omnilane 0.31.0 → 0.32.0

package/routing.local.yaml.example

@@ -8,7 +8,7 @@
 # consult is a multi-vendor direct-target chain. configure.sh intentionally
 # skips it because that menu writes one candidate per lane. If overriding it,
 # retain every vendor you want to address by name:
-# consult: codex gpt-5.6-sol max | claude claude-opus-5 high | grok grok-4.5 - | gemini "Gemini 3.1 Pro (High)" -
+# consult: codex gpt-5.6-sol max | claude claude-fable-5-1 high | grok grok-4.6 - | gemini "Gemini 3.7 Flash (High)" -
 
 # ── Starter profiles ─────────────────────────────────────────────
 # Uncomment ONE block that matches what you actually subscribe to.
@@ -26,10 +26,10 @@
 # live-search:     off - -
 # coding-overflow: off - -
 
-# Profile: Claude Code (Fable 5) as the main loop — let Fable keep judgment/taste,
+# Profile: Claude Code (Fable 5.1) as the main loop — let Fable keep judgment/taste,
 # push only coding volume out to Codex.
-# hard-judgment:   claude claude-fable-5 high
-# taste-final:     claude claude-fable-5 high
+# hard-judgment:   claude claude-fable-5-1 high
+# taste-final:     claude claude-fable-5-1 high
 
 # Profile: Codex-heavy (Sol main) — keep the hard lanes on Codex, Claude for taste.
 # taste-final:     claude claude-opus-5 high

package/routing.yaml

@@ -8,39 +8,37 @@
 #   same table degrades gracefully when you only subscribe to one or two vendors.
 # Override any line in ~/.omnilane/routing.local.yaml (same format; local wins).
 # Every benchmark score, price and throughput figure behind these orderings lives in
-# docs/model-capabilities-2026-07.md, with the date it was retrieved. The comments below
+# docs/model-capabilities-2026-09.md, with the date it was retrieved. The comments below
 # deliberately carry no numbers: they state WHY a lane is ordered the way it is, which
 # stays true for months, while the numbers move every few weeks. Change an ordering and
 # you update the doc; a figure going stale should never need a routing-table edit.
-# (Audited 2026-07-12; re-audited 2026-07-25, 2026-08-02 and 2026-08-03.)
-# defaults follow Artificial Analysis data, 2026-07
+# (Audited 2026-07-12; re-audited 2026-07-25, 2026-08-02, 2026-08-03, and 2026-09-02.)
+# defaults follow Artificial Analysis data, 2026-09
 # snapshot. Verified against AA site records + vendor pricing pages: Intelligence &
 # Coding indexes and 7:2:1 blended prices all match (AA field price1mBlended7To2To1);
 # coding cost-per-task is chart-only (not independently reconstructed). Prices are
 # standard short-context API tier — on subscription CLIs treat $ as relative ranking.
 # Your own job outcomes (~/.omnilane/jobs/) outrank these priors; edit lanes to match.
 
-hardest-coding:  codex gpt-5.6-sol xhigh | claude claude-opus-5 xhigh  # ordered on coding capability specifically, not general intelligence. Sol dropped from max to xhigh on 2026-08-03: on AA's per-effort Coding Index, Sol at xhigh outscores both Sol at max and every Claude tier, at a third less cost — max buys overthinking here, not accuracy. xhigh is also Anthropic's documented starting point for coding/agentic work. Keep Sol first for the established Codex harness lane.
-bulk-mechanical: codex gpt-5.6-terra max | claude claude-sonnet-5 high | gemini "Gemini 3.6 Flash (High)" -  # ordered on endurance per dollar: Terra leads Sonnet 5 on both intelligence and cost per task
-triage:          codex gpt-5.6-luna medium | gemini "Gemini 3.6 Flash (Low)" - | claude claude-haiku-4-5 -  # high-volume scans, ordered on cost per task: Luna is the cheapest model at its intelligence tier by a wide margin
-hard-judgment:   claude claude-opus-5 xhigh | codex gpt-5.6-sol max   # ordered on agentic knowledge work, where Opus 5 leads Sol on AA's benchmarks. xhigh per Anthropic guidance (high is the documented floor for intelligence-sensitive work; max is for correctness-over-cost only) — raise to max locally via `omnilane configure set` if your workload needs it.
-taste-final:     claude claude-opus-5 high | codex gpt-5.6-sol max    # user-facing prose, prompt/doc polish, Chinese phrasing, style arbitration
-consult:         codex gpt-5.6-sol max | claude claude-opus-5 high | grok grok-4.5 - | gemini "Gemini 3.1 Pro (High)" -  # direct named-model consultation; use --vendor to prevent fallback
-ui-draft:        codex gpt-5.6-sol xhigh | claude claude-opus-5 high  # only with a design system / reference images; open-ended visual taste -> taste-final
-long-context:    gemini "Gemini 3.1 Pro (High)" - | codex gpt-5.6-sol high | claude claude-opus-5 high  # all have 1M context; ordered on AA-LCR, which scores exactly this lane's work — extracting and synthesising across long documents — and where Gemini leads both fallbacks. Corrected 2026-08-03: this comment used to send multi-hop synthesis to the Claude candidate on second-hand prior-generation figures, and current first-party per-effort data reverses that, so the two fallbacks swapped. Caveat in docs: AA-LCR runs at 10k-100k tokens, so nothing here settles behaviour at a full 1M
-fast-agentic:    codex gpt-5.6-luna max | gemini "Gemini 3.6 Flash (High)" -  # fast multi-step tool loops. Reordered 2026-08-03: Luna leads Flash on agentic benchmarks AND costs a fraction as much per task, so Flash's remaining edge is raw throughput alone. Keep Flash first only if your loops are latency-bound. Both take image input, so the lane's multimodal checks are unaffected
-live-search:     grok grok-4.5 - | off          # native X/web search lane; no real substitute
-coding-overflow: grok grok-4.5 - | kimi kimi-k3 - | qwen qwen3-coder-plus - | opencode - - | off  # codex-quota relief valve: mid-tier coding; Grok 4.5 is a capable mid-tier coder but AA measures a high hallucination rate — verify every factual claim it ships. qwen3-coder-plus = 2025-09-23 snapshot alias (Qwen 3.6 Plus exists; re-evaluate before swapping). kimi/qwen model fields are CLI aliases — adjust to your login. opencode "-" model = its own configured default.
-arbitrate:       off - -                        # opinion panel is OPT-IN: it costs one call per voter per round.
+hardest-coding: claude claude-fable-5-1 xhigh | codex gpt-5.6-sol xhigh # ordered on coding capability: the leading Claude tier wins both coding components; Sol remains the established Codex-harness value fallback
+bulk-mechanical: codex gpt-5.6-sol high | gemini "Gemini 3.7 Flash (High)" - | claude claude-sonnet-5 high # ordered on endurance per dollar: Sol dominates Terra within Codex; current Flash is the faster, cheaper middle fallback; Sonnet preserves subscription quota
+triage: codex gpt-5.6-luna high | gemini "Gemini 3.7 Flash (Low)" - | claude claude-haiku-4-5 - # ordered on cost per task at usable intelligence: Luna high buys a meaningful quality lift cheaply; Flash and Haiku are low-cost cross-vendor fallbacks
+hard-judgment: claude claude-fable-5-1 xhigh | codex gpt-5.6-sol max | grok grok-4.6 - # ordered on agentic knowledge work: Fable leads the Claude field; Sol stays ahead of Grok because Grok effort is ignored and its reproduced row is unknown
+taste-final: claude claude-fable-5-1 high | codex gpt-5.6-sol max # ordered on prose and polish: Fable leads Opus on intelligence and factual breadth; Sol is the cross-vendor fallback
+consult: codex gpt-5.6-sol max | claude claude-fable-5-1 high | grok grok-4.6 - | gemini "Gemini 3.7 Flash (High)" - # direct named-model chain uses the strongest current Claude and Flash slots; keep --vendor to prevent fallback
+ui-draft: codex gpt-5.6-sol xhigh | claude claude-fable-5-1 high # ordered for drafts with a design system or reference images: Sol leads measured multimodal and coding evidence; Fable follows for polish
+long-context: gemini "Gemini 3.7 Flash (Medium)" - | codex gpt-5.6-terra max | claude claude-opus-5 medium # ordered on long-context reasoning, then cost and throughput: Flash leads; Terra matches its long-context result; Opus is the cheaper Claude fallback
+fast-agentic: gemini "Gemini 3.7 Flash (Medium)" - | codex gpt-5.6-luna high # ordered on interactive tool-loop latency: Flash gives up little agentic quality for far faster first output; Luna high is the low-latency Codex fallback
+live-search: grok grok-4.6 - | off # native X and web search lane; no real substitute
+coding-overflow: grok grok-4.6 - | gemini "Gemini 3.7 Flash (High)" - | kimi kimi-k3 - | qwen qwen3-coder-plus - | opencode - - | off # coding relief ordered by capability and value: Grok has the lowest frontier hallucination rate; Flash is the cheapest strong coder here; revisit the best-value Qwen tier when its CLI alias can be verified
+arbitrate: off - - # opinion panel remains opt-in because each voter and round consumes quota
                                                 # Enable: `arbitrate: vote codex,claude,grok -` (any 1-4 of codex/claude/grok/gemini)
                                                 # Debate round (each voter rebuts the others): set the effort field to 2.
                                                 # Custom gate: `arbitrate: exec /path/to/script -`
-# Claude Fable 5 (claude-fable-5) is deliberately absent from the defaults: the top Claude tier
-# is usually the MAIN LOOP itself, not a dispatched worker, and it prices at twice Opus 5.
-# This is a cost / guardrail / main-loop policy choice, NOT a capability verdict — AA and
-# Epoch AI disagree on which of the two leads general intelligence and call it effectively a
-# tie, while Opus 5 leads clearly on agentic knowledge work at a lower cost per task. Fable 5
-# does keep the lead on factual breadth, so name it explicitly for recall-heavy consults. If you want
-# to route to it anyway, pick it in the configurator or set e.g.
-#   taste-final: claude claude-fable-5 high
-# in ~/.omnilane/routing.local.yaml.
+# Claude Fable 5.1 is in the judgment, taste, and hardest-coding defaults because
+# it leads Opus 5 on every Artificial Analysis axis at the same effort.
+# It is not in bulk or triage: it prices at twice Opus 5 per token and consumes
+# the most subscription quota per turn. Opus 5 remains the lower-hallucination,
+# lower-price Claude choice and can return to any lane via
+# ~/.omnilane/routing.local.yaml, for example:
+# hard-judgment: claude claude-opus-5 xhigh

package/scripts/configure.sh

@@ -151,10 +151,10 @@ esac
 # Dynamic/API catalogs stay curated — "c" always accepts an exact model ID.
 CODEX_MODELS=("gpt-5.6" "gpt-5.6-sol" "gpt-5.6-terra" "gpt-5.6-luna" "gpt-5.5" "gpt-5.4" "gpt-5.4-mini" "gpt-5.3-codex-spark")
 CODEX_EFFORTS=("xhigh" "max" "ultra" "high" "medium" "low" "minimal" "none")
-CLAUDE_MODELS=("default" "best" "fable" "opus" "sonnet" "haiku" "opus[1m]" "sonnet[1m]" "opusplan" "claude-fable-5" "claude-opus-5" "claude-sonnet-5" "claude-opus-4-8" "claude-opus-4-7" "claude-opus-4-6" "claude-opus-4-5-20251101" "claude-sonnet-4-6" "claude-sonnet-4-5-20250929" "claude-haiku-4-5" "claude-haiku-4-5-20251001")
+CLAUDE_MODELS=("default" "best" "fable" "opus" "sonnet" "haiku" "opus[1m]" "sonnet[1m]" "opusplan" "claude-fable-5" "claude-fable-5-1" "claude-opus-5" "claude-sonnet-5" "claude-opus-4-8" "claude-opus-4-7" "claude-opus-4-6" "claude-opus-4-5-20251101" "claude-sonnet-4-6" "claude-sonnet-4-5-20250929" "claude-haiku-4-5" "claude-haiku-4-5-20251001")
 CLAUDE_EFFORTS=("max" "xhigh" "high" "medium" "low" "-")
-GEMINI_MODELS=("gemini-3.6-flash-high" "gemini-3.6-flash-medium" "gemini-3.6-flash-low" "gemini-3.5-flash-high" "gemini-3.5-flash-medium" "gemini-3.5-flash-low" "gemini-3.1-pro-high" "gemini-3.1-pro-low" "claude-sonnet-4-6" "claude-opus-4-6-thinking" "gpt-oss-120b-medium")
-GROK_MODELS=("grok-4.5" "headroom-grok-build" "grok-4.3-official")
+GEMINI_MODELS=("gemini-3.7-flash-high" "gemini-3.7-flash-medium" "gemini-3.7-flash-low" "gemini-3.6-flash-high" "gemini-3.6-flash-medium" "gemini-3.6-flash-low" "gemini-3.1-pro-high" "gemini-3.1-pro-low" "claude-sonnet-4-6" "claude-opus-4-6-thinking" "gpt-oss-120b-medium")
+GROK_MODELS=("grok-4.6" "headroom-grok-build" "grok-4.3-official")
 KIMI_MODELS=("kimi-k3" "kimi-k2.7-code" "kimi-k2.5")
 QWEN_MODELS=("qwen3.7-max" "qwen3.7-plus" "qwen3.6-plus" "qwen3.5-plus" "qwen3-max-2026-01-23" "qwen3-coder-next" "qwen3-coder-plus" "qwen3-coder-flash")
 # OpenCode models use provider/model form; OpenRouter models use catalog slugs.

package/scripts/runners/run-vote.sh

@@ -31,9 +31,9 @@ trap cleanup_temp_files EXIT
 voter_spec() { # vendor -> "model<TAB>effort"
   case "$1" in
     codex)  printf 'gpt-5.6-sol\thigh' ;;
-    claude) printf 'claude-opus-5\thigh' ;;
-    gemini) printf 'Gemini 3.1 Pro (High)\t-' ;;
-    grok)   printf 'grok-4.5\t-' ;;
+    claude) printf 'claude-fable-5-1\thigh' ;;
+    gemini) printf 'Gemini 3.7 Flash (High)\t-' ;;
+    grok)   printf 'grok-4.6\t-' ;;
     *)      return 1 ;;
   esac
 }

package/skills/omnilane/SKILL.md

@@ -50,28 +50,26 @@ what dispatch picks when the first-choice vendor CLI is not installed.
 
 | Lane | First choice | Backup | When |
 |---|---|---|---|
-| hardest-coding | GPT-5.6 Sol (xhigh) | Claude Opus 5 (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
-| bulk-mechanical | GPT-5.6 Terra (max) | Claude Sonnet 5 (high) | Refactors, migrations, tests, review sweeps — mechanical endurance |
-| triage | GPT-5.6 Luna (medium) | Gemini 3.6 Flash (Low) | High-volume scans, first-pass filtering |
-| hard-judgment | Claude Opus 5 (xhigh) | GPT-5.6 Sol (max) | Architecture arbitration, deep reasoning, second opinions |
-| taste-final | Claude Opus 5 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, Chinese phrasing, style arbitration |
-| consult | Explicit named vendor/model | — (no fallback) | Direct natural-language consultation; always keep `--vendor` |
-| ui-draft | GPT-5.6 Sol (xhigh) | Claude Opus 5 (high) | UI drafts only WITH a design system / reference images; open-ended visual taste goes to taste-final |
-| long-context | Gemini 3.1 Pro (High) | GPT-5.6 Sol (high) | 1M-token synthesis; Pro is agentic-capable, while fast repeated loops prefer Flash on speed/cost |
-| fast-agentic | GPT-5.6 Luna (max) | Gemini 3.6 Flash (High) | Fast multi-step agentic loops, multimodal checks |
-| live-search | Grok 4.5 | — (off) | Realtime X/web search and social context |
-| coding-overflow | Grok 4.5 | Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex-quota relief valve for mid-tier coding; verify factual claims |
+| hardest-coding | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (xhigh) | Hardest implementation, deep root-cause debug, correctness-critical edits |
+| bulk-mechanical | GPT-5.6 Sol (high) | Gemini 3.7 Flash (High) → Claude Sonnet 5 (high) | Refactors, migrations, tests, review sweeps — mechanical endurance |
+| triage | GPT-5.6 Luna (high) | Gemini 3.7 Flash (Low) → Claude Haiku 4.5 | High-volume scans, first-pass filtering |
+| hard-judgment | Claude Fable 5.1 (xhigh) | GPT-5.6 Sol (max) → Grok 4.6 | Architecture arbitration, deep reasoning, second opinions |
+| taste-final | Claude Fable 5.1 (high) | GPT-5.6 Sol (max) | User-facing prose, prompt/doc polish, Chinese phrasing, style arbitration |
+| consult | GPT-5.6 Sol (max) | Claude Fable 5.1 (high) → Grok 4.6 → Gemini 3.7 Flash (High) | Direct named-model consultation; always keep `--vendor` |
+| ui-draft | GPT-5.6 Sol (xhigh) | Claude Fable 5.1 (high) | UI drafts only WITH a design system / reference images; open-ended visual taste goes to taste-final |
+| long-context | Gemini 3.7 Flash (Medium) | GPT-5.6 Terra (max) → Claude Opus 5 (medium) | Long-context synthesis ordered on AA-LCR, then cost and throughput |
+| fast-agentic | Gemini 3.7 Flash (Medium) | GPT-5.6 Luna (high) | Fast multi-step agentic loops, multimodal checks |
+| live-search | Grok 4.6 | — (off) | Realtime X/web search and social context |
+| coding-overflow | Grok 4.6 | Gemini 3.7 Flash (High) → Kimi K3 → Qwen3 Coder Plus → OpenCode | Codex-quota relief valve for mid-tier coding; verify factual claims |
 | arbitrate | off (opt-in vote panel) | — | Disabled by default. Enable with `arbitrate: vote codex,claude,grok -` in routing.local.yaml or via the configurator (any 1-4 voters). One quota hit PER VOTER PER ROUND; you chair: read the opinions and own the decision. Effort field 2 = debate round (voters rebut each other) |
 
-Claude Fable 5 (`claude-fable-5`) is absent from the defaults on purpose: the
-top Claude tier is usually the main loop itself, not a dispatched worker, and
-it prices at twice Opus 5. This is a cost / guardrail / main-loop policy choice,
-not a capability verdict — Artificial Analysis calls Opus 5 (61) and Fable 5 (60)
-"effectively tied" on the Intelligence Index, but Opus 5 leads AA-Briefcase by
-146 Elo at 20% lower cost per task. Fable 5 keeps the lead on factual breadth
-(AA-Omniscience), so name it explicitly for recall-heavy consults. To route to
-it anyway, select it in the configurator or override a lane in
-`~/.omnilane/routing.local.yaml` (e.g. `taste-final: claude claude-fable-5 high`).
+Claude Fable 5.1 (`claude-fable-5-1`) is in the judgment, taste, and
+hardest-coding defaults because it leads Opus 5 on every Artificial Analysis
+axis at the same effort. It is not in bulk or triage because it prices at twice
+Opus 5 per token and consumes the most subscription quota per turn. Opus 5
+remains the lower-hallucination, lower-price Claude choice and can return to any
+lane via `~/.omnilane/routing.local.yaml`, for example:
+`hard-judgment: claude claude-opus-5 xhigh`.
 
 ## Natural-language consultation
 
@@ -91,15 +89,15 @@ Users may speak normally; they do not need lane names.
 | Alias | Vendor | Model | Effort |
 |---|---|---|---|
 | Opus | claude | claude-opus-5 | high |
-| Fable | claude | claude-fable-5 | high |
+| Fable 5.1 | claude | claude-fable-5-1 | high |
 | Sonnet | claude | claude-sonnet-5 | high |
 | Haiku | claude | claude-haiku-4-5 | - |
 | Sol | codex | gpt-5.6-sol | max |
 | Terra | codex | gpt-5.6-terra | max |
-| Luna | codex | gpt-5.6-luna | medium |
-| Grok 4.5 | grok | grok-4.5 | - |
-| Gemini Pro | gemini | Gemini 3.1 Pro (High) | - |
-| Gemini Flash | gemini | Gemini 3.6 Flash (High) | - |
+| Luna | codex | gpt-5.6-luna | high |
+| Grok 4.6 | grok | grok-4.6 | - |
+| Gemini 3.1 Pro | gemini | Gemini 3.1 Pro (High) | - |
+| Gemini 3.7 Flash | gemini | Gemini 3.7 Flash (High) | - |
 | Kimi | kimi | kimi-k3 | - |
 | Qwen | qwen | qwen3-coder-plus | - |
 | OpenCode | opencode | provider/model form, or `-` for its own default | - |
@@ -159,19 +157,24 @@ dispatch stay in this skill and the CLI. Manage the local board with
 
 ## Per-model notes (apply the row matching YOUR main model)
 
-- **Claude (Fable/Opus main)**: top judgment and taste are yours, but
-  implementation still dispatches by default — self-execute only reserved
-  commander items; push all coding volume out to the lanes.
+- **Claude Fable 5.1 main**: hard judgment, taste finalization, and the hardest
+  coding are yours. Dispatch bulk work to Sol high and long-context or fast
+  loops to Gemini 3.7 Flash.
+- **Claude Opus 5 main**: judgment and taste remain strong self-execute lanes;
+  use local overrides when its lower hallucination rate or price is preferred.
 - **Claude Sonnet main**: coordination/tools/mid-tier coding only; never
   self-assign top judgment or hardest implementation.
 - **GPT Sol main**: hardest coding + hard judgment are yours (use max for
   judgment turns, xhigh for coding); cross to taste-final for style calls.
-- **GPT Terra main**: bulk work is yours at max; escalate the genuinely hardest
-  pieces to Sol instead of grinding.
-- **Grok 4.5 main**: mid-tier coding + live-search are yours; verify every API
-  signature and cited fact before shipping (measured high hallucination rate).
-- **Gemini Flash main**: fast agentic/multimodal loops are yours; never
-  self-assign top judgment.
-- **Gemini 3.1 Pro main**: 1M-context synthesis and context-heavy agentic work
-  are yours. Prefer Gemini Flash for fast repeated tool loops on speed/cost;
-  route hardest coding and judgment to the stronger codex lanes.
+- **GPT Terra main**: long-context Codex fallback work is yours at max;
+  bulk-mechanical now defaults to Sol high, and genuinely hardest pieces
+  escalate to Sol xhigh.
+- **Grok 4.6 main**: live-search and coding overflow are yours; its measured
+  hallucination rate is the lowest among the frontier rows, but still verify
+  every API signature and cited fact before shipping.
+- **Gemini 3.7 Flash main**: long-context and fast agentic/multimodal loops
+  are yours at the lane's configured effort; bulk and overflow use the high row.
+  Never self-assign top judgment.
+- **Gemini 3.1 Pro main**: it remains directly selectable, but the default
+  long-context lane now prefers Gemini 3.7 Flash on LCR, cost, and throughput;
+  route hardest coding and judgment to the stronger Codex and Claude lanes.