Sam & Claude b096168aee docs(wiki): model selection + evaluation harness design ... New wiki page: model-selection-and-eval.md (445 lines) Completes the T2.x trifecta design: - Evaluation harness: 3 modes (self-report, local LLM, cloud LLM) - Model selection: weighted scoring (success rate, cost, capability, latency) - Integration with hive-routing: data flow + implementation phases - 4 implementation phases, ~10 days total, ~570 lines Indexed in both en/index.md and sl/index.md. Follows PR #241 (conflict marker fix) and the now-merged screenshot pipeline. The eval harness provides the feedback loop that makes model-selection decisions data-driven rather than heuristic. Sam & Claude		2026-06-27 22:18:18 +02:00
..
sl	docs(wiki): model selection + evaluation harness design	2026-06-27 22:18:18 +02:00
a2a-complexity-audit.md	style: restore main green — fmt + prettier drift (Sam & Claude)	2026-06-27 17:19:57 +02:00
agent-events-reference.md	docs: move reference docs into wiki (agent-events, headroom, layered-soul)	2026-06-24 17:32:13 +02:00
agent-harness.md	fix(wiki): agent harness title — pi, zot & Colibri (not just zot + Colibri)	2026-06-26 14:15:47 +02:00
contracts.md	fix: Layer 1 — contracts, MCP naming, lock contention	2026-06-27 13:48:21 +02:00
cost-dashboard.md	docs: replace stale tmux-screenshot refs in cost-dashboard.md	2026-06-27 21:22:47 +02:00
cost-model.md	docs(wiki): add per-task cost tracking section to cost-model (EN+SL)	2026-06-27 12:17:24 +02:00
daemon-not-demon.md	docs: rename PLAN/PROPOSAL/HANDOFF/ENHANCEMENT → implementation names	2026-06-26 17:32:39 +02:00
deployment.md	docs: rename PLAN/PROPOSAL/HANDOFF/ENHANCEMENT → implementation names	2026-06-26 17:32:39 +02:00
external-mcp.md	docs: rename PLAN/PROPOSAL/HANDOFF/ENHANCEMENT → implementation names	2026-06-26 17:32:39 +02:00
glasspane.md	refactor: kill→stop across API surface, CLI, TUI, and docs	2026-06-26 14:40:10 +02:00
headroom-sidecar.md	docs: move reference docs into wiki (agent-events, headroom, layered-soul)	2026-06-24 17:32:13 +02:00
hive-pane.md	style: restore main green — fmt + prettier drift (Sam & Claude)	2026-06-27 17:19:57 +02:00
hive-routing.md	style: restore main green — fmt + prettier drift (Sam & Claude)	2026-06-27 17:19:57 +02:00
index.md	docs(wiki): model selection + evaluation harness design	2026-06-27 22:18:18 +02:00
jail-confinement.md	docs(wiki): cross-link cost-model → task-board	2026-06-24 13:47:14 +02:00
layered-soul.md	fix(skills): correct source-of-truth — colibri, not clawdie-ai	2026-06-26 21:43:08 +02:00
model-selection-and-eval.md	docs(wiki): model selection + evaluation harness design	2026-06-27 22:18:18 +02:00
mother-hive.md	fix(mother): report-task-cost resolves hostname→node_id + wiki	2026-06-27 14:08:11 +02:00
naming-decisions.md	docs(guide): port 39 procedural docs from clawdie-ai to colibri	2026-06-26 09:16:43 +02:00
operator-attention.md	docs(wiki): polish terminal + operator-attention pages	2026-06-25 23:40:23 +02:00
operator-cli.md	refactor: kill→stop across API surface, CLI, TUI, and docs	2026-06-26 14:40:10 +02:00
quality-gates.md	feat(hooks): install-hooks.sh — one-command hook activation	2026-06-24 14:09:59 +02:00
runtime-inventory.md	docs(wiki): add 9 subsystem pages (rebuilt on current main)	2026-06-24 16:48:49 +02:00
skills-catalog.md	fix(skills): correct source-of-truth — colibri, not clawdie-ai	2026-06-26 21:43:08 +02:00
store-schema.md	docs(wiki): add 9 subsystem pages (rebuilt on current main)	2026-06-24 16:48:49 +02:00
task-board.md	feat(wiki): expand to full coverage — cost-model, glasspane, task-board, jail-confinement	2026-06-24 13:37:31 +02:00
terminal.md	docs(wiki): polish terminal + operator-attention pages	2026-06-25 23:40:23 +02:00
tui.md	style: restore main green — fmt + prettier drift (Sam & Claude)	2026-06-27 17:19:57 +02:00
vault-provision.md	docs(wiki): add 9 subsystem pages (rebuilt on current main)	2026-06-24 16:48:49 +02:00