Commit graph

13 commits

Author SHA1 Message Date
Natalie
57c3b76ef5 docs(prospector): add training-loop (CoT-labeled corpus -> LoRA -> eval gate)
Some checks are pending
CI / verify (push) Waiting to run
Thesis: enrich 10K+ history into per-turn {read, move, outcome, source}
records before training. Map the two producers (matcher=classify+retrieve,
agent=generate) to data routing; distill agent wins into the matcher
library as the cost/quality shortcut. LoRA per role on a transient
training droplet; multi-LoRA serving on the single inference droplet;
eval-gated build flip. Classifier first, generator second, orchestrator
never trained.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-29 18:00:01 -04:00
Natalie
2af7c6bda7 docs(prospector): split AI roles into orchestrator vs pipeline
Distinguish three AI roles across two tiers: the orchestrator/chat agent
(Tier A, control-surface CLIENT, user-facing, presence-warmed) vs the
classifier + message-generator (Tier B, pipeline components the app CALLS,
queue-warmed). Plane-3 autonomy agent = same orchestrator, event-driven
entry point. Fix warm-up triggers to be role-specific.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-29 16:20:21 -04:00
Natalie
bc47a2a72d docs(prospector): add GPU cost-control feature (warm-up, meter, pause)
Presence-driven auto-warm (confirm toast), live uptime cost meter,
pause=teardown to stop billing, GPU policy moved to settings config.
Corrects the cost model: DO bills for droplet existence, not inference.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-29 16:18:08 -04:00
Natalie
50d5527345 docs(prospector): add v4 AI-first control-surface build plan
Three control planes (operation/observation/autonomy) + governance, OSS
model end to end. Sequences parity+observability -> governance -> autonomy.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-29 16:10:25 -04:00
Natalie
3fafb943bb feat(ui+ mcp+docs): complete UI fusion (Triage sidebar+toolbar+bi matching designs/main+reports 4 fused with bi+Queue tabs+sim+log+Pastebin sync+Control PWA install); extend MCP with draft/send/thread/list/pastebin/reports/mr/markets for full legacy cockpit parity; update deploy.md with migration 0006 + notes. Per MIGRATION-PLAN Phases 1+3+5. Builds/tsc green. 2026-06-29 09:31:13 -04:00
Natalie
845f437cb5 docs: README + package.json reflect the implemented web/ operator PWA
The full coworker-replacement app is built in web/ (served by this repo's
NestJS backend), not the platform my/ surface. Document the six views and the
/prospector/* endpoints each uses, the shared-audit/human_owned/Life-opt-in
guarantees, and dev/build commands. Keep the platform my/ SSO vision as-is.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-29 07:58:45 -04:00
Natalie
d22b27b883 docs(deploy): DB step now via Terraform (uvlava/terraform/do) apply + outputs
Replace manual doctl DB creation with the declarative IaC path: terraform apply
creates people+prospector DBs+users on the managed cluster; pull DB passwords +
host from terraform output into the service .envs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:54:49 -04:00
Natalie
8bd6670878 docs(deploy): correct DB topology — DO Managed Postgres, not local
Probe found no local PG: droplet pgbouncer fronts a DO Managed cluster
(private-lilith-store-pg, holds live quinn). people+prospector are new DBs on
that cluster (additive); services connect direct to :25060 over SSL. Node 20
already installed on lime.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:34:02 -04:00
Natalie
6ca7a32964 feat(prospector): enhance backend+MCP per MISSING_REQUIREMENTS.md (P0 gaps: real raw classify, booking triad+takeover verdict, composition+confidence, send safety floors incl vendor/human/known, structured returns; add /prospector/classify + mcp tool; richer inbound+runner+gate+people signals; update docs). Builds/tests green. Per PLAN.md + docs/features/mcp/MISSING_REQUIREMENTS.md. 2026-06-29 07:30:08 -04:00
Natalie
100ffc60c1 docs(deploy): prod runbook for the DO droplet (lime/lilith-store-backend)
Grounded in a read-only probe: Ubuntu 24.04, Node 18 (needs 20 for NestJS 11),
PG16+pgbouncer, mac-sync co-tenant, mesh 10.9.0.5. Steps: node20, create people+
prospector DBs (additive), migrations, ship dist + npm ci, env, systemd units,
mac-sync inbound webhook, point dev UI at prod over the mesh (10.9.0.5:3210).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:28:49 -04:00
Natalie
631e131327 docs: correct deploy target (black dead -> DO droplet) + on-demand GPU lifecycle
black homelan is gone; prod target is the DO backend droplet (lilith-store-backend,
209.38.51.98 / wg 10.9.0.5) where mac-sync-server already runs. Fix black:2546x
DB-host refs in comments/migrations. GPU is on-demand + queue-driven: hold warm
while backlog is deep, release on idle grace (not strictly per-tick).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:22:29 -04:00
Natalie
16732f9693 docs(draft-engine): OSS-on-GPU + CoT workflow builder; rename MVP engine 'template'
Document the draft engine direction: OSS uncensored models on DO GPU droplets
(reuse LPv2 provisioning, no model-boss), engine id 'do-gpu-<model>_<build>', and
pastebin → CoT workflow builder (versioned reasoning chains the model runs;
pastebin canon as injected context; corrections as per-build tuning data). Rename
the MVP static-render engine value 'pastebin' -> 'template' (pastebin is now
context, not the engine).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 07:14:29 -04:00
Natalie
92c98b9ade refactor: restructure to src/ app + @packages/mcp-prospector; off-Claude default; MCP
Restructure to match the @mac-sync sister-app convention + operator direction:
- Backend service -> repo root (root package = the app); engine is CORE source,
  now src/engine/ (not a separate package); imports rewritten to relative.
- MCP server -> @packages/mcp-prospector/ (agent interface; thin REST wrapper so
  the coworker can trial this backend and fall back to legacy quinn-prospector).
- web/ stays a top-level surface.
- draft_engine default 'claude:sonnet' -> 'pastebin': the whole point is to run
  OFF hosted Claude (which refuses adult-services copy) on OSS-uncensored LLMs on
  raw GPU droplets; generative target is 'gpu:<model>'. Reuse LPv2's existing DO
  GPU provisioning, not model-boss.
- docs/features/mcp.md: how the MCP works + the coworker graceful-switch protocol.
- .gitignore: ignore Swift .build/.

Verified: tsc clean, 101 tests (92 engine + 9 runner), app boots from root,
mcp-prospector builds + boots, smoke tests green (scam held, settings=pastebin).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 06:39:13 -04:00