conductor/rune
1
2 Fork 1
Code Issues 36 Pull Requests 30 Actions 69 Packages Projects Releases 564 Wiki Activity

[P2-04] Formalize memory types and retrieval intent #38

New Issue
Closed
opened 2026-08-28 20:54:46 +01:00 by conductor · 3 comments
conductor commented 2026-08-28 20:54:46 +01:00
Owner
Copy link
Copy source

Plain summary

Persistent material stops being one generic blob: formal typed access for raw evidence, episodic memory, semantic knowledge, procedural skills, self/personality knowledge, and learning evidence — each with its own budget.

Example

A recall request targets the right store by type, and ContextBroker allocates separate budgets per memory class.

Technical details

Parent epic: #16

Manifest ID: P2-04

Priority: P2
Goal: stop treating all persistent material as one generic context source.

Define typed access for:

  • raw evidence/history;
  • episodic memory;
  • semantic knowledge;
  • procedural memory/skills;
  • self/personality knowledge;
  • learning evidence.

Acceptance criteria:

  • recall request targets appropriate store/type;
  • ContextBroker can allocate separate budgets;
  • irrelevant memory classes remain dormant.

Dependencies: P1-03.

Resolved dependency references

  • Depends on: #26 (P1-03)
  • Blocks: #39 (P2-05), #40 (P2-06), #42 (P2-08), #47 (P3-04)

Relevant source files

Not specified in the handoff. P0-01 must identify authoritative paths before implementation; do not guess by adding another path.

Do not do

  • Do not begin this issue before its dependencies are complete.
  • Do not create a parallel authority path; replace, extend, or remain dormant.
  • Do not add unrelated cognitive subsystems or additive feature growth.
  • Do not treat module/schema existence, background activity, or model self-report as acceptance evidence.

Source directive

Preserved from /home/nick/Desktop/rune_v1_course_correction_handoff.md, Section 14. The handoff is authoritative if this issue summary is ambiguous.

Pipeline requirements

  • TDD: frozen/regression tests written first, red → green
  • ruff check and ruff format --check clean
  • Spec-compliance review gate: PASS
  • Code-quality review gate: Approved
  • Full orchestration suite regression green
  • Canary passes (where applicable)
  • Closed with a properly formatted closing comment + commit/PR references
## Plain summary Persistent material stops being one generic blob: formal typed access for raw evidence, episodic memory, semantic knowledge, procedural skills, self/personality knowledge, and learning evidence — each with its own budget. ## Example A recall request targets the right store by type, and ContextBroker allocates separate budgets per memory class. ## Technical details Parent epic: #16 Manifest ID: **P2-04** **Priority:** P2 **Goal:** stop treating all persistent material as one generic context source. Define typed access for: - raw evidence/history; - episodic memory; - semantic knowledge; - procedural memory/skills; - self/personality knowledge; - learning evidence. **Acceptance criteria:** - recall request targets appropriate store/type; - ContextBroker can allocate separate budgets; - irrelevant memory classes remain dormant. **Dependencies:** P1-03. --- ## Resolved dependency references - Depends on: #26 (P1-03) - Blocks: #39 (P2-05), #40 (P2-06), #42 (P2-08), #47 (P3-04) ## Relevant source files Not specified in the handoff. P0-01 must identify authoritative paths before implementation; do not guess by adding another path. ## Do not do - Do not begin this issue before its dependencies are complete. - Do not create a parallel authority path; replace, extend, or remain dormant. - Do not add unrelated cognitive subsystems or additive feature growth. - Do not treat module/schema existence, background activity, or model self-report as acceptance evidence. ## Source directive Preserved from `/home/nick/Desktop/rune_v1_course_correction_handoff.md`, Section 14. The handoff is authoritative if this issue summary is ambiguous. ## Pipeline requirements - [ ] TDD: frozen/regression tests written first, red → green - [ ] `ruff check` and `ruff format --check` clean - [ ] Spec-compliance review gate: PASS - [ ] Code-quality review gate: Approved - [ ] Full orchestration suite regression green - [ ] Canary passes (where applicable) - [ ] Closed with a properly formatted closing comment + commit/PR references
conductor added the P2 — mediumv1-course-correction labels 2026-08-28 20:54:46 +01:00
gitea-actions Bot added the featuregrowthidentitymemory labels 2026-08-28 20:55:46 +01:00
gitea-actions Bot added the custodian label 2026-09-03 22:54:24 +01:00
conductor commented 2026-09-05 19:22:31 +01:00
Author
Owner
Copy link
Copy source

Handoff addendum (RUNE_VIBE_CODE_INTEGRITY_HANDOFF §5.4) — memory type vs retrieval intent

Extend this issue: preserve distinct semantics for raw evidence-history / episodic / semantic knowledge / procedural skills / self-personality knowledge. Learning evidence is a cross-cutting provenance substrate attached to persistent objects — not a memory class.

Separate memory type (what kind of remembering) from retrieval intent ("why do I believe/do this?"). A request first determines the kind of remembering, then which memory classes/stores are eligible. One physical database per cognitive type is NOT required — semantic authority outranks storage topology.

## Handoff addendum (RUNE_VIBE_CODE_INTEGRITY_HANDOFF §5.4) — memory type vs retrieval intent Extend this issue: preserve distinct semantics for raw evidence-history / episodic / semantic knowledge / procedural skills / self-personality knowledge. Learning **evidence** is a cross-cutting provenance substrate attached to persistent objects — not a memory class. Separate **memory type** (what kind of remembering) from **retrieval intent** ("why do I believe/do this?"). A request first determines the kind of remembering, then which memory classes/stores are eligible. One physical database per cognitive type is NOT required — semantic authority outranks storage topology.
conductor commented 2026-09-05 19:42:15 +01:00
Author
Owner
Copy link
Copy source

Second addendum (EXTERNAL_PROJECT_LESSONS_HANDOFF — Amendment #38) — deterministic-prior flow + structural semantics

Prior addendum stands (type vs intent, no per-type databases). Net-new:

  • Preferred flow: deterministic classification prior → typed retrieval authority → task/context/evidence may override. Deterministic classification (regex/rules) is a cheap ROUTING PRIOR — never authoritative truth (Mnemosyne lesson, borrowed carefully).
  • Structural memory semantics to preserve: raw evidence/history, episodic, semantic knowledge, procedural skills, self/personality knowledge. Learning evidence stays cross-cutting provenance.
  • Still NOT required: one database per type, a second memory stack, or a fixed topical taxonomy (topical organisation is #45-adjacent / adaptive-concepts territory).
## Second addendum (EXTERNAL_PROJECT_LESSONS_HANDOFF — Amendment #38) — deterministic-prior flow + structural semantics Prior addendum stands (type vs intent, no per-type databases). **Net-new:** - **Preferred flow**: deterministic classification prior → typed retrieval authority → task/context/evidence may override. Deterministic classification (regex/rules) is a cheap ROUTING PRIOR — never authoritative truth (Mnemosyne lesson, borrowed carefully). - Structural memory semantics to preserve: raw evidence/history, episodic, semantic knowledge, procedural skills, self/personality knowledge. Learning evidence stays cross-cutting provenance. - Still NOT required: one database per type, a second memory stack, or a fixed topical taxonomy (topical organisation is #45-adjacent / adaptive-concepts territory).
conductor commented 2026-10-08 13:14:55 +01:00
Author
Owner
Copy link
Copy source

CLOSED PROGRAMMATICALLY — commit fa648aa (contract BUILDER-2026-10-08T12:09:33Z-9404ac). See tests/test_p2_quintet.py (16/16 green).

CLOSED PROGRAMMATICALLY — commit fa648aa (contract BUILDER-2026-10-08T12:09:33Z-9404ac). See tests/test_p2_quintet.py (16/16 green).
Sign in to join this conversation.
No Branch/Tag Specified
Labels
Clear labels
P0 — critical
Spine/core correctness or blocks other work — do first
 P1 — high
Material user value or real defect (money, bugs, next-stage dep)
 P2 — medium
Quality/consolidation improvement
 P3 — low
Measurement / benchmark / deferred policy
 blocked
Dependencies open
 bug
Confirmed defect or regression
 custodian
epic
Rune v1 course-correction issue graph
 feature
New capability or improvement
 governance
growth
identity
in-progress
Currently being worked on by Rune
 incomplete
Incomplete work — draft PR with ledger, awaiting resume
 infrastructure
life
memory
memory-atlas
Memory Research Atlas child domain
 needs-testing
Needs manual testing with dumbed-down steps before close
 perception
ready
Order satisfied - Rune may start
 release-drift
research
Research jobs — spikes, watchlists, evidence work
 rune
rune
 scaffolding
scaffolding
 spine,correction
spine,correction
 spine,deferred
spine,deferred
 spine,resolved
spine,resolved
 strangler,burn,endgame,deferred
strangler,burn,endgame,deferred
 strangler,burn,endgame,inventory,epic
strangler,burn,endgame,inventory,epic
 tui
tui
 tui,epic
tui,epic
 tui,openspec
tui,openspec
 v1-course-correction
Rune v1 course-correction issue graph
No labels P2 — medium custodian feature growth identity memory v1-course-correction
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
conductor
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: conductor/rune#38