llm-orchestrator 1.3.0 → 1.3.1

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "llm-orchestrator",
   "description": "Write /task once — it plans the work, shards it across parallel subagents, gates every phase and verifies before claiming done. Claude Code, Codex, OpenCode, Kilo.",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "author": {
     "name": "Bogdan-Gabriel Torcescu",
     "url": "https://www.linkedin.com/in/bogdantorcescu/"

package/README.md

@@ -456,7 +456,7 @@ Incumbents hold a seat on a provider ladder. Candidates are measured but unseate
 |---|---|---|---|---|---|---|
 | GPT-6 Luna | openai | codex | incumbent | W | low, medium, high, xhigh, max (reasoning_effort) | $0.1 / $0.5 |
 | GPT-5.6 Luna | openai | codex | incumbent (fallback for GPT-6 Luna) | W | low, medium, high, xhigh, max (reasoning_effort) | $0.2 / $1.2 |
-| GPT-5.6 Terra | openai | codex | incumbent | S | low, medium, high, xhigh, max (reasoning_effort) | $2 / $12 |
+| GPT-5.6 Terra | openai | codex | incumbent (S fallback; GPT-6 Sol holds the S seat one notch down) | S | low, medium, high, xhigh, max (reasoning_effort) | $2 / $12 |
 | GPT-6 Sol | openai | codex | incumbent | X | low, medium, high, xhigh, max (reasoning_effort) | $2 / $10 |
 | GPT-5.6 Sol | openai | codex | incumbent (fallback for GPT-6 Sol) | X | low, medium, high, xhigh, max (reasoning_effort) | $4 / $20 |
 | GPT-6 Astra | openai | codex | incumbent | F | low, medium, high, xhigh, max (reasoning_effort) | $10 / $50 |

package/lib/router.mjs

@@ -209,10 +209,14 @@ function effortScale(model) {
   return model.thinking?.control === 'budget_tokens' ? BUDGET_ORDER : EFFORT_ORDER;
 }
 
-function desiredEffort(model, level) {
+function desiredEffort(model, level, tier = null) {
   const matrix = loadMatrix();
   const row = matrix.thinking_levels[level];
   if (!row) return null;
+  // A model seated on a tier below its home runs a declared, lower effort there so it
+  // is score-matched to that tier's model rather than over-provisioned.
+  const override = tier ? model.thinking?.tier_effort?.[tier]?.[level] : undefined;
+  if (override) return override;
   if (model.thinking?.control === 'budget_tokens') {
     if (['T0', 'T1'].includes(level)) return 'disabled';
     if (['T2', 'T3'].includes(level)) return 'enabled';
@@ -228,8 +232,8 @@ function desiredEffort(model, level) {
  * about the evidence, not licence to invent an enum: we take the model's cheapest
  * published setting that is at least as deep as the request, or nothing.
  */
-function resolveEffort(model, level) {
-  const desired = desiredEffort(model, level);
+function resolveEffort(model, level, tier = null) {
+  const desired = desiredEffort(model, level, tier);
   if (desired === null) return { effort: null, substituted: false };
   const levels = Array.isArray(model.thinking?.levels) ? model.thinking.levels : [];
   if (levels.length === 0 || levels.includes(desired)) return { effort: desired, substituted: false };
@@ -341,10 +345,10 @@ export function rankModels({
     if (model.caps?.requires_explicit_flag && !explicitFable51) continue;
     if (model.caps?.requires_explicit_flag) cap_notes.push(`capped exception: ≤${Math.round((model.caps.share_max ?? 0) * 100)}% of dispatches, explicit request only`);
 
-    const resolved = resolveEffort(model, parsed.level);
+    const resolved = resolveEffort(model, parsed.level, parsed.tier);
     let effort = resolved.effort;
     if (effort === null) continue; // no expression for this thinking level on this control
-    if (resolved.substituted) cap_notes.push(`no measured \`${desiredEffort(model, parsed.level)}\` point; nearest published setting is \`${effort}\``);
+    if (resolved.substituted) cap_notes.push(`no measured \`${desiredEffort(model, parsed.level, parsed.tier)}\` point; nearest published setting is \`${effort}\``);
 
     const scale = effortScale(model);
     const cap = model.caps?.max_effort ?? scale[scale.length - 1];

package/models/top-models.json

@@ -366,6 +366,7 @@
       "admission": "incumbent",
       "tier": "X",
       "eligible_tiers": [
+        "S",
         "X"
       ],
       "supersedes": "gpt-5-6-sol",
@@ -388,7 +389,10 @@
         ],
         "always_on": false,
         "default_for_tier": "high",
-        "note": "Same Codex policy as GPT-5.6 Sol: ceiling `high`; T4 is `high` plus an independent second Sol `high` reviewer with no shared history. The API also accepts `none`, which is not measured and never routed."
+        "note": "Same Codex policy as GPT-5.6 Sol: ceiling `high`; T4 is `high` plus an independent second Sol `high` reviewer with no shared history. The API also accepts `none`, which is not measured and never routed. On the S seat it runs one notch down (tier_effort), score-matched to Terra.",
+        "tier_effort": {
+          "S": {"T1": "low", "T2": "low", "T3": "medium"}
+        }
       },
       "price": {
         "input_usd_per_mtok": 2,
@@ -463,7 +467,7 @@
       },
       "notes": [
         "Successor to GPT-5.6 Sol on the Codex X seat at half the per-token price ($2/$10 vs $4/$20, permanent pricing). It is cheaper per completed task at every measured effort and scores equal or higher at each (high 43 @ $0.37 vs 42 @ $0.81); GPT-5.6 Sol stays routable as its fallback.",
-        "Its `medium` (40 @ $0.25) also dominates GPT-5.6 Terra `xhigh` (38 @ $0.63); the S seat stays Terra because an incumbent's tier is its ladder seat, not a score — see the routing note."
+        "Also holds the Codex S seat: at every S pair it is cheaper and stronger than GPT-5.6 Terra (S T2: `low` 34 @ $0.13 vs Terra `medium` 30 @ $0.18; S T3: `medium` 40 @ $0.25 vs Terra `high` 34 @ $0.34). Terra stays routable as the S fallback."
       ],
       "sources": [
         "https://artificialanalysis.ai/models/gpt-6-sol",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llm-orchestrator",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "description": "Write /task once — it plans the work, shards it across parallel subagents, gates every phase and verifies before claiming done. Claude Code, Codex, OpenCode, Kilo.",
   "type": "module",
   "engines": {

package/policies/routing.md

@@ -75,7 +75,7 @@ the incumbents below are role mappings, not guarantees of availability.
 | Tier | Role | Claude incumbent | Codex incumbent |
 | --- | --- | --- | --- |
 | **W** worker | local, mechanical, repetitive, well-defined: code search, classification, extraction, small edits, boilerplate, simple tests, consistency checks, scoped transforms | Haiku 4.5 (`claude-haiku-4-5`) | `gpt-6-luna`, falling back to `gpt-5.6-luna` |
-| **S** standard | default software-engineering model: normal implementation, frontend/backend, moderate debugging, tests, reasonable multi-file refactors, codebase analysis, tool use | Sonnet 5 (`claude-sonnet-5`) | `gpt-5.6-terra` |
+| **S** standard | default software-engineering model: normal implementation, frontend/backend, moderate debugging, tests, reasonable multi-file refactors, codebase analysis, tool use | Sonnet 5 (`claude-sonnet-5`) | `gpt-6-sol` one notch down, falling back to `gpt-5.6-terra` |
 | **X** senior | hard debugging, architecture, concurrency, migrations, security, auth, payments, billing, backwards compatibility, critical code review, many invariants | Opus 5.5 (`claude-opus-5-5`), falling back to Opus 5 (`claude-opus-5`) | `gpt-6-sol`, falling back to `gpt-5.6-sol` |
 | **F** frontier | exceptional escalation: very ambiguous, long-horizon, cross-system, major architecture, very large codebase, planning under heavy constraints, or when X fails to produce a solid solution | Fable 5 (`claude-fable-5`) — default F. Fable 5.1 (`claude-fable-5-1`) is a hard-capped exception: **≤2% of all dispatches**, explicit request or documented F-T4 failure on Fable 5 only | GPT-6 Astra (`gpt-6-astra`) — a real single-agent frontier tier, no decomposition workaround needed |
 
@@ -86,7 +86,7 @@ Verified prices (Sep 2026, provider pricing pages), USD in/out per MTok:
 | Tier | Claude model | Claude $ in/out | Codex model | Codex $ in/out |
 | --- | --- | --- | --- | --- |
 | W | Haiku 4.5 (200K ctx) | $1 / $5 | `gpt-6-luna` (1.05M ctx); fallback `gpt-5.6-luna` $0.20 / $1.20 | $0.10 / $0.50 |
-| S | Sonnet 5 (1M ctx) | $2 / $10 | `gpt-5.6-terra` (1.05M ctx) | $2 / $12 |
+| S | Sonnet 5 (1M ctx) | $2 / $10 | `gpt-6-sol` one effort notch down (T1/T2 `low`, T3 `medium`); fallback `gpt-5.6-terra` $2 / $12 | $2 / $10 |
 | X | Opus 5.5 (1M ctx); fallback Opus 5 $5 / $25 | $4 / $20 | `gpt-6-sol` (1.05M ctx); fallback `gpt-5.6-sol` $4 / $20 | $2 / $10 |
 | F | Fable 5 (1M ctx) | $10 / $50 | `gpt-6-astra` (1.05M ctx) | $10 / $50 list — **but the cheapest F per completed task of any model here** |
 | F+ (≤2%) | Fable 5.1 (1M ctx) | $10 / $50 list — **effective cost significantly higher** (always-on thinking, longer turns, more output tokens per task) | — (Astra covers F) | — |

package/registries/routing-matrix.json

@@ -14,7 +14,8 @@
     "S": {
       "name": "standard",
       "responsibility": "Default software-engineering model: normal implementation, frontend/backend, moderate debugging, tests, reasonable multi-file refactors, codebase analysis, tool use.",
-      "incumbents": {"claude": "claude-sonnet-5", "codex": "gpt-5.6-terra"}
+      "incumbents": {"claude": "claude-sonnet-5", "codex": "gpt-6-sol"},
+      "fallbacks": {"codex": ["gpt-5.6-terra"]}
     },
     "X": {
       "name": "senior",
@@ -88,15 +89,15 @@
     },
     "S T1": {
       "claude": {"model": "claude-sonnet-5", "effort": "low"},
-      "codex": {"model": "gpt-5.6-terra", "effort": "low"}
+      "codex": {"model": "gpt-6-sol", "effort": "low"}
     },
     "S T2": {
       "claude": {"model": "claude-sonnet-5", "effort": "medium"},
-      "codex": {"model": "gpt-5.6-terra", "effort": "medium"}
+      "codex": {"model": "gpt-6-sol", "effort": "low"}
     },
     "S T3": {
       "claude": {"model": "claude-sonnet-5", "effort": "high"},
-      "codex": {"model": "gpt-5.6-terra", "effort": "high"}
+      "codex": {"model": "gpt-6-sol", "effort": "medium"}
     },
     "X T2": {
       "claude": {"model": "claude-opus-5-5", "effort": "medium"},
@@ -293,8 +294,7 @@
       {"model": "gpt-6-luna", "effort": "medium"},
       {"model": "gpt-6-luna", "effort": "xhigh"},
       {"model": "gpt-6-luna", "effort": "max"},
-      {"model": "gpt-5.6-terra", "effort": "medium"},
-      {"model": "gpt-5.6-terra", "effort": "high"},
+      {"model": "gpt-6-sol", "effort": "low"},
       {"model": "gpt-6-sol", "effort": "medium"},
       {"model": "gpt-6-sol", "effort": "high"},
       {"model": "gpt-6-sol", "effort": "high", "independent_second_reviewer": true},

package/schemas/top-models.schema.json

@@ -106,6 +106,11 @@
               "always_on": { "type": ["boolean", "null"] },
               "default_for_tier": { "type": ["string", "null"] },
               "note": { "type": "string" },
+              "tier_effort": {
+                "type": "object",
+                "description": "Per seat below the model's home tier: thinking level → effort to run there, so the model is score-matched to that tier instead of over-provisioned.",
+                "additionalProperties": { "type": "object", "additionalProperties": { "type": "string" } }
+              },
               "unmeasured_levels": {
                 "type": "array",
                 "items": { "type": "string" },