mptyl/ThothII
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

docs: verify structured semantic contracts

Browse Source
This commit is contained in:
marcopan
2026-08-08 21:14:17 +02:00
parent b84d4db946
commit bed43c747e
6 changed files with 219 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/test-verify-workspace-install-docs.sh
+80 -37
View File
@@ -159,25 +159,29 @@ if [[ $project_state_status -eq 0 ]] || ! grep -Fq "contradictory active text" "
exit 1
fi
project_state_live_heading="$negative_root/project-state-live-heading.md"
python3 - "$root/PROJECT_STATE.md" "$project_state_live_heading" <<'PY'
for level in 1 2 3 4 5 6; do
project_state_live_heading="$negative_root/project-state-live-heading-h$level.md"
python3 - "$root/PROJECT_STATE.md" "$project_state_live_heading" "$level" <<'PY'
import pathlib, sys
source = pathlib.Path(sys.argv[1]).read_text()
target = pathlib.Path(sys.argv[2])
level = int(sys.argv[3])
marker = source.index("## Historical snapshots")
historical = source[marker:]
historical = historical.replace("### Historical snapshot — Session summary redesign (2026-07-23)", "### Session summary redesign — LIVE 2026-07-23", 1)
replacement = "#" * level + " Session summary redesign — LIVE 2026-07-23"
historical = historical.replace("### Historical snapshot — Session summary redesign (2026-07-23)", replacement, 1)
target.write_text(source[:marker] + historical)
PY
set +e
verify_project_state_current_contract "$project_state_live_heading" historical-live-heading >"$project_state_output" 2>&1
project_state_status=$?
set -e
if [[ $project_state_status -eq 0 ]] || ! grep -Fq "active/live heading markers" "$project_state_output"; then
echo "historical LIVE-heading fixture was not rejected correctly" >&2
cat "$project_state_output" >&2
exit 1
fi
set +e
verify_project_state_current_contract "$project_state_live_heading" "historical-live-heading-h$level" >"$project_state_output" 2>&1
project_state_status=$?
set -e
if [[ $project_state_status -eq 0 ]] || ! grep -Fq "active/live heading markers" "$project_state_output"; then
echo "historical LIVE-heading fixture was not rejected correctly for heading level $level" >&2
cat "$project_state_output" >&2
exit 1
fi
done
workspace_fixture="$negative_root/workspace-invalid.yaml"
python3 - "$root/deploy/workspaces/example.yaml" "$workspace_fixture" <<'PY'
@@ -225,13 +229,13 @@ import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
text = text.replace(
"One workspace owns one Qdrant collection; schema, Evidence, and Memory records share that collection and remain\nisolated by payload `kind`.",
"Each workspace reserves a single Qdrant collection. Schema, Evidence, and Memory stay inside that same collection and are separated by payload `kind`.",
"| Workspace semantic index | Each workspace reserves a single Qdrant collection. | Schema, Evidence, and Memory stay in that one collection and remain isolated by payload `kind`. |",
"| Workspace semantic index | A workspace keeps exactly one Qdrant collection reserved for itself. | Schema, Evidence, and Memory remain together in that collection and are still separated by payload `kind`. |",
)
path.write_text(text)
PY
require_concept_tokens "$local_manual_paraphrase" "local manual paraphrase" "workspace" "qdrant" "collection" >/dev/null
require_pattern "$local_manual_paraphrase" "local manual paraphrase" '(?is)(single|one|each).{0,120}(workspace|qdrant|collection).{0,120}(reserves|reserve|owns|single)' >/dev/null
semantic_index_spec='{"rows":[{"scope":"workspace semantic index","ownership rule":"(each|one|single|exactly one).*(workspace).*(single|one|exactly one).*(Qdrant).*(collection)|(workspace keeps exactly one qdrant collection reserved for itself)","isolation rule":"schema.*evidence.*memory.*(one|that).*(collection).*(kind|payload)|schema.*evidence.*memory.*together.*collection.*(kind|payload)"}]}'
verify_markdown_table_relationships "$local_manual_paraphrase" "local manual paraphrase" "Semantic index ownership contract" "$semantic_index_spec" >/dev/null
local_manual_missing="$negative_root/local-manual-missing.md"
cp "$root/docs/install/local-workspace-registry.md" "$local_manual_missing"
@@ -240,13 +244,13 @@ import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
text = text.replace(
"Schema-v3 is the only operational descriptor format. Schema-v1/v2 descriptors remain\n`migration_required` until an explicit reviewed migration writes schema version 3. One workspace owns one Qdrant collection; schema, Evidence, and Memory records share that collection and remain\nisolated by payload `kind`.\n",
"Schema-v3 is the only operational descriptor format. Schema-v1/v2 descriptors remain `migration_required` until an explicit reviewed migration writes schema version 3.\n",
"| Workspace semantic index | Each workspace reserves a single Qdrant collection. | Schema, Evidence, and Memory stay in that one collection and remain isolated by payload `kind`. |\n",
"",
)
path.write_text(text)
PY
set +e
require_pattern "$local_manual_missing" "local manual missing ownership" '(?is)(single|one|each).{0,120}(workspace|qdrant|collection).{0,120}(reserves|reserve|owns|single)' >"$workspace_output" 2>&1
verify_markdown_table_relationships "$local_manual_missing" "local manual missing ownership" "Semantic index ownership contract" "$semantic_index_spec" >"$workspace_output" 2>&1
workspace_status=$?
set -e
if [[ $workspace_status -eq 0 ]]; then
@@ -255,27 +259,48 @@ if [[ $workspace_status -eq 0 ]]; then
exit 1
fi
local_manual_scattered="$negative_root/local-manual-scattered.md"
cp "$root/docs/install/local-workspace-registry.md" "$local_manual_scattered"
python3 - "$local_manual_scattered" <<'PY'
import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
text = text.replace(
"| Workspace semantic index | Each workspace reserves a single Qdrant collection. | Schema, Evidence, and Memory stay in that one collection and remain isolated by payload `kind`. |\n",
"",
)
text += "\nWorkspace. Qdrant. Collection. Schema. Evidence. Memory. Payload kind.\n"
path.write_text(text)
PY
set +e
verify_markdown_table_relationships "$local_manual_scattered" "local manual scattered ownership" "Semantic index ownership contract" "$semantic_index_spec" >"$workspace_output" 2>&1
workspace_status=$?
set -e
if [[ $workspace_status -eq 0 ]]; then
echo "scattered ownership tokens fixture was not rejected correctly" >&2
cat "$workspace_output" >&2
exit 1
fi
compact_paraphrase="$negative_root/compact-paraphrase.md"
cp "$root/docs/installazione-docker-4-contesti.md" "$compact_paraphrase"
python3 - "$compact_paraphrase" <<'PY'
import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
text = text.replace(
"Qdrant e Ollama embedding sono servizi interni obbligatori del progetto Compose. Restano esterni solo DWH e LLM.",
"Nel Compose di ThothII Qdrant e l'embedding Ollama fanno parte dei servizi interni obbligatori; DWH e LLM restano invece gli unici servizi esterni.",
)
text = text.replace("| DWH | Esterno | Endpoint esterno configurato dall'installazione. |", "| DWH | Esterno | Endpoint esterno deciso dall'installazione. |")
text = text.replace("| LLM | Esterno | Endpoint o policy esterna all'infrastruttura semantica interna. |", "| LLM | Esterno | Endpoint o policy che resta esterna all'infrastruttura semantica interna. |")
text = text.replace("| Qdrant | Interno | Servizio Compose interno obbligatorio con volume persistente `qdrant-data`. |", "| Qdrant | Interno | Servizio Compose interno obbligatorio con il volume persistente `qdrant-data`. |")
text = text.replace("| Ollama embedding | Interno | Servizio Compose interno obbligatorio per `qwen3-embedding:0.6b`. |", "| Ollama embedding | Interno | Servizio Compose interno obbligatorio dedicato a `qwen3-embedding:0.6b`. |")
path.write_text(text)
PY
for pattern in \
'Qdrant' \
'Ollama' \
'(interni obbligatori|servizi interni obbligatori|interni al progetto Compose)' \
'DWH' \
'LLM' \
'(esterni solo|solo esterni|restano esterni|unici servizi esterni|unici esterni)'; do
require_pattern "$compact_paraphrase" "compact manual paraphrase" "$pattern" >/dev/null
done
compact_spec='{"rows":[
{"componente":"^DWH$","ownership":"^Esterno$","contratto operativo":"endpoint.*estern"},
{"componente":"^LLM$","ownership":"^Esterno$","contratto operativo":"esterna|esterno"},
{"componente":"^Qdrant$","ownership":"^Interno$","contratto operativo":"interno.*obbligatorio.*qdrant-data"},
{"componente":"^Ollama embedding$","ownership":"^Interno$","contratto operativo":"interno.*obbligatorio.*qwen3-embedding:0\\.6b"}
]}'
verify_markdown_table_relationships "$compact_paraphrase" "compact manual paraphrase" "Contratto sintetico di ownership" "$compact_spec" >/dev/null
compact_inversion="$negative_root/compact-inversion.md"
cp "$root/docs/installazione-docker-4-contesti.md" "$compact_inversion"
@@ -283,14 +308,11 @@ python3 - "$compact_inversion" <<'PY'
import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
text = text.replace(
"Qdrant e Ollama embedding sono servizi interni obbligatori del progetto Compose. Restano esterni solo DWH e LLM.",
"Qdrant, Ollama, DWH e LLM restano tutti servizi esterni.",
)
text = text.replace("| Qdrant | Interno | Servizio Compose interno obbligatorio con volume persistente `qdrant-data`. |", "| Qdrant | Esterno | Servizio esterno condiviso. |")
path.write_text(text)
PY
set +e
require_pattern "$compact_inversion" "compact inversion" '(interni obbligatori|servizi interni obbligatori|interni al progetto Compose)' >"$workspace_output" 2>&1
verify_markdown_table_relationships "$compact_inversion" "compact inversion" "Contratto sintetico di ownership" "$compact_spec" >"$workspace_output" 2>&1
workspace_status=$?
set -e
if [[ $workspace_status -eq 0 ]]; then
@@ -299,6 +321,27 @@ if [[ $workspace_status -eq 0 ]]; then
exit 1
fi
compact_scattered="$negative_root/compact-scattered.md"
cp "$root/docs/installazione-docker-4-contesti.md" "$compact_scattered"
python3 - "$compact_scattered" <<'PY'
import pathlib, sys
path = pathlib.Path(sys.argv[1])
text = path.read_text()
start = text.index("## Contratto sintetico di ownership")
end = text.index("## Comando standard locale")
text = text[:start] + "Qdrant Interno DWH Esterno LLM Esterno Ollama embedding Interno.\n\n" + text[end:]
path.write_text(text)
PY
set +e
verify_markdown_table_relationships "$compact_scattered" "compact scattered tokens" "Contratto sintetico di ownership" "$compact_spec" >"$workspace_output" 2>&1
workspace_status=$?
set -e
if [[ $workspace_status -eq 0 ]]; then
echo "compact scattered-token fixture was not rejected correctly" >&2
cat "$workspace_output" >&2
exit 1
fi
adapted_reorder="$negative_root/caddy-adapted-reorder.json"
adapted_bypass="$negative_root/caddy-adapted-bypass.json"
node - "$adapted_reorder" "$adapted_bypass" <<'NODE'
scripts/verify-workspace-install-docs.sh
+73 -9
View File
@@ -105,6 +105,56 @@ for token in tokens:
PY
}
verify_markdown_table_relationships() {
local source="$1" label="$2" heading="$3" spec_json="$4"
python3 - "$source" "$label" "$heading" "$spec_json" <<'PY'
import json, pathlib, re, sys
path = pathlib.Path(sys.argv[1])
label = sys.argv[2]
heading = sys.argv[3]
spec = json.loads(sys.argv[4])
text = path.read_text()
match = re.search(rf"^##+\s+{re.escape(heading)}\s*$", text, re.MULTILINE)
if not match:
raise SystemExit(f"{label}: missing structured section '{heading}'")
lines = text[match.end():].splitlines()
table = []
for line in lines:
if not line.strip():
if table:
break
continue
if not line.lstrip().startswith("|"):
if table:
break
continue
table.append(line.rstrip())
if len(table) < 3:
raise SystemExit(f"{label}: structured table '{heading}' is incomplete")
headers = [cell.strip().lower() for cell in table[0].strip().strip("|").split("|")]
rows = []
for raw in table[2:]:
cells = [cell.strip() for cell in raw.strip().strip("|").split("|")]
if len(cells) != len(headers):
raise SystemExit(f"{label}: malformed row in '{heading}'")
rows.append(dict(zip(headers, cells)))
for row_spec in spec["rows"]:
found = False
for row in rows:
ok = True
for column, pattern in row_spec.items():
value = row.get(column.lower(), "")
if not re.search(pattern, value, re.IGNORECASE | re.DOTALL):
ok = False
break
if ok:
found = True
break
if not found:
raise SystemExit(f"{label}: missing relationship in '{heading}': {row_spec}")
PY
}
verify_compose_internal_semantic_contract() {
python3 - "$root/compose.yaml" <<'PY'
import sys, yaml, pathlib
@@ -251,6 +301,29 @@ verify_internal_semantic_infrastructure_docs() {
verify_vector_helper_interfaces || return 1
verify_project_state_current_contract "$root/PROJECT_STATE.md" "PROJECT_STATE.md" || return 1
local ownership_spec semantic_index_spec compact_spec
ownership_spec='{"rows":[
{"component":"^DWH$","ownership":"^External$","operator contract":"external|endpoint|installation"},
{"component":"^LLM$","ownership":"^External$","operator contract":"external|endpoint|policy"},
{"component":"^Qdrant$","ownership":"^Internal$","operator contract":"internal|Compose|qdrant-data"},
{"component":"^Ollama embedding$","ownership":"^Internal$","operator contract":"internal|Compose|qwen3-embedding:0\\.6b"}
]}'
semantic_index_spec='{"rows":[
{"scope":"workspace semantic index","ownership rule":"(each|one|single).*(workspace).*(single|one).*(Qdrant).*(collection)|(each workspace reserves a single qdrant collection)","isolation rule":"schema.*evidence.*memory.*(one|that).*(collection).*(kind|payload)"}
]}'
compact_spec='{"rows":[
{"componente":"^DWH$","ownership":"^Esterno$","contratto operativo":"endpoint.*estern"},
{"componente":"^LLM$","ownership":"^Esterno$","contratto operativo":"esterna|esterno"},
{"componente":"^Qdrant$","ownership":"^Interno$","contratto operativo":"interno.*obbligatorio.*qdrant-data"},
{"componente":"^Ollama embedding$","ownership":"^Interno$","contratto operativo":"interno.*obbligatorio.*qwen3-embedding:0\\.6b"}
]}'
verify_markdown_table_relationships "$local_manual" "local workspace manual" "Architecture ownership contract" "$ownership_spec" || return 1
verify_markdown_table_relationships "$server_manual" "server workspace manual" "Architecture ownership contract" "$ownership_spec" || return 1
verify_markdown_table_relationships "$local_manual" "local workspace manual" "Semantic index ownership contract" "$semantic_index_spec" || return 1
verify_markdown_table_relationships "$server_manual" "server workspace manual" "Semantic index ownership contract" "$semantic_index_spec" || return 1
verify_markdown_table_relationships "$compact_manual" "four-context install note" "Contratto sintetico di ownership" "$compact_spec" || return 1
require_pattern "$readme" "README" 'mandatory stack.+qdrant.+embedding.+embedding-model-init' || return 1
require_pattern "$readme" "README" 'qwen3-embedding:0\.6b' || return 1
require_pattern "$readme" "README" 'qdrant-data.+embedding-models' || return 1
@@ -260,19 +333,10 @@ verify_internal_semantic_infrastructure_docs() {
for manual in "$local_manual" "$server_manual"; do
require_pattern "$manual" "$(basename "$manual")" 'qwen3-embedding:0\.6b' || return 1
require_pattern "$manual" "$(basename "$manual")" 'migration_required' || return 1
require_concept_tokens "$manual" "$(basename "$manual")" \
"workspace" "qdrant" "collection" || return 1
require_pattern "$manual" "$(basename "$manual")" '(?is)(one|single|each).{0,120}(workspace|qdrant|collection).{0,120}(owns|reserve|reserved|single)' || return 1
done
require_pattern "$local_manual" "local workspace manual" 'CPU-first' || return 1
require_pattern "$local_manual" "local workspace manual" 'THOTH_ENABLE_EMBEDDING_GPU=1' || return 1
require_pattern "$server_manual" "server workspace manual" 'Qdrant backup/restore' || return 1
require_pattern "$server_manual" "server workspace manual" '(Git remote|DWH|LLM|bastion)' || return 1
require_pattern "$server_manual" "server workspace manual" '(stay external|remain external|sono esterni)' || return 1
require_concept_tokens "$compact_manual" "four-context install note" \
"qdrant" "ollama" "dwh" "llm" || return 1
require_pattern "$compact_manual" "four-context install note" '(?is)(interni obbligatori|servizi interni obbligatori|interni al progetto compose)' || return 1
require_pattern "$compact_manual" "four-context install note" '(?is)(esterni solo|solo esterni|restano esterni|unici servizi esterni|unici esterni)' || return 1
require_pattern "$compact_manual" "four-context install note" '1024 dimensioni' || return 1
require_pattern "$diagnostics" "workspace diagnostic protocol" 'schema version 3' || return 1
require_pattern "$diagnostics" "workspace diagnostic protocol" 'semantic_index_incompatible' || return 1