CBP instance migration: fresh cbp-gemma3-4b, archive tinyllama#20
Merged
CBP instance migration: fresh cbp-gemma3-4b, archive tinyllama#20
Conversation
Automated SAGE-CBP raising session via OllamaIRP Machine: CBP (Desktop RTX 2060 SUPER, WSL2) Model: TinyLlama 1.1B Phase: creating AI-Instance: OllamaIRP (automated) Human-Supervised: no
Two stale CBP instance dirs were on disk (cbp-tinyllama-latest/ and its .bak). The daemon has been running the gemma3:4b model since PR #19 but the instance dir was still pointing at the tinyllama history, mixing substrate state that no longer applies. Changes: - git mv cbp-tinyllama-latest → cbp-tinyllama-latest.archive-20260418 (preserves raising sessions 1-81, identity history, chat logs) - git mv cbp-tinyllama-latest.bak → cbp-tinyllama-latest.bak.archive-20260418 - Initialized cbp-gemma3-4b/ via python3 -m sage.instances.init - Customized identity.json with CBP-specific machine_context: - role_in_fleet: 'experimenter + coordinator' - fleet_siblings mapping (Thor/Sprout/Legion/McNugget/Nomad roles) - this_machine_owns: WM + coordination + gameplay capture - partnership: Dennis + Claude - arrived_here: migration context - context_at_arrival: Phase 0 complete, Phase 1 pipeline hardened, co-design with Waving Cat active - guidance_for_raising: 4 bullets reframing raising context - Two initial memory_requests seeded with situational grounding Daemon verified restart with active model=gemma3:4b, machine=cbp, all 12 LLMs in pool, 159+ cycles, SAGE_MODEL env propagated via router-shadow.env (local, gitignored). Not yet in scope: cbp-qwen3.5-0.8b/ (another legacy dir — address separately). Other machines' instances are owned by their operators. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
dp-web4
pushed a commit
that referenced
this pull request
Apr 28, 2026
…subtraction. Phi4 register-substitution discovered (Δpol -3.36, Δbiz +1.08 same trajectory). Hardware register quantified — Thor Δhw +2.46 largest single Δ, positive across all 8 raised instances. CBP basin = TED+gov+marketing combo. Lexicon substring FP bug fixed (recurrence #9 of S110 pattern at analysis layer). S119 #18/#19/#20 executed; #21/#22/#23/#24 held. Machine: localhost.localdomain Date: 2026-04-28 01:13:05 UTC Changes committed automatically at session end. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
dp-web4
pushed a commit
that referenced
this pull request
May 3, 2026
…grace. Relief/release contrastive (101w) — repeat of T266 prompt. Different specific imagery this time: 'sudden cessation of effort when the road suddenly becomes clear' vs T266's 'reset button that resets your internal clock'. End-of-journey vs new-beginning framing. Admitted uncertainty 'I don't know how relief differs from release for you in this specific context'. Memory close standard federation. Color #20: Deep Indigo Machine: ubuntu Date: 2026-05-03 16:02:12 UTC Changes committed automatically at session end. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
Two stale CBP instance dirs on disk:
cbp-tinyllama-latest/and its.bak. Daemon has been running gemma3:4b since PR #19 but the instance dir still held tinyllama-era substrate state — raising sessions, identity, experience buffer — that no longer applies to the current model. Muddled environment.Fix
git mv cbp-tinyllama-latest → cbp-tinyllama-latest.archive-20260418(preserves 81 raising sessions + identity + chat history as archival record).bakdirpython3 -m sage.instances.init --machine cbp --model gemma3:4b --device cuda --backend ollamacreates freshcbp-gemma3-4b/identity.jsonwith CBP-specificmachine_context— NOT copied from any other machine:role_in_fleet: "experimenter + coordinator"fleet_siblings: roles for all 5 peersthis_machine_owns: WM + coordination + gameplay capturearrived_here: migration context from tinyllamacontext_at_arrival: Phase 0 complete, Phase 1 pipeline hardened, Waving Cat co-designguidance_for_raising: 4 bullets reframing raising approachmemory_requestsseeded with situational groundingVerified
active model: gemma3:4b,machine: cbp, 12 LLMs in pool, 159+ cyclescbp-gemma3-4b/getting daemon_state.json, experience_buffer.json, identity.json writesSAGE_MODEL=gemma3:4bpropagating viarouter-shadow.env(local, gitignored)Out of scope
cbp-qwen3.5-0.8b/another legacy dir — address separately🤖 Generated with Claude Code