Antoine/ATOCore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: fold project-scoped memories into context pack

Browse Source 
The retrieval-quality review on 2026-04-11 found that active
project/knowledge/episodic memories never reached the pack: only
Trusted Project State and identity/preference memories were being
assembled. Reinforcement bumped confidence on memories that had
no retrieval outlet, so the reflection loop was half-open.

This change adds a third memory tier between identity/preference
and retrieved chunks:

- PROJECT_MEMORY_BUDGET_RATIO = 0.15
- Memory types: project, knowledge, episodic
- Only populated when a canonical project is in scope — without
  a project hint, project memories stay out (cross-project bleed
  would rot the signal)
- Rendered under a dedicated "--- Project Memories ---" header
  so the LLM can distinguish it from the identity/preference band
- Trim order in _trim_context_to_budget: retrieval → project
  memories → identity/preference → project state (most recently
  added tier drops first when budget is tight)

get_memories_for_context gains header/footer kwargs so the two
memory blocks can be distinguished in a single pack without a
second helper.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Anto01
2026-04-11 11:35:40 -04:00
parent 9366ba7879
commit 8ea53f4003
3 changed files with 134 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
src/atocore/context/builder.py
View File

@@ -30,6 +30,12 @@ SYSTEM_PREFIX = (
# identity: 5%, preferences: 5%, project state: 20%, retrieval: 60%+
PROJECT_STATE_BUDGET_RATIO = 0.20
MEMORY_BUDGET_RATIO = 0.10 # 5% identity + 5% preference
# Project-scoped memories (project/knowledge/episodic) are the outlet
# for the Phase 9 reflection loop on the retrieval side. Budget sits
# between identity/preference and retrieved chunks so a reinforced
# memory can actually reach the model.
PROJECT_MEMORY_BUDGET_RATIO = 0.15
PROJECT_MEMORY_TYPES = ["project", "knowledge", "episodic"]
# Last built context pack for debug inspection
_last_context_pack: "ContextPack | None" = None
@@ -51,6 +57,8 @@ class ContextPack:
project_state_chars: int = 0
memory_text: str = ""
memory_chars: int = 0
project_memory_text: str = ""
project_memory_chars: int = 0
total_chars: int = 0
budget: int = 0
budget_remaining: int = 0
@@ -109,8 +117,28 @@ def build_context(
budget=memory_budget,
)
# 2b. Get project-scoped memories (third precedence). Only
# populated when a canonical project is in scope — cross-project
# memory bleed would rot the pack. Active-only filtering is
# handled by the shared min_confidence=0.5 gate inside
# get_memories_for_context.
project_memory_text = ""
project_memory_chars = 0
if canonical_project:
project_memory_budget = min(
int(budget * PROJECT_MEMORY_BUDGET_RATIO),
max(budget - project_state_chars - memory_chars, 0),
)
project_memory_text, project_memory_chars = get_memories_for_context(
memory_types=PROJECT_MEMORY_TYPES,
project=canonical_project,
budget=project_memory_budget,
header="--- Project Memories ---",
footer="--- End Project Memories ---",
)
# 3. Calculate remaining budget for retrieval
retrieval_budget = budget - project_state_chars - memory_chars
retrieval_budget = budget - project_state_chars - memory_chars - project_memory_chars
# 4. Retrieve candidates
candidates = (
@@ -130,11 +158,14 @@ def build_context(
selected = _select_within_budget(scored, max(retrieval_budget, 0))
# 7. Format full context
formatted = _format_full_context(project_state_text, memory_text, selected)
formatted = _format_full_context(
project_state_text, memory_text, project_memory_text, selected
)
if len(formatted) > budget:
formatted, selected = _trim_context_to_budget(
project_state_text,
memory_text,
project_memory_text,
selected,
budget,
)
@@ -144,6 +175,7 @@ def build_context(
project_state_chars = len(project_state_text)
memory_chars = len(memory_text)
project_memory_chars = len(project_memory_text)
retrieval_chars = sum(c.char_count for c in selected)
total_chars = len(formatted)
duration_ms = int((time.time() - start) * 1000)
@@ -154,6 +186,8 @@ def build_context(
project_state_chars=project_state_chars,
memory_text=memory_text,
memory_chars=memory_chars,
project_memory_text=project_memory_text,
project_memory_chars=project_memory_chars,
total_chars=total_chars,
budget=budget,
budget_remaining=budget - total_chars,
@@ -171,6 +205,7 @@ def build_context(
chunks_used=len(selected),
project_state_chars=project_state_chars,
memory_chars=memory_chars,
project_memory_chars=project_memory_chars,
retrieval_chars=retrieval_chars,
total_chars=total_chars,
budget_remaining=budget - total_chars,
@@ -250,6 +285,7 @@ def _select_within_budget(
def _format_full_context(
project_state_text: str,
memory_text: str,
project_memory_text: str,
chunks: list[ContextChunk],
) -> str:
"""Format project state + memories + retrieved chunks into full context block."""
@@ -265,7 +301,12 @@ def _format_full_context(
parts.append(memory_text)
parts.append("")
# 3. Retrieved chunks (lowest trust)
# 3. Project-scoped memories (third trust level)
if project_memory_text:
parts.append(project_memory_text)
parts.append("")
# 4. Retrieved chunks (lowest trust)
if chunks:
parts.append("--- AtoCore Retrieved Context ---")
if project_state_text:
@@ -277,7 +318,7 @@ def _format_full_context(
parts.append(chunk.content)
parts.append("")
parts.append("--- End Context ---")
elif not project_state_text and not memory_text:
elif not project_state_text and not memory_text and not project_memory_text:
parts.append("--- AtoCore Context ---\nNo relevant context found.\n--- End Context ---")
return "\n".join(parts)
@@ -299,6 +340,7 @@ def _pack_to_dict(pack: ContextPack) -> dict:
"project_hint": pack.project_hint,
"project_state_chars": pack.project_state_chars,
"memory_chars": pack.memory_chars,
"project_memory_chars": pack.project_memory_chars,
"chunks_used": len(pack.chunks_used),
"total_chars": pack.total_chars,
"budget": pack.budget,
@@ -306,6 +348,7 @@ def _pack_to_dict(pack: ContextPack) -> dict:
"duration_ms": pack.duration_ms,
"has_project_state": bool(pack.project_state_text),
"has_memories": bool(pack.memory_text),
"has_project_memories": bool(pack.project_memory_text),
"chunks": [
{
"source_file": c.source_file,
@@ -335,26 +378,45 @@ def _truncate_text_block(text: str, budget: int) -> tuple[str, int]:
def _trim_context_to_budget(
project_state_text: str,
memory_text: str,
project_memory_text: str,
chunks: list[ContextChunk],
budget: int,
) -> tuple[str, list[ContextChunk]]:
"""Trim retrieval first, then memory, then project state until formatted context fits."""
"""Trim retrieval → project memories → identity/preference → project state."""
kept_chunks = list(chunks)
formatted = _format_full_context(project_state_text, memory_text, kept_chunks)
formatted = _format_full_context(
project_state_text, memory_text, project_memory_text, kept_chunks
)
while len(formatted) > budget and kept_chunks:
kept_chunks.pop()
formatted = _format_full_context(project_state_text, memory_text, kept_chunks)
formatted = _format_full_context(
project_state_text, memory_text, project_memory_text, kept_chunks
)
if len(formatted) <= budget:
return formatted, kept_chunks
# Drop project memories next (they were the most recently added
# tier and carry less trust than identity/preference).
project_memory_text, _ = _truncate_text_block(
project_memory_text,
max(budget - len(project_state_text) - len(memory_text), 0),
)
formatted = _format_full_context(
project_state_text, memory_text, project_memory_text, kept_chunks
)
if len(formatted) <= budget:
return formatted, kept_chunks
memory_text, _ = _truncate_text_block(memory_text, max(budget - len(project_state_text), 0))
formatted = _format_full_context(project_state_text, memory_text, kept_chunks)
formatted = _format_full_context(
project_state_text, memory_text, project_memory_text, kept_chunks
)
if len(formatted) <= budget:
return formatted, kept_chunks
project_state_text, _ = _truncate_text_block(project_state_text, budget)
formatted = _format_full_context(project_state_text, "", [])
formatted = _format_full_context(project_state_text, "", "", [])
if len(formatted) > budget:
formatted, _ = _truncate_text_block(formatted, budget)
return formatted, []

9
src/atocore/memory/service.py
View File

@@ -344,6 +344,8 @@ def get_memories_for_context(
memory_types: list[str] | None = None,
project: str | None = None,
budget: int = 500,
header: str = "--- AtoCore Memory ---",
footer: str = "--- End Memory ---",
) -> tuple[str, int]:
"""Get formatted memories for context injection.
@@ -351,15 +353,16 @@ def get_memories_for_context(
Budget allocation per Master Plan section 9:
identity: 5%, preference: 5%, rest from retrieval budget
The caller can override ``header`` / ``footer`` to distinguish
multiple memory blocks in the same pack (e.g. identity/preference
vs project/knowledge memories).
"""
if memory_types is None:
memory_types = ["identity", "preference"]
if budget <= 0:
return "", 0
header = "--- AtoCore Memory ---"
footer = "--- End Memory ---"
wrapper_chars = len(header) + len(footer) + 2
if budget <= wrapper_chars:
return "", 0

57
tests/test_context_builder.py
View File

@@ -251,3 +251,60 @@ def test_unknown_hint_falls_back_to_raw_lookup(tmp_data_dir, sample_markdown, mo
pack = build_context("status?", project_hint="orphan-project", budget=2000)
assert "Solo run" in pack.formatted_context
def test_project_memories_included_in_pack(tmp_data_dir, sample_markdown):
"""Active project-scoped memories for the target project should
land in a dedicated '--- Project Memories ---' band so the
Phase 9 reflection loop has a retrieval outlet."""
from atocore.memory.service import create_memory
init_db()
init_project_state_schema()
ingest_file(sample_markdown)
mem = create_memory(
memory_type="project",
content="the mirror architecture is Option B conical back for p04-gigabit",
project="p04-gigabit",
confidence=0.9,
)
# A sibling memory for a different project must NOT leak into the pack.
create_memory(
memory_type="project",
content="polisher suite splits into sim, post, control, contracts",
project="p06-polisher",
confidence=0.9,
)
pack = build_context(
"remind me about the mirror architecture",
project_hint="p04-gigabit",
budget=3000,
)
assert "--- Project Memories ---" in pack.formatted_context
assert "Option B conical back" in pack.formatted_context
assert "polisher suite splits" not in pack.formatted_context
assert pack.project_memory_chars > 0
assert mem.project == "p04-gigabit"
def test_project_memories_absent_without_project_hint(tmp_data_dir, sample_markdown):
"""Without a project hint, project memories stay out of the pack —
cross-project bleed would rot the signal."""
from atocore.memory.service import create_memory
init_db()
init_project_state_schema()
ingest_file(sample_markdown)
create_memory(
memory_type="project",
content="scoped project knowledge that should not leak globally",
project="p04-gigabit",
confidence=0.9,
)
pack = build_context("tell me something", budget=3000)
assert "--- Project Memories ---" not in pack.formatted_context
assert pack.project_memory_chars == 0