ai-consultants 2.10.5 → 2.10.8

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model AI deliberation system that queries up to 15 AI
 
 **Self-Exclusion**: The invoking agent is automatically excluded from the panel to prevent self-consultation. Claude Code won't query Claude, Codex CLI won't query Codex, etc.
 
-**Version**: 2.10.5
+**Version**: 2.10.8
 
 ## Distribution
 
@@ -414,9 +414,9 @@ Three tiers of models are available for each consultant, configurable via `apply
 
 | Tier | Description | Example Models |
 |------|-------------|----------------|
-| **premium** | Latest flagship models | opus-4.6, gemini-3.1-pro-preview, gpt-5.3-codex |
-| **standard** | Good quality at reasonable cost | sonnet-4.6, gemini-3-flash-preview, gpt-5.3 |
-| **economy** | Optimized for speed and low cost | haiku-4.5, gemini-2.0-flash, gpt-4o-mini |
+| **premium** | Latest flagship models | claude-opus-4-7, gemini-3.1-pro-preview, gpt-5.5 |
+| **standard** | Good quality at reasonable cost | claude-sonnet-4-6, gemini-3-flash-preview, gpt-5.3 |
+| **economy** | Optimized for speed and low cost | claude-haiku-4-5, gemini-2.0-flash, gpt-4o-mini |
 
 **Default models are now premium tier** for maximum quality.
 
@@ -429,7 +429,7 @@ apply_model_tier "economy"   # Set all consultants to economy models
 
 # Get model for a specific consultant and tier (v2.8.1)
 get_model_for_tier "gemini" "premium"   # → gemini-3.1-pro-preview
-get_model_for_tier "claude" "economy"   # → haiku-4.5
+get_model_for_tier "claude" "economy"   # → claude-haiku-4-5
 ```
 
 ### Quality Tier Presets
@@ -451,17 +451,17 @@ All consultants now use premium models by default:
 
 | Consultant | Default Model |
 |------------|---------------|
-| Claude | opus-4.6 |
+| Claude | claude-opus-4-7 |
 | Gemini | gemini-3.1-pro-preview |
-| Codex | gpt-5.3-codex |
+| Codex | gpt-5.5 |
 | Mistral | mistral-large-3 |
-| Cursor | composer-1.5 |
-| DeepSeek | deepseek-reasoner |
+| Cursor | composer-2 |
+| DeepSeek | deepseek-v4-pro |
 | GLM | glm-5.1 |
-| Grok | grok-4.20-0309-reasoning |
+| Grok | grok-4.3 |
 | Qwen3 | qwen3.6-plus |
 | Kimi | kimi-code/kimi-for-coding |
-| Aider | gpt-5.3-codex |
+| Aider | nvidia/nemotron-3-super-120b-a12b:free |
 | MiniMax | MiniMax-M2.7 |
 | Kilo | auto |
 | Ollama | qwen2.5-coder:32b |
@@ -653,9 +653,9 @@ for f in scripts/*.sh scripts/lib/*.sh; do bash -n "$f" && echo "OK: $f"; done
 | `PANIC_CONFIDENCE_THRESHOLD` | 5 | Panic threshold (v2.2) |
 | `ENABLE_OLLAMA` | false | Local model support (v2.2) |
 | `OLLAMA_MODEL` | qwen2.5-coder:32b | Ollama model (v2.5 - premium default) |
-| `CLAUDE_MODEL` | opus-4.6 | Claude model (v2.5) |
+| `CLAUDE_MODEL` | claude-opus-4-7 | Claude model (v2.5) |
 | `GEMINI_MODEL` | gemini-3.1-pro-preview | Gemini model (v2.5) |
-| `CODEX_MODEL` | gpt-5.3-codex | Codex model (v2.5) |
+| `CODEX_MODEL` | gpt-5.5 | Codex model (v2.5) |
 | `MISTRAL_MODEL` | mistral-large-3 | Mistral model (v2.5) |
 | `SYNTHESIS_STRATEGY` | majority | Synthesis strategy (v2.2) |
 | `ENABLE_SEMANTIC_CACHE` | true | Semantic response caching (v2.3) |
@@ -802,6 +802,28 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v2.10.8
+- Fixed `docs/cost_rates.json` drift introduced by v2.10.6: `consultant_fallbacks` (used at runtime by `lib/costs.sh`) and `model_tiers` were still pointing at the old IDs (`opus-4.6`, `gpt-5.3-codex`, `composer-1.5`, `deepseek-reasoner`, `sonnet-4.6`, `haiku-4.5`)
+- Added price entries for the v2.10.6 model IDs: `claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5`, `gpt-5.5`, `composer-2`, `deepseek-v4-pro`, `nvidia/nemotron-3-super-120b-a12b:free`
+- Moved superseded IDs to the legacy section so cost calculation still works for historical responses or pinned overrides
+- Synced `COST_RATES.md` tables to match
+- Pricing for `nvidia/nemotron-3-super-120b-a12b:free` set to $0/$0 (OpenRouter free tier)
+
+### v2.10.7
+- Grok premium upgraded from `grok-4.20-0309-reasoning` to `grok-4.3` (released 2026-04-30)
+- ~75% cheaper input ($1.25/M vs $5.00/M) and ~83% cheaper output ($2.50/M vs $15.00/M)
+- 1M-token context window
+- Moved `grok-4.20-0309-reasoning` to legacy section in cost catalog
+- Standard (`grok-3`) and economy (`grok-3-mini`) tiers unchanged
+
+### v2.10.6
+- Codex premium upgraded from `gpt-5.3-codex` to `gpt-5.5`
+- Cursor premium upgraded from `composer-1.5` to `composer-2`
+- Aider switched provider: `gpt-5.3-codex` → `nvidia/nemotron-3-super-120b-a12b:free` (free tier)
+- DeepSeek premium upgraded from `deepseek-reasoner` to `deepseek-v4-pro`
+- Claude IDs migrated from short aliases to canonical model IDs across all tiers: `opus-4.6` → `claude-opus-4-7`, `sonnet-4.6` → `claude-sonnet-4-6`, `haiku-4.5` → `claude-haiku-4-5`
+- Fixed Kilo SIGPIPE abort under `set -euo pipefail` (replaced `head -c` with parameter expansion)
+
 ### v2.10.5
 - Qwen3 premium model upgraded from `qwen3.5-plus` to `qwen3.6-plus` ($0.325/$1.95 per M tokens)
 - Qwen3 standard tier now uses open-weight `qwen3.6-35b-a3b` (MoE, 35B total / 3B active)

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v2.10.5
+# AI Consultants v2.10.8
 
 > Query multiple AI models simultaneously for expert opinions on coding questions. Get diverse perspectives, automatic synthesis, confidence-weighted recommendations, and multi-agent debate.
 
-[![Version](https://img.shields.io/badge/version-2.10.5-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-2.10.8-blue.svg)](https://github.com/matteoscurati/ai-consultants)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Claude Code Skill](https://img.shields.io/badge/Claude%20Code-Skill-orange.svg)](https://docs.anthropic.com/en/docs/claude-code/skills)
 [![GitHub stars](https://img.shields.io/github/stars/matteoscurati/ai-consultants?style=social)](https://github.com/matteoscurati/ai-consultants)

package/SKILL.md

@@ -5,10 +5,10 @@ license: MIT
 compatibility: Requires bash, jq, and at least 2 AI CLI tools (gemini, codex, vibe, etc.). macOS and Linux.
 metadata:
   author: matteoscurati
-  version: 2.10.5
+  version: 2.10.8
 ---
 
-# AI Consultants v2.10.5 - AI Expert Panel
+# AI Consultants v2.10.8 - AI Expert Panel
 
 Simultaneously consult multiple AIs as "consultants" for coding questions. Each consultant has a **configurable persona** that influences their response style.
 

package/docs/COST_RATES.md

@@ -1,4 +1,4 @@
-# Cost Rates - AI Consultants v2.10.5
+# Cost Rates - AI Consultants v2.10.8
 
 This page documents the per-token rates used by the cost tracking system.
 
@@ -21,22 +21,23 @@ Since v2.5, models are organized into three tiers. Use `apply_model_tier()` or `
 | gemini-3.1-pro-preview | Premium | $0.00125 | Gemini |
 | gemini-3-flash-preview | Standard | $0.000075 | Gemini |
 | gemini-2.0-flash | Economy | $0.0001 | Gemini |
-| gpt-5.3-codex | Premium | $0.01 | Codex |
-| gpt-5.3 | Standard | $0.005 | Codex |
-| gpt-4o-mini | Economy | $0.00015 | Codex |
-| opus-4.6 | Premium | $0.015 | Claude |
-| sonnet-4.6 | Standard | $0.003 | Claude |
-| haiku-4.5 | Economy | $0.00025 | Claude |
+| gpt-5.5 | Premium | $0.01 | Codex |
+| gpt-5.3 | Standard | $0.005 | Codex/Aider |
+| gpt-4o-mini | Economy | $0.00015 | Codex/Aider |
+| nvidia/nemotron-3-super-120b-a12b:free | Premium | $0.00 | Aider |
+| claude-opus-4-7 | Premium | $0.015 | Claude |
+| claude-sonnet-4-6 | Standard | $0.003 | Claude |
+| claude-haiku-4-5 | Economy | $0.00025 | Claude |
 | mistral-large-3 | Premium | $0.004 | Mistral |
 | mistral-medium-latest | Standard | $0.0027 | Mistral |
 | devstral-small-2 | Economy | $0.001 | Mistral |
-| composer-1.5 | Premium/Standard | $0.005 | Cursor |
-| deepseek-reasoner | Premium | $0.002 | DeepSeek |
+| composer-2 | Premium/Standard | $0.005 | Cursor |
+| deepseek-v4-pro | Premium | $0.002 | DeepSeek |
 | deepseek-v3.2 | Standard | $0.0014 | DeepSeek |
 | deepseek-chat | Economy | $0.001 | DeepSeek |
 | glm-5.1 | Premium/Standard | $0.002 | GLM |
 | glm-4-flash | Economy | $0.0005 | GLM |
-| grok-4.20-0309-reasoning | Premium | $0.005 | Grok |
+| grok-4.3 | Premium | $0.00125 | Grok |
 | grok-3 | Standard | $0.003 | Grok |
 | grok-3-mini | Economy | $0.001 | Grok |
 | qwen3.6-plus | Premium | $0.000325 | Qwen3 |
@@ -55,22 +56,23 @@ Since v2.5, models are organized into three tiers. Use `apply_model_tier()` or `
 | gemini-3.1-pro-preview | Premium | $0.005 | Gemini |
 | gemini-3-flash-preview | Standard | $0.0003 | Gemini |
 | gemini-2.0-flash | Economy | $0.0004 | Gemini |
-| gpt-5.3-codex | Premium | $0.03 | Codex |
-| gpt-5.3 | Standard | $0.015 | Codex |
-| gpt-4o-mini | Economy | $0.0006 | Codex |
-| opus-4.6 | Premium | $0.075 | Claude |
-| sonnet-4.6 | Standard | $0.015 | Claude |
-| haiku-4.5 | Economy | $0.00125 | Claude |
+| gpt-5.5 | Premium | $0.03 | Codex |
+| gpt-5.3 | Standard | $0.015 | Codex/Aider |
+| gpt-4o-mini | Economy | $0.0006 | Codex/Aider |
+| nvidia/nemotron-3-super-120b-a12b:free | Premium | $0.00 | Aider |
+| claude-opus-4-7 | Premium | $0.075 | Claude |
+| claude-sonnet-4-6 | Standard | $0.015 | Claude |
+| claude-haiku-4-5 | Economy | $0.00125 | Claude |
 | mistral-large-3 | Premium | $0.012 | Mistral |
 | mistral-medium-latest | Standard | $0.0081 | Mistral |
 | devstral-small-2 | Economy | $0.003 | Mistral |
-| composer-1.5 | Premium/Standard | $0.015 | Cursor |
-| deepseek-reasoner | Premium | $0.006 | DeepSeek |
+| composer-2 | Premium/Standard | $0.015 | Cursor |
+| deepseek-v4-pro | Premium | $0.006 | DeepSeek |
 | deepseek-v3.2 | Standard | $0.004 | DeepSeek |
 | deepseek-chat | Economy | $0.003 | DeepSeek |
 | glm-5.1 | Premium/Standard | $0.006 | GLM |
 | glm-4-flash | Economy | $0.0015 | GLM |
-| grok-4.20-0309-reasoning | Premium | $0.015 | Grok |
+| grok-4.3 | Premium | $0.0025 | Grok |
 | grok-3 | Standard | $0.009 | Grok |
 | grok-3-mini | Economy | $0.003 | Grok |
 | qwen3.6-plus | Premium | $0.00195 | Qwen3 |

package/docs/cost_rates.json

@@ -1,24 +1,25 @@
 {
-  "version": "2.10.5",
-  "updated": "2026-03-04",
+  "version": "2.10.8",
+  "updated": "2026-05-03",
   "models": {
-    "_comment_premium": "Premium tier models - March 2026",
-    "opus-4.6": {"input": 5.00, "output": 25.00},
+    "_comment_premium": "Premium tier models - May 2026",
+    "claude-opus-4-7": {"input": 5.00, "output": 25.00},
     "gemini-3.1-pro-preview": {"input": 1.25, "output": 5.00},
-    "gpt-5.3-codex": {"input": 3.00, "output": 12.00},
+    "gpt-5.5": {"input": 3.00, "output": 12.00},
     "mistral-large-3": {"input": 2.00, "output": 6.00},
-    "deepseek-reasoner": {"input": 0.55, "output": 2.19},
+    "deepseek-v4-pro": {"input": 0.55, "output": 2.19},
     "glm-5.1": {"input": 0.50, "output": 2.00},
-    "grok-4.20-0309-reasoning": {"input": 5.00, "output": 15.00},
+    "grok-4.3": {"input": 1.25, "output": 2.50},
     "qwen3.6-plus": {"input": 0.325, "output": 1.95},
     "qwen3.6-35b-a3b": {"input": 0.163, "output": 0.90},
-    "composer-1.5": {"input": 0.005, "output": 0.015},
+    "composer-2": {"input": 0.005, "output": 0.015},
     "minimax-m2.7": {"input": 0.50, "output": 2.00},
     "kimi-code/kimi-for-coding": {"input": 0.50, "output": 2.00},
     "amp": {"input": 0.005, "output": 0.015},
+    "nvidia/nemotron-3-super-120b-a12b:free": {"input": 0.00, "output": 0.00},
 
     "_comment_standard": "Standard tier models",
-    "sonnet-4.6": {"input": 3.00, "output": 15.00},
+    "claude-sonnet-4-6": {"input": 3.00, "output": 15.00},
     "gemini-3-flash-preview": {"input": 0.075, "output": 0.30},
     "gpt-5.3": {"input": 2.50, "output": 10.00},
     "mistral-medium-latest": {"input": 0.0027, "output": 0.0081},
@@ -26,7 +27,7 @@
     "grok-3": {"input": 3.00, "output": 9.00},
 
     "_comment_economy": "Economy tier models",
-    "haiku-4.5": {"input": 0.001, "output": 0.005},
+    "claude-haiku-4-5": {"input": 0.001, "output": 0.005},
     "gemini-2.0-flash": {"input": 0.0001, "output": 0.0004},
     "gpt-4o-mini": {"input": 0.00015, "output": 0.0006},
     "devstral-small-2": {"input": 0.001, "output": 0.003},
@@ -37,7 +38,14 @@
     "minimax-m2.5": {"input": 0.30, "output": 1.50},
 
     "_comment_legacy": "Legacy models for backwards compatibility",
+    "opus-4.6": {"input": 5.00, "output": 25.00},
+    "sonnet-4.6": {"input": 3.00, "output": 15.00},
+    "haiku-4.5": {"input": 0.001, "output": 0.005},
+    "gpt-5.3-codex": {"input": 3.00, "output": 12.00},
+    "composer-1.5": {"input": 0.005, "output": 0.015},
+    "deepseek-reasoner": {"input": 0.55, "output": 2.19},
     "qwen3.5-plus": {"input": 1.60, "output": 6.40},
+    "grok-4.20-0309-reasoning": {"input": 5.00, "output": 15.00},
     "claude-opus-4-5-20251124": {"input": 5.00, "output": 25.00},
     "claude-sonnet-4-5-20251124": {"input": 3.00, "output": 15.00},
     "claude-3-5-haiku-20241022": {"input": 0.001, "output": 0.005},
@@ -69,18 +77,18 @@
     "minimax-m2.1": {"input": 0.30, "output": 1.50}
   },
   "consultant_fallbacks": {
-    "_comment": "Premium defaults - Updated March 2026",
-    "claude": "opus-4.6",
+    "_comment": "Premium defaults - Updated May 2026",
+    "claude": "claude-opus-4-7",
     "gemini": "gemini-3.1-pro-preview",
-    "codex": "gpt-5.3-codex",
+    "codex": "gpt-5.5",
     "mistral": "mistral-large-3",
-    "deepseek": "deepseek-reasoner",
+    "deepseek": "deepseek-v4-pro",
     "glm": "glm-5.1",
-    "grok": "grok-4.20-0309-reasoning",
+    "grok": "grok-4.3",
     "qwen3": "qwen3.6-plus",
-    "aider": "gpt-5.3-codex",
+    "aider": "nvidia/nemotron-3-super-120b-a12b:free",
     "kilo": "auto",
-    "cursor": "composer-1.5",
+    "cursor": "composer-2",
     "amp": "amp",
     "kimi": "kimi-code/kimi-for-coding",
     "minimax": "minimax-m2.7",
@@ -89,24 +97,24 @@
   "model_tiers": {
     "_comment": "Model tiers for apply_model_tier() function",
     "premium": {
-      "claude": "opus-4.6",
+      "claude": "claude-opus-4-7",
       "gemini": "gemini-3.1-pro-preview",
-      "codex": "gpt-5.3-codex",
+      "codex": "gpt-5.5",
       "mistral": "mistral-large-3",
-      "deepseek": "deepseek-reasoner",
+      "deepseek": "deepseek-v4-pro",
       "glm": "glm-5.1",
-      "grok": "grok-4.20-0309-reasoning",
+      "grok": "grok-4.3",
       "qwen3": "qwen3.6-plus",
-      "aider": "gpt-5.3-codex",
+      "aider": "nvidia/nemotron-3-super-120b-a12b:free",
       "kilo": "auto",
-      "cursor": "composer-1.5",
+      "cursor": "composer-2",
       "amp": "amp",
       "kimi": "kimi-code/kimi-for-coding",
       "minimax": "minimax-m2.7",
       "ollama": "qwen2.5-coder:32b"
     },
     "standard": {
-      "claude": "sonnet-4.6",
+      "claude": "claude-sonnet-4-6",
       "gemini": "gemini-3-flash-preview",
       "codex": "gpt-5.3",
       "mistral": "mistral-medium-latest",
@@ -116,14 +124,14 @@
       "qwen3": "qwen3.6-35b-a3b",
       "aider": "gpt-5.3",
       "kilo": "auto",
-      "cursor": "composer-1.5",
+      "cursor": "composer-2",
       "amp": "amp",
       "kimi": "kimi-code/kimi-for-coding",
       "minimax": "minimax-m2.7",
       "ollama": "llama3.3"
     },
     "economy": {
-      "claude": "haiku-4.5",
+      "claude": "claude-haiku-4-5",
       "gemini": "gemini-2.0-flash",
       "codex": "gpt-4o-mini",
       "mistral": "devstral-small-2",

package/docs/releases/v2.10.6.md

@@ -0,0 +1,59 @@
+# Release v2.10.6
+
+**Date:** 2026-05-02
+**Type:** Patch — Premium model upgrades across 5 consultants + Kilo SIGPIPE fix
+**Previous:** v2.10.5
+
+## Highlights
+
+- Codex, Cursor, Aider, DeepSeek, and Claude all bumped to newer premium defaults
+- Aider switches provider to NVIDIA Nemotron 3 Super (free tier) via OpenRouter
+- Claude model IDs migrated from short aliases (`opus-4.6`) to canonical IDs (`claude-opus-4-7`)
+- Kilo no longer aborts under `set -euo pipefail` due to SIGPIPE from `head -c`
+
+## What's New
+
+### Premium Model Upgrades
+
+| Consultant | Before (v2.10.5) | After (v2.10.6) |
+|------------|------------------|------------------|
+| Codex      | `gpt-5.3-codex` | `gpt-5.5` |
+| Cursor     | `composer-1.5` | `composer-2` |
+| Aider      | `gpt-5.3-codex` | `nvidia/nemotron-3-super-120b-a12b:free` |
+| DeepSeek   | `deepseek-reasoner` | `deepseek-v4-pro` |
+| Claude     | `opus-4.6` / `sonnet-4.6` / `haiku-4.5` | `claude-opus-4-7` / `claude-sonnet-4-6` / `claude-haiku-4-5` |
+
+The Claude rename also covers standard and economy tiers — all three Claude tiers now use canonical IDs (`claude-<family>-<major>-<minor>`) matching the Anthropic API model identifiers, eliminating the alias indirection that previously required mapping in API mode.
+
+Aider moves off OpenAI Codex to NVIDIA's Nemotron 3 Super 120B (A12B-active MoE) on the OpenRouter free tier, lowering cost-per-consultation for collaborative coding workflows.
+
+### Kilo SIGPIPE Fix
+
+`query_kilo.sh` previously truncated output via `echo "$CONTENT" | head -5 | ... | head -c 200`. Under `set -o pipefail`, `head -c` closing the pipe before the upstream `sed` finished writing produced a SIGPIPE that aborted the entire script. Replaced the trailing `head -c` with bash parameter expansion (`${var:0:N}`), which truncates safely without involving the pipeline.
+
+## Breaking Changes
+
+None. Existing `CLAUDE_MODEL`, `CODEX_MODEL`, `CURSOR_MODEL`, `AIDER_MODEL`, and `DEEPSEEK_MODEL` overrides continue to work — only the *defaults* changed.
+
+If you were relying on the short Claude aliases (`opus-4.6`, etc.) in scripts, those still work as overrides through the CLI; the change only affects what's selected when no override is present.
+
+## Upgrade Guide
+
+```bash
+# If installed via git clone
+cd ~/.claude/skills/ai-consultants && git pull
+
+# If installed via curl | bash
+curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash
+```
+
+No configuration changes required.
+
+## Commits
+
+- `e797d69` fix(kilo): use parameter expansion to avoid SIGPIPE under set -euo pipefail
+- `e52d6d4` feat: upgrade Codex, Cursor, Aider, DeepSeek, Claude premium models
+
+## Contributors
+
+- @matteoscurati

package/docs/releases/v2.10.7.md

@@ -0,0 +1,53 @@
+# Release v2.10.7
+
+**Date:** 2026-05-02
+**Type:** Patch — Grok premium model upgrade to grok-4.3
+**Previous:** v2.10.6
+
+## Highlights
+
+- Grok premium upgraded from `grok-4.20-0309-reasoning` to `grok-4.3`
+- ~75% cheaper input, ~83% cheaper output, with a 1M-token context window
+- xAI explicitly recommends migrating all callers to grok-4.3
+
+## What's New
+
+### Grok 4.3 Upgrade
+
+xAI released Grok 4.3 on April 30, 2026 as their flagship model, replacing the previous reasoning-focused `grok-4.20-0309-reasoning`. The new model is positioned as both the most intelligent and the fastest in the lineup, with aggressive pricing.
+
+| Tier | Before (v2.10.6) | After (v2.10.7) |
+|------|-------------------|------------------|
+| Premium | grok-4.20-0309-reasoning ($5.00/$15.00 per M) | grok-4.3 ($1.25/$2.50 per M) |
+| Standard | grok-3 ($3.00/$9.00 per M) | grok-3 (unchanged) |
+| Economy | grok-3-mini ($1.00/$3.00 per M) | grok-3-mini (unchanged) |
+
+The premium tier moves from $20.00 combined per million tokens (input + output average) to $3.75 — a roughly 5x reduction at typical query shapes. The 1M-token context window is unchanged from the prior reasoning variant.
+
+**Note on tiered pricing:** xAI bills requests exceeding 200k input tokens at a higher rate. For very long-context queries, consult the xAI Console for the exact tiered pricing.
+
+The standard and economy tiers continue to use `grok-3` and `grok-3-mini` respectively. The previous premium model `grok-4.20-0309-reasoning` was moved to the legacy section of `docs/cost_rates.json` so cost calculation continues to work for any historical responses or pinned overrides.
+
+## Breaking Changes
+
+None. Existing `GROK_MODEL` overrides continue to work — only the default changed.
+
+## Upgrade Guide
+
+```bash
+# If installed via git clone
+cd ~/.claude/skills/ai-consultants && git pull
+
+# If installed via curl | bash
+curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash
+```
+
+No configuration changes required.
+
+## Commits
+
+- `1d3a53b` feat(grok): upgrade premium to grok-4.3 (released 2026-04-30)
+
+## Contributors
+
+- @matteoscurati

package/docs/releases/v2.10.8.md

@@ -0,0 +1,58 @@
+# Release v2.10.8
+
+**Date:** 2026-05-03
+**Type:** Patch — Cost catalog sync (fixes v2.10.6 drift)
+**Previous:** v2.10.7
+
+## Highlights
+
+- Fixes a runtime drift introduced by v2.10.6: `docs/cost_rates.json` was still pointing `consultant_fallbacks` at the old model IDs (`opus-4.6`, `gpt-5.3-codex`, `composer-1.5`, `deepseek-reasoner`)
+- Adds price entries for the v2.10.6 model IDs (Claude canonical IDs, `gpt-5.5`, `composer-2`, `deepseek-v4-pro`, `nvidia/nemotron-3-super-120b-a12b:free`)
+- Old IDs preserved in the legacy section so cost calculation still works for historical responses or pinned overrides
+
+## What's New
+
+### Cost Catalog Sync
+
+In v2.10.6 we updated `scripts/config.sh` to use canonical model IDs for Claude and to switch Codex/Cursor/Aider/DeepSeek to newer models. However, `docs/cost_rates.json` — which is read at runtime by `lib/costs.sh` to resolve fallback prices when a consultant doesn't report its own model — was not updated. Two effects:
+
+1. `consultant_fallbacks.claude = "opus-4.6"` would have caused fallback cost lookups to use `opus-4.6` even when the consultant ran on `claude-opus-4-7`. The price for `claude-opus-4-7` was missing from the catalog entirely, which would have triggered the `default_rate` ($0.005/$0.015 per 1k) for any direct lookup of the new ID.
+2. The reference `model_tiers` table in the JSON file (documentation, not used at runtime) was inconsistent with the canonical source in `config.sh::get_model_for_tier()`.
+
+Both issues are now fixed. `consultant_fallbacks` and `model_tiers` mirror the active defaults in `config.sh`, and every model ID referenced by the defaults has a corresponding price entry.
+
+### Catalog Layout Changes
+
+| Section | Added | Moved to legacy |
+|---------|-------|------------------|
+| Premium | `claude-opus-4-7`, `gpt-5.5`, `composer-2`, `deepseek-v4-pro`, `nvidia/nemotron-3-super-120b-a12b:free` | `opus-4.6`, `gpt-5.3-codex`, `composer-1.5`, `deepseek-reasoner` |
+| Standard | `claude-sonnet-4-6` | `sonnet-4.6` |
+| Economy | `claude-haiku-4-5` | `haiku-4.5` |
+
+Pricing values mirror the prior entries for direct successors (the model lineage is the same, only the canonical ID changed). `nvidia/nemotron-3-super-120b-a12b:free` is set to $0/$0 to reflect OpenRouter's free tier — this means Aider consultations contribute zero to cost tracking when running on the default model.
+
+`COST_RATES.md` was updated to mirror the new active and legacy IDs.
+
+## Breaking Changes
+
+None.
+
+## Upgrade Guide
+
+```bash
+# If installed via git clone
+cd ~/.claude/skills/ai-consultants && git pull
+
+# If installed via curl | bash
+curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash
+```
+
+No configuration changes required.
+
+## Commits
+
+- `885e2ea` fix(costs): sync cost catalog with v2.10.6 model defaults
+
+## Contributors
+
+- @matteoscurati

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-consultants",
-  "version": "2.10.5",
+  "version": "2.10.8",
   "description": "Multi-model AI deliberation system - query up to 15 AI consultants for coding problems",
   "bin": {
     "ai-consultants": "bin/ai-consultants"

package/scripts/config.sh

@@ -63,8 +63,8 @@ GEMINI_CMD="${GEMINI_CMD:-gemini}"
 # CODEX CONFIGURATION - The Pragmatist
 # =============================================================================
 
-# Model: "gpt-5.3-codex" (default), "gpt-5.3", "gpt-4o-mini", etc.
-CODEX_MODEL="${CODEX_MODEL:-gpt-5.3-codex}"
+# Model: "gpt-5.5" (default), "gpt-5.3", "gpt-4o-mini", etc.
+CODEX_MODEL="${CODEX_MODEL:-gpt-5.5}"
 CODEX_TIMEOUT_SECONDS="${CODEX_TIMEOUT:-180}"
 CODEX_CMD="${CODEX_CMD:-codex}"
 
@@ -89,7 +89,7 @@ KILO_CMD="${KILO_CMD:-kilocode}"
 # CURSOR CONFIGURATION - The Integrator
 # =============================================================================
 
-CURSOR_MODEL="${CURSOR_MODEL:-composer-1.5}"
+CURSOR_MODEL="${CURSOR_MODEL:-composer-2}"
 CURSOR_TIMEOUT_SECONDS="${CURSOR_TIMEOUT:-180}"
 CURSOR_CMD="${CURSOR_CMD:-agent}"
 
@@ -97,7 +97,7 @@ CURSOR_CMD="${CURSOR_CMD:-agent}"
 # AIDER CONFIGURATION - The Pair Programmer
 # =============================================================================
 
-AIDER_MODEL="${AIDER_MODEL:-gpt-5.3-codex}"
+AIDER_MODEL="${AIDER_MODEL:-nvidia/nemotron-3-super-120b-a12b:free}"
 AIDER_TIMEOUT_SECONDS="${AIDER_TIMEOUT:-180}"
 AIDER_CMD="${AIDER_CMD:-aider}"
 
@@ -127,7 +127,7 @@ GLM_FORMAT="${GLM_FORMAT:-openai}"
 # GROK CONFIGURATION - The Provocateur (API-based)
 # =============================================================================
 
-GROK_MODEL="${GROK_MODEL:-grok-4.20-0309-reasoning}"
+GROK_MODEL="${GROK_MODEL:-grok-4.3}"
 GROK_TIMEOUT_SECONDS="${GROK_TIMEOUT:-180}"
 GROK_API_URL="${GROK_API_URL:-https://api.x.ai/v1/chat/completions}"
 GROK_FORMAT="${GROK_FORMAT:-openai}"
@@ -137,7 +137,7 @@ GROK_FORMAT="${GROK_FORMAT:-openai}"
 # DEEPSEEK CONFIGURATION - The Methodologist (API-based)
 # =============================================================================
 
-DEEPSEEK_MODEL="${DEEPSEEK_MODEL:-deepseek-reasoner}"
+DEEPSEEK_MODEL="${DEEPSEEK_MODEL:-deepseek-v4-pro}"
 DEEPSEEK_TIMEOUT_SECONDS="${DEEPSEEK_TIMEOUT:-180}"
 DEEPSEEK_API_URL="${DEEPSEEK_API_URL:-https://api.deepseek.com/v1/chat/completions}"
 DEEPSEEK_FORMAT="${DEEPSEEK_FORMAT:-openai}"
@@ -176,7 +176,7 @@ KIMI_CMD="${KIMI_CMD:-kimi}"
 # CLAUDE CONFIGURATION - The Synthesizer (v2.2)
 # =============================================================================
 
-CLAUDE_MODEL="${CLAUDE_MODEL:-opus-4.6}"
+CLAUDE_MODEL="${CLAUDE_MODEL:-claude-opus-4-7}"
 CLAUDE_TIMEOUT_SECONDS="${CLAUDE_TIMEOUT:-240}"
 CLAUDE_CMD="${CLAUDE_CMD:-claude}"
 
@@ -525,16 +525,16 @@ get_model_for_tier() {
     case "$tier" in
         premium|max|best)
             case "$consultant" in
-                claude)   echo "opus-4.6" ;;
+                claude)   echo "claude-opus-4-7" ;;
                 gemini)   echo "gemini-3.1-pro-preview" ;;
-                codex)    echo "gpt-5.3-codex" ;;
+                codex)    echo "gpt-5.5" ;;
                 mistral)  echo "mistral-large-3" ;;
-                cursor)   echo "composer-1.5" ;;
-                deepseek) echo "deepseek-reasoner" ;;
+                cursor)   echo "composer-2" ;;
+                deepseek) echo "deepseek-v4-pro" ;;
                 glm)      echo "glm-5.1" ;;
-                grok)     echo "grok-4.20-0309-reasoning" ;;
+                grok)     echo "grok-4.3" ;;
                 qwen3)    echo "qwen3.6-plus" ;;
-                aider)    echo "gpt-5.3-codex" ;;
+                aider)    echo "nvidia/nemotron-3-super-120b-a12b:free" ;;
                 amp)      echo "amp" ;;
                 ollama)   echo "qwen2.5-coder:32b" ;;
                 kimi)     echo "kimi-code/kimi-for-coding" ;;
@@ -545,7 +545,7 @@ get_model_for_tier() {
             ;;
         standard|medium|balanced)
             case "$consultant" in
-                claude)   echo "sonnet-4.6" ;;
+                claude)   echo "claude-sonnet-4-6" ;;
                 gemini)   echo "gemini-3-flash-preview" ;;
                 codex)    echo "gpt-5.3" ;;
                 mistral)  echo "mistral-medium-latest" ;;
@@ -565,7 +565,7 @@ get_model_for_tier() {
             ;;
         economy|fast|quick)
             case "$consultant" in
-                claude)   echo "haiku-4.5" ;;
+                claude)   echo "claude-haiku-4-5" ;;
                 gemini)   echo "gemini-2.0-flash" ;;
                 codex)    echo "gpt-4o-mini" ;;
                 mistral)  echo "devstral-small-2" ;;
@@ -750,4 +750,4 @@ EOF
 # VERSION
 # =============================================================================
 
-AI_CONSULTANTS_VERSION="2.10.5"
+AI_CONSULTANTS_VERSION="2.10.8"

package/scripts/query_kilo.sh

@@ -95,13 +95,15 @@ if [[ $exit_code -eq 0 && -n "${CONTENT:-}" ]]; then
             "$TEMP_OUTPUT" "$OUTPUT_FILE" "$exit_code" "$LATENCY_MS"
     else
         # Extract structured fields from markdown/text output
-        # Summary: first meaningful line(s), up to 200 chars
-        local_summary=$(echo "$CONTENT" | head -5 | tr '\n' ' ' | sed 's/^[[:space:]]*//;s/[[:space:]]*$//' | head -c 200)
+        # Note: truncation via parameter expansion (not `head -c`) to avoid SIGPIPE
+        # aborting the script under `set -euo pipefail`.
+        local_summary=$(echo "$CONTENT" | head -5 | tr '\n' ' ' | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')
+        local_summary="${local_summary:0:200}"
 
-        # Approach: look for headings or key phrases
         local_approach=$(echo "$CONTENT" | grep -iE '^#+\s|^approach:|^recommendation:|^solution:' | head -1 | \
-            sed 's/^[#[:space:]]*//;s/^[Aa]pproach:[[:space:]]*//' | head -c 100)
-        [[ -z "$local_approach" ]] && local_approach=$(echo "$local_summary" | head -c 60)
+            sed 's/^[#[:space:]]*//;s/^[Aa]pproach:[[:space:]]*//' || true)
+        local_approach="${local_approach:0:100}"
+        [[ -z "$local_approach" ]] && local_approach="${local_summary:0:60}"
 
         # Confidence: estimate from language strength
         local_confidence=6

package/scripts/test_suite.sh

@@ -1088,7 +1088,7 @@ test_economic_models() {
 
     assert_equals "gemini-2.0-flash" "$(get_economic_model "gemini")" "gemini economy is gemini-2.0-flash"
     assert_equals "gpt-4o-mini"      "$(get_economic_model "codex")"  "codex economy is gpt-4o-mini"
-    assert_equals "haiku-4.5"        "$(get_economic_model "claude")" "claude economy is haiku-4.5"
+    assert_equals "claude-haiku-4-5" "$(get_economic_model "claude")" "claude economy is claude-haiku-4-5"
     assert_equals "MiniMax-M2.5"     "$(get_economic_model "minimax")" "minimax economy is MiniMax-M2.5"
     assert_equals ""                 "$(get_economic_model "unknown")" "unknown consultant returns empty"
 }
@@ -1424,9 +1424,9 @@ test_escalation() {
 test_model_for_tier() {
     suite "config.sh: get_model_for_tier"
 
-    assert_equals "opus-4.6"              "$(get_model_for_tier "claude" "premium")"  "claude premium is opus-4.6"
-    assert_equals "sonnet-4.6"            "$(get_model_for_tier "claude" "standard")" "claude standard is sonnet-4.6"
-    assert_equals "haiku-4.5"             "$(get_model_for_tier "claude" "economy")"  "claude economy is haiku-4.5"
+    assert_equals "claude-opus-4-7"       "$(get_model_for_tier "claude" "premium")"  "claude premium is claude-opus-4-7"
+    assert_equals "claude-sonnet-4-6"     "$(get_model_for_tier "claude" "standard")" "claude standard is claude-sonnet-4-6"
+    assert_equals "claude-haiku-4-5"      "$(get_model_for_tier "claude" "economy")"  "claude economy is claude-haiku-4-5"
     assert_equals "gemini-3.1-pro-preview" "$(get_model_for_tier "gemini" "premium")" "gemini premium is gemini-3.1-pro-preview"
     assert_equals "gemini-2.0-flash"       "$(get_model_for_tier "gemini" "economy")" "gemini economy is gemini-2.0-flash"
     assert_equals "MiniMax-M2.7"           "$(get_model_for_tier "minimax" "premium")" "minimax premium is MiniMax-M2.7"