conductor/rune
1
2 Fork 1
Code Issues 38 Pull Requests 28 Actions 26 Packages Projects Releases 564 Wiki Activity

[P2-03] Compile personality corpus into a bounded persistent self-model #37

New Issue
Closed
opened 2026-08-28 20:54:45 +01:00 by conductor · 3 comments
conductor commented 2026-08-28 20:54:45 +01:00
Owner
Copy link
Copy source

Plain summary

The personality corpus is compiled into a compact persistent self-model with a hard token budget, so Rune doesn't reread every source influence each turn — while the full evidence stays retrievable for 'why' questions, contradictions, and growth.

Example

Normal personality payload fits a fixed budget; removing the source corpus from the active prompt does not erase Rune's character.

Technical details

Parent epic: #16

Manifest ID: P2-03

Priority: P2
Goal: retain all source influences without rereading them every turn.

Architecture:

large evidence corpus
→ synthesis
→ compact current self
→ normal expression

Source evidence remains retrievable for “why” questions, contradiction handling and growth.

Acceptance criteria:

  • normal personality payload has a hard token budget;
  • removing source corpus from active prompt does not erase stable character;
  • trait changes are slow/evidence-backed.

Dependencies: P0-03, P2-02.

Resolved dependency references

  • Depends on: #19 (P0-03), #36 (P2-02)
  • Blocks: None.

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 The personality corpus is compiled into a compact persistent self-model with a hard token budget, so Rune doesn't reread every source influence each turn — while the full evidence stays retrievable for 'why' questions, contradictions, and growth. ## Example Normal personality payload fits a fixed budget; removing the source corpus from the active prompt does not erase Rune's character. ## Technical details Parent epic: #16 Manifest ID: **P2-03** **Priority:** P2 **Goal:** retain all source influences without rereading them every turn. **Architecture:** ```text large evidence corpus → synthesis → compact current self → normal expression ``` Source evidence remains retrievable for “why” questions, contradiction handling and growth. **Acceptance criteria:** - normal personality payload has a hard token budget; - removing source corpus from active prompt does not erase stable character; - trait changes are slow/evidence-backed. **Dependencies:** P0-03, P2-02. --- ## Resolved dependency references - Depends on: #19 (P0-03), #36 (P2-02) - Blocks: None. ## 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 20:54:45 +01:00
gitea-actions Bot added the featuregrowthidentity labels 2026-08-28 20:55:44 +01:00
gitea-actions Bot added the bugcustodian labels 2026-09-03 22:54:21 +01:00
conductor commented 2026-09-05 19:22:25 +01:00
Author
Owner
Copy link
Copy source

Handoff addendum (RUNE_VIBE_CODE_INTEGRITY_HANDOFF §5.3) — anti-ossification safeguards

Extend this issue: the self-model must distinguish conceptually where useful — observed tendency / chosen value / stable preference / temporary state / uncertain hypothesis / user-established boundary / counterevidence.

Feedback-loop guard (mandatory): self-generated behaviour influenced by the current self-model must NOT be treated as independent confirming evidence without discounting/qualification. Otherwise: model says "I am X" → X injected → behaves X → "X" confirmed by own behaviour → ossified.

## Handoff addendum (RUNE_VIBE_CODE_INTEGRITY_HANDOFF §5.3) — anti-ossification safeguards Extend this issue: the self-model must distinguish conceptually where useful — observed tendency / chosen value / stable preference / temporary state / uncertain hypothesis / user-established boundary / counterevidence. **Feedback-loop guard (mandatory):** self-generated behaviour influenced by the current self-model must NOT be treated as independent confirming evidence without discounting/qualification. Otherwise: model says "I am X" → X injected → behaves X → "X" confirmed by own behaviour → ossified.
conductor commented 2026-09-05 19:42:15 +01:00
Author
Owner
Copy link
Copy source

Second addendum (EXTERNAL_PROJECT_LESSONS_HANDOFF — Amendment #37) — destructive-write guard

Prior addendum stands (attribution taxonomy, feedback-loop guard). Net-new:

  • Destructive-write guard: large shrinkage or replacement of the current self-model must be conspicuous, attributable, versioned/recoverable, and linked to the evidence/outcome that justified it. A stronger promotion path applies to shrinkage than to growth.
  • This pairs with the new high-value cognitive-state mutation-guards issue (handoff §4) — self-model is the first protected state class.
## Second addendum (EXTERNAL_PROJECT_LESSONS_HANDOFF — Amendment #37) — destructive-write guard Prior addendum stands (attribution taxonomy, feedback-loop guard). **Net-new:** - **Destructive-write guard**: large shrinkage or replacement of the current self-model must be conspicuous, attributable, versioned/recoverable, and linked to the evidence/outcome that justified it. A stronger promotion path applies to shrinkage than to growth. - This pairs with the new high-value cognitive-state mutation-guards issue (handoff §4) — self-model is the first protected state class.
conductor removed the bug label 2026-09-11 22:46:22 +01:00
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 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#37