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

refactor(harness): route workflow persistence through repositories

Browse Source
This commit is contained in:
User
2026-07-16 18:01:29 +02:00
parent 259f021313
commit c1cddaa667
30 changed files with 925 additions and 348 deletions
Download Patch File Download Diff File Expand all files Collapse all files
harness/tht/phase.py
+48 -37
View File
@@ -17,7 +17,7 @@ from pathlib import Path
from pydantic import ValidationError
from tht.decisions import DecisionRecord, list_decisions
from tht.session.models import SchemaLinking
from tht.session.models import SchemaLinking, SessionSnapshot
from tht.workflow import load_workflow
@@ -31,11 +31,22 @@ def _phase_num(subject: str) -> int | None:
return None
def _audit_excluding_retracted(session_dir: Path) -> list[DecisionRecord]:
def _decisions(source: Path | SessionSnapshot) -> list[DecisionRecord]:
return list(source.decisions) if isinstance(source, SessionSnapshot) else list_decisions(source)
def _artifact(source: Path | SessionSnapshot, key: str, filename: str) -> str | None:
if isinstance(source, SessionSnapshot):
return source.artifacts.get(key)
path = source / filename
return path.read_text() if path.exists() else None
def _audit_excluding_retracted(source: Path | SessionSnapshot) -> list[DecisionRecord]:
"""Tutto il ledger (append-only) tranne le decisioni ritirate e i marker di ritrazione.
Base per il fold di current_phase: il guard 'n == cur' del fold e' gia' reopen-aware
(una phase_approved:N dopo un reopen a M<N non fa avanzare perche' cur!=N)."""
all_d = list_decisions(session_dir)
all_d = _decisions(source)
retracted_seqs = {
d.retracts for d in all_d if d.type == "decision_retracted" and d.retracts is not None
}
@@ -46,7 +57,7 @@ def _audit_excluding_retracted(session_dir: Path) -> list[DecisionRecord]:
]
def current_phase(session_dir: Path) -> int:
def current_phase(source: Path | SessionSnapshot) -> int:
"""Fase corrente come fold cronologico sull'audit (con ritirate escluse).
cur parte da 1; ogni phase_approved/phase_auto_approved per la fase CORRENTE avanza
@@ -57,7 +68,7 @@ def current_phase(session_dir: Path) -> int:
wf = load_workflow()
max_plus_one = wf.max_phase + 1
cur = 1
for d in _audit_excluding_retracted(session_dir):
for d in _audit_excluding_retracted(source):
n = _phase_num(d.subject)
if n is None:
continue
@@ -68,7 +79,7 @@ def current_phase(session_dir: Path) -> int:
return cur
def effective_decisions(session_dir: Path) -> list[DecisionRecord]:
def effective_decisions(source: Path | SessionSnapshot) -> list[DecisionRecord]:
"""La vista canonica 'effective as of pointer'. TUTTI gli helper non-fold devono usare questa.
Semantica: una decisione e' effective se appartiene a una fase <= current_phase.
@@ -81,9 +92,9 @@ def effective_decisions(session_dir: Path) -> list[DecisionRecord]:
Inoltre esclude le decisioni ritirate (decision_retracted) e i marker stessi.
"""
cur = current_phase(session_dir)
cur = current_phase(source)
out: list[DecisionRecord] = []
for d in _audit_excluding_retracted(session_dir):
for d in _audit_excluding_retracted(source):
n = _phase_num(d.subject)
# Per le decisioni con subject "a nome" (es. cte_approved -> nome CTE, evidence_*
# -> id evidence) il subject non porta la fase: si usa la fase emittente registrata
@@ -106,9 +117,9 @@ _META_TYPES = frozenset(
)
def substantive_count_current_phase(session_dir: Path) -> int:
def substantive_count_current_phase(source: Path | SessionSnapshot) -> int:
"""Numero di decisioni sostanziali dall'ultimo confine di fase (vista effective)."""
decs = effective_decisions(session_dir)
decs = effective_decisions(source)
start = 0
for i, d in enumerate(decs):
if d.type in _BOUNDARY_TYPES:
@@ -116,14 +127,14 @@ def substantive_count_current_phase(session_dir: Path) -> int:
return sum(1 for d in decs[start:] if d.type not in _META_TYPES)
def auto_advance_eligible(session_dir: Path) -> bool:
def auto_advance_eligible(source: Path | SessionSnapshot) -> bool:
"""Vero sse la fase corrente puo' auto-avanzare (zero decisioni sostanziali + prereq ok)."""
cur = current_phase(session_dir)
cur = current_phase(source)
if cur not in _AUTO_ADVANCE_PHASES:
return False
if substantive_count_current_phase(session_dir) > 0:
if substantive_count_current_phase(source) > 0:
return False
return not advance_problems(session_dir, cur)
return not advance_problems(source, cur)
# --- CTE helpers (consultano effective_decisions) ---------------------------
@@ -131,21 +142,21 @@ def auto_advance_eligible(session_dir: Path) -> bool:
CTE_PLAN_FILE = "cte_plan.json"
def cte_plan(session_dir: Path) -> list[str]:
path = session_dir / CTE_PLAN_FILE
if not path.exists():
def cte_plan(source: Path | SessionSnapshot) -> list[str]:
raw = _artifact(source, "cte_plan", CTE_PLAN_FILE)
if raw is None:
return []
return json.loads(path.read_text())
return json.loads(raw)
def approved_ctes(session_dir: Path) -> set[str]:
def approved_ctes(source: Path | SessionSnapshot) -> set[str]:
"""Insieme dei CTE approvati, dalla vista effective (esclude stale post-reopen)."""
return {d.subject for d in effective_decisions(session_dir) if d.type == "cte_approved"}
return {d.subject for d in effective_decisions(source) if d.type == "cte_approved"}
def next_cte(session_dir: Path) -> str | None:
approved = approved_ctes(session_dir)
for name in cte_plan(session_dir):
def next_cte(source: Path | SessionSnapshot) -> str | None:
approved = approved_ctes(source)
for name in cte_plan(source):
if name not in approved:
return name
return None
@@ -153,18 +164,18 @@ def next_cte(session_dir: Path) -> str | None:
# --- advance_problems (ladder if-phase-N che consulta effective_decisions) ---
def _has_decision(session_dir: Path, type_: str) -> bool:
return any(d.type == type_ for d in effective_decisions(session_dir))
def _has_decision(source: Path | SessionSnapshot, type_: str) -> bool:
return any(d.type == type_ for d in effective_decisions(source))
def _has_decision_subject(session_dir: Path, type_: str, subject: str) -> bool:
def _has_decision_subject(source: Path | SessionSnapshot, type_: str, subject: str) -> bool:
return any(
d.type == type_ and d.subject == subject
for d in effective_decisions(session_dir)
for d in effective_decisions(source)
)
def advance_problems(session_dir: Path, phase: int) -> list[str]:
def advance_problems(source: Path | SessionSnapshot, phase: int) -> list[str]:
"""Prerequisiti minimi per chiudere `phase` (lista vuota = ok).
Ladder if-phase-N (Strada 2): la logica specifica resta, ma ogni lettura passa per
@@ -172,19 +183,19 @@ def advance_problems(session_dir: Path, phase: int) -> list[str]:
l'evaluator generico (F2 pieno) entra in un secondo momento.
"""
problems: list[str] = []
if phase == 3 and not _has_decision(session_dir, "question_rewritten"):
if phase == 3 and not _has_decision(source, "question_rewritten"):
problems.append("manca la decisione question_rewritten (Fase 3)")
if phase == 5:
path = session_dir / "schema_linking.json"
if not path.exists():
raw = _artifact(source, "schema_linking", "schema_linking.json")
if raw is None:
problems.append("schema_linking.json assente (Fase 5)")
else:
try:
SchemaLinking.model_validate(json.loads(path.read_text()))
SchemaLinking.model_validate(json.loads(raw))
except (json.JSONDecodeError, ValidationError) as e:
problems.append(f"schema_linking.json non valido (Fase 5): {e}")
if phase == 6 and not _has_decision_subject(session_dir, "phase_skipped", "phase:6"):
plan = cte_plan(session_dir)
if phase == 6 and not _has_decision_subject(source, "phase_skipped", "phase:6"):
plan = cte_plan(source)
if not plan:
problems.append(
"Fase 6: nessun piano CTE (cte_plan.json) e nessun salto esplicito. "
@@ -192,14 +203,14 @@ def advance_problems(session_dir: Path, phase: int) -> list[str]:
"registrando una decisione phase_skipped subject phase:6."
)
else:
nc = next_cte(session_dir)
nc = next_cte(source)
if nc is not None:
problems.append(f"CTE non ancora approvato: {nc} (Fase 6)")
if phase == 7 and not _has_decision(session_dir, "sql_approved"):
if phase == 7 and not _has_decision(source, "sql_approved"):
problems.append("manca la decisione sql_approved (Fase 7)")
if phase == 8 and not any(
d.type in ("datamart_requested", "datamart_declined")
for d in effective_decisions(session_dir)
for d in effective_decisions(source)
):
problems.append(
"Fase 8: nessuna risposta sulla generazione dbt del datamart "