTES.md
-  assistant: none
-  witness_file: results/**/*.json
-  partition: ral
-  status: active
-  note: "personal remote, recorded as a fact — not a PyAutoLabs repo; activated 2026-09-09 for graphical-ep phase 4, ral_root created and first runs submitted; NOTES.md predates the graphical/HPC work and needs a refresh"
-
-autolens_inference:
-  remote: PyAutoLabs/autolens_inference
-  local_path: /home/jammy/Code/PyAutoLabs/lens/autolens_inference
-  ral_root: /mnt/ral/jnightin/autolens_inference
-  mirror: none
-  sync_cli: hpc/sync
-  sync_verbs: [pull, logs, status, submit, jobs, sacct, cancel, tail, du, check]
-  ledger: wiki/project/state.md
-  assistant: autolens_assistant
-  witness_file: results/**/*.json
-  partition: both
-  status: active
-  note: "born 2026-09-10 as the from-scratch restart of inference_programme (retired PyAutoCortex#22); nothing inherited; phase 1 = birth (PyAutoMind#399), first task slam_hst_base"

scripts/cortex.py

@@ -77,6 +77,7 @@
 # grammars
 # --------------------------------------------------------------------------- #
 PROJECT_KEY_RE = re.compile(r"^[a-z][a-z0-9_]*$")
+PROJECT_KEY_LINE_RE = re.compile(r"^([a-z][a-z0-9_]*):\s*(#.*)?$")
 LEDGER_FILE_RE = re.compile(r"^projects/([a-z][a-z0-9_]*)\.md$")
 DATE_RE = re.compile(r"^\d{4}-\d{2}-\d{2}$")
 WALL_RE = re.compile(r"^\d+:\d{2}$")
@@ -185,8 +186,22 @@ def _replace_section(text: str, name: str, body: "list[str]") -> str:
 # --------------------------------------------------------------------------- #
 # projects.yaml
 # --------------------------------------------------------------------------- #
+def _duplicate_key_problems(text: str) -> "list[str]":
+    """`yaml.safe_load` silently keeps the last of a repeated mapping key, so a
+    project row pasted twice would vanish from view: scan the raw column-0
+    keys first and name every repeat with its line numbers."""
+    seen: "dict[str, list[int]]" = {}
+    for n, line in enumerate(text.split("\n"), 1):
+        m = PROJECT_KEY_LINE_RE.match(line)
+        if m:
+            seen.setdefault(m.group(1), []).append(n)
+    return [f"projects.yaml: duplicate project key {key!r} "
+            f"(lines {', '.join(map(str, lines))})"
+            for key, lines in seen.items() if len(lines) > 1]
+
+
 def parse_projects(text: str) -> "tuple[dict[str, dict], list[str]]":
-    problems: "list[str]" = []
+    problems: "list[str]" = _duplicate_key_problems(text)
     try:
         doc = yaml.safe_load(text)
     except yaml.YAMLError as e:

tests/test_cortex.py

@@ -222,6 +222,24 @@ def test_projects_yaml_is_validated(tmp_path):
     assert any("unknown field `colour` on example" in p for p in _problems(root))
 
 
+def test_projects_yaml_rejects_duplicate_project_keys(tmp_path):
+    # yaml.safe_load keeps the last of a repeated key silently; the raw-line
+    # guard must name the repeat (25e0168 tripled 11 rows this way).
+    root = _copy(tmp_path)
+    path = root / "projects.yaml"
+    text = path.read_text()
+    lines = text.split("\n")
+    first = lines.index("example:") + 1
+    start = text.index("example:\n")
+    row = text[start:text.index("\n\n", start) + 1]
+    path.write_text(text.rstrip("\n") + "\n\n" + row)
+    second = len(text.rstrip("\n").split("\n")) + 2
+    problems = _problems(root)
+    assert f"projects.yaml: duplicate project key 'example' (lines {first}, {second})" in problems
+    assert not any("duplicate project key 'single'" in p for p in problems)
+    assert _problems(SKELETON) == []
+
+
 # --------------------------------------------------------------------------- #
 # the writing verbs
 # --------------------------------------------------------------------------- #