This commit is contained in:
Lars committed 2026-08-26 10:42:20 +02:00
1 parent 60f0d2830d
commit 53b1eff833
62 files changed
+6578 -355

No files matched your search

+190 -37
View File
@@ -1,7 +1,9 @@
"""Writing profile store with facets, governance, and evidence. AI drafts are never a positive style source."""
from __future__ import annotations
import hashlib
import json
import re
import uuid
from db import get_db, row_to_dict
@@ -44,6 +46,13 @@ BRIEF_IMPORT_EXCERPTS = 6
INITIAL_BUILD_SOURCES = 40
EXCERPT_CHARS = 1200
TRAIT_EXCERPT_CHARS = 280
TASK_BRIEF_MAX_CHARS = 4000
TASK_BRIEF_CORE_CHARS = 800
TASK_BRIEF_FACET_CHARS = 700
TASK_BRIEF_TRAIT_CHARS = 280
TASK_BRIEF_EXEMPLAR_CHARS = 220
TASK_BRIEF_MAX_TRAITS = 6
TASK_BRIEF_MAX_EXEMPLARS = 2
DIALOGUE_KIND = "dialogue_style"
MAX_DIALOGUE_MESSAGES = 8
MAX_DIALOGUE_CHARS = 500
@@ -980,6 +989,104 @@ def _load_ranked_sources(profile_id: str) -> dict[str, list[dict]]:
return {"journal_entry": entries, "imported_text": imports, "dialogue_style": dialogue}
def _source_content_digest(item: dict) -> str:
body = re.sub(r"\s+", " ", plain_text(item.get("body") or "")).strip().lower()
return hashlib.sha256(body.encode("utf-8")).hexdigest()
def _dedupe_brief_sources(items: list[dict], *, seen_keys: set[tuple[str, str]] | None = None) -> list[dict]:
"""Display-only. Originals remain in writing_profile_sources."""
seen_entry: set[str] = set()
seen = seen_keys if seen_keys is not None else set()
result = []
for item in items:
entry_id = (item.get("entry_id") or "").strip()
if entry_id:
if entry_id in seen_entry:
continue
seen_entry.add(entry_id)
when = (item.get("occurred_at") or "")[:10]
digest = _source_content_digest(item)
key = (when, digest)
if key in seen:
continue
seen.add(key)
result.append(item)
return result
def _clip_field(text: str, limit: int) -> str:
raw = (text or "").strip()
if limit <= 0 or not raw:
return ""
if len(raw) <= limit:
return raw
cut = raw[:limit]
if not raw[limit].isspace():
sp = max(cut.rfind(" "), cut.rfind("\n"), cut.rfind("\t"))
if sp >= max(1, limit // 3):
cut = cut[:sp]
else:
return ""
return cut.rstrip(" \t\n,;:-")
def _norm_overlap(left: str, right: str) -> float:
a = re.sub(r"\s+", " ", (left or "").strip().lower())
b = re.sub(r"\s+", " ", (right or "").strip().lower())
if not a or not b:
return 0.0
if a == b or a in b or b in a:
return min(len(a), len(b)) / max(len(a), len(b))
return 0.0
def _trait_recency_stamp(item: dict) -> str | None:
stamps = [item.get("updated"), item.get("observed_to"), item.get("observed_from")]
for ref in item.get("exemplars") or []:
stamps.append(ref.get("occurred_at"))
stamps = [stamp for stamp in stamps if stamp]
return max(stamps) if stamps else None
def _select_task_traits(traits: list[dict]) -> list[dict]:
relevant = [
item
for item in traits
if item.get("status") == "active"
and (item.get("statement") or "")
and item.get("facet_key") in {"autobiographical_journal", "core", ""}
]
if not relevant:
relevant = [item for item in traits if item.get("status") == "active" and (item.get("statement") or "")]
current = []
long_term = []
for item in relevant:
stamp = _trait_recency_stamp(item)
role = recency_role(stamp)
weight = recency_weight(stamp)
scored = (item, weight, role)
if role == "current_expression":
current.append(scored)
else:
long_term.append(scored)
current.sort(key=lambda row: (-row[1], row[0].get("slug") or ""))
long_term.sort(key=lambda row: (-row[1], row[0].get("slug") or ""))
picked: list[dict] = []
for item, _, _ in current[:4]:
picked.append(item)
for item, _, _ in long_term:
if len(picked) >= TASK_BRIEF_MAX_TRAITS:
break
picked.append(item)
if len(picked) < TASK_BRIEF_MAX_TRAITS:
for item, _, _ in current[4:]:
if len(picked) >= TASK_BRIEF_MAX_TRAITS:
break
picked.append(item)
return picked[:TASK_BRIEF_MAX_TRAITS]
def _source_line(item: dict) -> str:
when = (item.get("occurred_at") or "")[:10]
role = recency_role(item.get("occurred_at") or item.get("created"))
@@ -989,8 +1096,9 @@ def _source_line(item: dict) -> str:
def _assemble_brief(profile_id: str) -> None:
ranked = _load_ranked_sources(profile_id)
entries = ranked["journal_entry"][:BRIEF_ENTRY_EXCERPTS]
imports = ranked["imported_text"][:BRIEF_IMPORT_EXCERPTS]
display_keys: set[tuple[str, str]] = set()
entries = _dedupe_brief_sources(ranked["journal_entry"], seen_keys=display_keys)[:BRIEF_ENTRY_EXCERPTS]
imports = _dedupe_brief_sources(ranked["imported_text"], seen_keys=display_keys)[:BRIEF_IMPORT_EXCERPTS]
dialogue = ranked["dialogue_style"]
profile_row = ensure_profile(profile_id)
with get_db() as conn:
@@ -1067,46 +1175,91 @@ def compile_task_brief(profile_id: str, task: str = "journal_generate") -> str:
from writing_profile_schema import is_meta_style_text
profile = get_profile(profile_id)
parts = []
core = profile.get("core") or {}
if core.get("value"):
parts.append("Core: " + (core.get("value") or ""))
traits = [item for item in profile.get("traits") or [] if item.get("status") == "active"]
if task == "journal_generate":
facet = next(
(
item
for item in profile.get("facets") or []
if item.get("facet_key") == "autobiographical_journal" and (item.get("value") or "")
),
None,
)
if facet:
parts.append("Autobiografisches Journaling (Facet-Delta): " + (facet.get("value") or ""))
relevant = [
if task != "journal_generate":
core = (profile.get("core") or {}).get("value") or ""
return _clip_field(core, TASK_BRIEF_MAX_CHARS)
parts: list[str] = []
core_text = ((profile.get("core") or {}).get("value") or "").strip()
if core_text:
clipped = _clip_field(core_text, TASK_BRIEF_CORE_CHARS)
if clipped:
parts.append("Core: " + clipped)
facet = next(
(
item
for item in traits
if item.get("facet_key") in {"autobiographical_journal", "core", ""} and (item.get("statement") or "")
]
if not relevant:
relevant = [item for item in traits if item.get("statement")]
for item in relevant[:6]:
line = f"- {item.get('label') or item.get('slug')}: {item.get('statement')}"
exemplars = [
ref.get("excerpt")
for ref in item.get("exemplars") or []
if ref.get("excerpt") and not is_meta_style_text(ref.get("excerpt"))
]
if exemplars:
line += " Beispiel: " + exemplars[0][:TRAIT_EXCERPT_CHARS]
parts.append(line)
if parts:
return "\n".join(parts).strip()
for item in profile.get("facets") or []
if item.get("facet_key") == "autobiographical_journal" and (item.get("value") or "")
),
None,
)
facet_text = ((facet or {}).get("value") or "").strip()
if facet_text and _norm_overlap(facet_text, core_text) < 0.8:
clipped = _clip_field(facet_text, TASK_BRIEF_FACET_CHARS)
if clipped:
parts.append("Autobiografisches Journaling (Facet-Delta): " + clipped)
selected = _select_task_traits(profile.get("traits") or [])
used_statements = [core_text, facet_text]
for item in selected:
statement = (item.get("statement") or "").strip()
if any(_norm_overlap(statement, previous) >= 0.85 for previous in used_statements if previous):
continue
clipped = _clip_field(statement, TASK_BRIEF_TRAIT_CHARS)
if not clipped:
continue
parts.append(f"- {item.get('label') or item.get('slug')}: {clipped}")
used_statements.append(statement)
exemplars: list[tuple[float, str]] = []
seen_ex = set()
for item in selected:
for ref in item.get("exemplars") or []:
excerpt = (ref.get("excerpt") or "").strip()
if not excerpt or is_meta_style_text(excerpt):
continue
digest = hashlib.sha256(re.sub(r"\s+", " ", excerpt.lower()).encode("utf-8")).hexdigest()
if digest in seen_ex:
continue
seen_ex.add(digest)
clipped = _clip_field(excerpt, TASK_BRIEF_EXEMPLAR_CHARS)
if not clipped:
continue
weight = recency_weight(ref.get("occurred_at") or _trait_recency_stamp(item))
exemplars.append((weight, clipped))
exemplars.sort(key=lambda row: -row[0])
chosen = []
for _, excerpt in exemplars:
if any(_norm_overlap(excerpt, prev) >= 0.8 for prev in chosen):
continue
chosen.append(excerpt)
if len(chosen) >= TASK_BRIEF_MAX_EXEMPLARS:
break
if chosen:
parts.append("Repräsentative Exemplare:")
for excerpt in chosen:
parts.append("- " + excerpt)
brief = "\n".join(part for part in parts if part).strip()
if len(brief) > TASK_BRIEF_MAX_CHARS:
without_examples = [part for part in parts if not part.startswith("Repräsentative Exemplare") and not (
part.startswith("- ") and chosen and any(part == "- " + excerpt for excerpt in chosen)
)]
brief = "\n".join(without_examples).strip()
parts = without_examples
while len(brief) > TASK_BRIEF_MAX_CHARS and parts:
last = parts.pop()
remain = TASK_BRIEF_MAX_CHARS - (len("\n".join(parts)) + (1 if parts else 0))
clipped = _clip_field(last, remain)
if clipped:
parts.append(clipped)
brief = "\n".join(parts).strip()
break
brief = "\n".join(parts).strip()
if brief:
return brief
ranked = _load_ranked_sources(profile_id)
snippets = (ranked.get("journal_entry") or [])[:2] + (ranked.get("imported_text") or [])[:1]
lines = []
for item in snippets:
body = plain_text(item.get("body") or "")[:280]
body = _clip_field(plain_text(item.get("body") or ""), 280)
if body and not is_meta_style_text(body):
lines.append(body)
return "\n\n".join(lines).strip()