ai-consultants 5.1.0 → 5.1.1

package/.env.example

@@ -215,7 +215,7 @@ GROK_API_URL=https://api.x.ai/v1/chat/completions
 # GROK_REASONING_EFFORT= # max_quality sets xhigh (Grok Build maximum)
 
 # DeepSeek - The Code Specialist
-DEEPSEEK_MODEL=deepseek-v4-pro
+DEEPSEEK_MODEL=deepseek-flash
 DEEPSEEK_TIMEOUT=180
 DEEPSEEK_MAX_QUALITY_TIMEOUT=600
 DEEPSEEK_API_MAX_TOKENS=16384

package/CLAUDE.md

@@ -6,7 +6,7 @@ AI Consultants is a multi-model coverage system that queries up to 10 AI consult
 
 **Self-Exclusion**: The invoking agent is automatically excluded from both the panel and synthesis. Claude Code won't query or synthesize with Claude, Codex CLI won't query or synthesize with Codex, etc.
 
-**Version**: 5.1.0
+**Version**: 5.1.1
 
 ## Distribution
 
@@ -392,7 +392,7 @@ All consultants now use premium models by default:
 | Gemini | Gemini 3.7 Flash (High) (via agy CLI); API: gemini-3.1-pro-preview |
 | Codex | gpt-6-astra |
 | Mistral | CLI: mistral-medium-3.5; API: mistral-large-3 |
-| DeepSeek | deepseek-v4-pro |
+| DeepSeek | deepseek-flash (DeepSeek-V4.1-Flash) |
 | GLM | glm-5.3-flash |
 | Grok | grok-4.6 |
 | Qwen3 | qwen3.7-max |
@@ -760,6 +760,13 @@ curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/s
 
 ## Changelog
 
+### v5.1.1 (2026-09-10)
+
+- **DeepSeek V4.1 Flash policy.** `scripts/config.sh` selects `deepseek-flash` for the default and every tier. `scripts/configure.sh` migrates only the two exact historical unpinned defaults; durable pins and explicit overrides remain intact. No credentials are imported or personal configuration rewritten by the upgrade.
+- **Conservative cost accounting.** `docs/cost_rates.json` and the catalog-independent fallbacks use $0.30/M input and $1.20/M output for Flash, including retired Flash aliases now served by the new model. `format_cost_caveats` discloses the peak/cache-miss assumption and excluded discounts; estimates are not provider invoices. Other legacy rates are retained as historical estimates.
+- **Verification and scope.** PR #27 passed all 32 CI suites, plus local API 101, configure 138 and core 451 checks. One authorized API request on `96816b5` returned HTTP 200 and a correct structured expiry-boundary answer, with `deepseek-flash` provider-reported, max effort, 119 input / 602 output measured tokens. The shared transport is unchanged; provider identity is not rewritten into a version label. No frozen P1.6 input or live benchmark claim changes.
+
+
 ### v5.1.0 (2026-09-09)
 
 - **Fable and Astra model policy.** `scripts/config.sh` and `scripts/configure.sh` align default/premium/maximum with Fable 5.1 and Astra, retain Opus 5/Terra for standard and Haiku/Luna for economy, and migrate exact historical unpinned Codex defaults while recording their origin. `resolve_codex_effort` applies implicit high per request so a later tier cannot inherit an automatically exported value.

package/README.md

@@ -1,8 +1,8 @@
-# AI Consultants v5.1.0
+# AI Consultants v5.1.1
 
 > **Coverage, not a single guess.** A panel of up to 10 frontier models from different vendors fans out on your question in parallel and hands you the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses.
 
-[![Version](https://img.shields.io/badge/version-5.1.0-blue.svg)](https://github.com/matteoscurati/ai-consultants)
+[![Version](https://img.shields.io/badge/version-5.1.1-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)
@@ -412,7 +412,7 @@ the observed version is response provenance only.
 | Consultant | Default Model | Persona | Focus |
 |------------|---------------|---------|-------|
 | **GLM** | glm-5.3-flash | The Methodologist | Structured approaches |
-| **DeepSeek** | deepseek-v4-pro | The Code Specialist | Algorithms, code generation |
+| **DeepSeek** | deepseek-flash (V4.1 Flash) | The Code Specialist | Algorithms, code generation |
 
 ### Installing Consultant CLIs
 
@@ -489,7 +489,7 @@ and cannot support a comprehensive coverage claim.
 | Codex | gpt-6-astra | gpt-6-astra | gpt-5.6-terra | gpt-5.6-luna |
 | Mistral CLI | mistral-medium-3.5 | mistral-medium-3.5 | mistral-medium-3.5 | devstral-small-2 |
 | Mistral API | mistral-large-3 | mistral-large-3 | mistral-large-3 | mistral-large-3 |
-| DeepSeek | deepseek-v4-pro | deepseek-v4-pro | deepseek-v4-flash | deepseek-v4-flash |
+| DeepSeek | deepseek-flash | deepseek-flash | deepseek-flash | deepseek-flash |
 | GLM | glm-5.3-flash | glm-5.3-flash | glm-5.3-flash | glm-4-flash |
 | Grok | grok-4.6 | grok-4.6 | grok-4.5 | grok-4.5 |
 | Qwen3 | qwen3.8-max when Token Plan is configured; otherwise qwen3.7-max | qwen3.7-max | qwen3.6-35b-a3b | qwen3-32b |

package/SKILL.md

@@ -5,10 +5,10 @@ license: MIT
 compatibility: Requires bash, jq, and at least 2 AI CLI tools (agy, codex, vibe, etc.). macOS and Linux.
 metadata:
   author: matteoscurati
-  version: 5.1.0
+  version: 5.1.1
 ---
 
-# AI Consultants v5.1.0 - AI Expert Panel
+# AI Consultants v5.1.1 - AI Expert Panel
 
 **Coverage, not a single guess.** Convene a panel of AI "consultants" from different vendors for coding questions: they fan out in parallel and you get the *union* of what they collectively see — the risks, edge cases, and approaches a single model misses. Each consultant has a **configurable persona** that decorrelates its analysis.
 

package/docs/COST_RATES.md

@@ -1,4 +1,4 @@
-# Cost Rates - AI Consultants v5.1.0
+# Cost Rates - AI Consultants v5.1.1
 
 This page documents the per-token rates used by the cost tracking system.
 
@@ -45,8 +45,9 @@ models programmatically.
 | composer-2.5 | Legacy | $0.0005 | Removed Cursor consultant |
 | composer-2 | Legacy | $0.0005 | Removed Cursor consultant |
 | gemini-3-flash | Legacy | $0.0005 | Removed Cursor consultant |
-| deepseek-v4-pro | Premium | $0.000435 | DeepSeek |
-| deepseek-v4-flash | Standard/Economy | $0.00014 | DeepSeek |
+| deepseek-v4-pro | Legacy explicit override | $0.000435 | DeepSeek |
+| deepseek-flash | All tiers | $0.0003 | DeepSeek (peak, cache miss) |
+| deepseek-v4-flash / deepseek-v4-flash-vision-exp | Retired aliases → V4.1 Flash | $0.0003 | DeepSeek (peak, cache miss) |
 | glm-5.3-flash | Maximum/Premium/Standard | Unpriced | GLM coding-plan endpoint |
 | glm-5.3 | Legacy pins | Unpriced | GLM coding-plan endpoint |
 | glm-4-flash | Economy | $0.001 | GLM |
@@ -89,8 +90,9 @@ models programmatically.
 | composer-2.5 | Legacy | $0.0025 | Removed Cursor consultant |
 | composer-2 | Legacy | $0.0025 | Removed Cursor consultant |
 | gemini-3-flash | Legacy | $0.003 | Removed Cursor consultant |
-| deepseek-v4-pro | Premium | $0.00087 | DeepSeek |
-| deepseek-v4-flash | Standard/Economy | $0.00028 | DeepSeek |
+| deepseek-v4-pro | Legacy explicit override | $0.00087 | DeepSeek |
+| deepseek-flash | All tiers | $0.0012 | DeepSeek (peak) |
+| deepseek-v4-flash / deepseek-v4-flash-vision-exp | Retired aliases → V4.1 Flash | $0.0012 | DeepSeek (peak) |
 | glm-5.3-flash | Maximum/Premium/Standard | Unpriced | GLM coding-plan endpoint |
 | glm-5.3 | Legacy pins | Unpriced | GLM coding-plan endpoint |
 | glm-4-flash | Economy | $0.003 | GLM |
@@ -191,3 +193,14 @@ presenting them as free.
 Cost tracking requires:
 - `bc` - For floating point calculations
 - `jq` - For JSON parsing
+
+## DeepSeek V4.1 Flash pricing
+
+As of 2026-09-10, the official API name `deepseek-flash` selects V4.1 Flash.
+The estimator uses peak cache-miss rates: $0.30/M input and $1.20/M output.
+Off-peak rates are $0.15/M input and $0.60/M output; cached input is $0.006/M
+peak or $0.003/M off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00
+UTC. The estimate deliberately excludes these discounts; it is not an invoice.
+Legacy Flash and Flash Vision Exp aliases are now served and billed as V4.1 Flash.
+Other legacy catalog entries remain historical estimates, not newly verified quotes.
+Source: [DeepSeek models and pricing](https://api-docs.deepseek.com/quick_start/pricing/).

package/docs/SETUP.md

@@ -850,3 +850,25 @@ argument list. Hidden flags such as `--no-memory` are still required in the
 actual request even when omitted from public help. Unsupported mandatory flags
 block dispatch; the optional `--no-auto-update` guard is used when its parser
 probe succeeds, including on CLIs that hide it from help.
+
+### DeepSeek V4.1 Flash
+
+DeepSeek uses the HTTP API with `DEEPSEEK_MODEL=deepseek-flash` in every tier.
+This is the official API alias for DeepSeek-V4.1-Flash as of 2026-09-10, not a
+version identity inferred from the requested name. Provider-reported model
+metadata is retained unchanged. `max_quality` continues to request `max` effort;
+other tiers leave effort to the provider unless explicitly configured. The
+provider defaults to thinking mode at high effort. Existing text-only Chat
+Completions requests and the 16,384-token completion budget remain compatible.
+
+`configure` migrates exact unpinned `deepseek-v4-pro` and `deepseek-v4-flash`
+values; `# ai-consultants:pin`, environment overrides and `--set` preserve explicit
+choices. Old Flash aliases are still accepted but route to V4.1 Flash upstream.
+An explicit pin preserves the requested ID, not a guarantee against provider
+routing changes. Peak cache-miss costs are estimates, excluding cache/off-peak
+discounts. An authorized one-attempt API smoke on 2026-09-10 passed with a structured
+response and provider-reported `deepseek-flash`; no version identity was invented
+from the alias. No CLI transport is introduced.
+
+Sources: [models/pricing](https://api-docs.deepseek.com/quick_start/pricing/) and
+[thinking mode](https://api-docs.deepseek.com/guides/thinking_mode/).

package/docs/cost_rates.json

@@ -1,7 +1,19 @@
 {
-  "version": "5.1.0",
+  "version": "5.1.1",
   "updated": "2026-08-23",
   "models": {
+    "deepseek-flash": {
+      "input": 0.0003,
+      "output": 0.0012,
+      "provider": "DeepSeek",
+      "notes": "DeepSeek-V4.1-Flash, verified 2026-09-10. Peak cache-miss estimate; off-peak and cache-hit discounts excluded. See https://api-docs.deepseek.com/quick_start/pricing/"
+    },
+    "deepseek-v4-flash-vision-exp": {
+      "input": 0.0003,
+      "output": 0.0012,
+      "provider": "DeepSeek",
+      "notes": "Retired alias served by V4.1 Flash; peak cache-miss estimate."
+    },
     "_comment_units": "All rates are USD per 1,000 tokens (per-1K). lib/costs.sh computes cost as (token_count / 1000) * rate, so every value here MUST be a per-1K rate = (provider $/1M price) / 1000. Do NOT paste $/MTok figures directly.",
     "_comment_premium": "Premium tier models - Sep 2026",
     "claude-fable-5-1": {
@@ -380,8 +392,8 @@
       "output": 0.003
     },
     "deepseek-v4-flash": {
-      "input": 0.00014,
-      "output": 0.00028
+      "input": 0.0003,
+      "output": 0.0012
     },
     "glm-5.2": {
       "input": 0.00098,
@@ -434,7 +446,7 @@
     "gemini": "Gemini 3.7 Flash (High)",
     "codex": "gpt-6-astra",
     "mistral": "mistral-large-3",
-    "deepseek": "deepseek-v4-pro",
+    "deepseek": "deepseek-flash",
     "glm": "glm-5.3-flash",
     "grok": "grok-4.6",
     "qwen3": "qwen3.7-max",
@@ -448,7 +460,7 @@
       "gemini": "Gemini 3.7 Flash (High)",
       "codex": "gpt-6-astra",
       "mistral": "mistral-medium-3.5",
-      "deepseek": "deepseek-v4-pro",
+      "deepseek": "deepseek-flash",
       "glm": "glm-5.3-flash",
       "grok": "grok-4.6",
       "qwen3": "qwen3.8-max",
@@ -460,7 +472,7 @@
       "gemini": "Gemini 3.7 Flash (High)",
       "codex": "gpt-6-astra",
       "mistral": "mistral-medium-3.5",
-      "deepseek": "deepseek-v4-pro",
+      "deepseek": "deepseek-flash",
       "glm": "glm-5.3-flash",
       "grok": "grok-4.6",
       "qwen3": "qwen3.7-max",
@@ -472,7 +484,7 @@
       "gemini": "Gemini 3.7 Flash (High)",
       "codex": "gpt-5.6-terra",
       "mistral": "mistral-medium-3.5",
-      "deepseek": "deepseek-v4-flash",
+      "deepseek": "deepseek-flash",
       "glm": "glm-5.3-flash",
       "grok": "grok-4.5",
       "qwen3": "qwen3.6-35b-a3b",
@@ -484,7 +496,7 @@
       "gemini": "Gemini 3.7 Flash (Low)",
       "codex": "gpt-5.6-luna",
       "mistral": "devstral-small-2",
-      "deepseek": "deepseek-v4-flash",
+      "deepseek": "deepseek-flash",
       "glm": "glm-4-flash",
       "grok": "grok-4.5",
       "qwen3": "qwen3-32b",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-consultants",
-  "version": "5.1.0",
+  "version": "5.1.1",
   "description": "A cross-vendor panel of up to 10 AI models that returns the coverage union of their distinct perspectives",
   "bin": {
     "ai-consultants": "bin/ai-consultants"

package/references/configuration.md

@@ -262,7 +262,7 @@ GROK_MAX_TURNS=4
 GROK_API_MAX_TOKENS=4096
 GROK_REASONING_EFFORT=      # max_quality sets xhigh (Grok Build maximum)
 GROK_OAUTH_MODE=shared      # shared (parallel default) | serialized (diagnostic)
-DEEPSEEK_MODEL=deepseek-v4-pro
+DEEPSEEK_MODEL=deepseek-flash  # DeepSeek-V4.1-Flash API alias
 DEEPSEEK_API_MAX_TOKENS=16384
 DEEPSEEK_MAX_QUALITY_TIMEOUT=600
 DEEPSEEK_REASONING_EFFORT=  # max_quality sets max

package/scripts/config.sh

@@ -243,7 +243,7 @@ export GROK_USE_API GROK_OAUTH_MODE
 # DEEPSEEK CONFIGURATION - The Methodologist (API-based)
 # =============================================================================
 
-DEEPSEEK_MODEL="${DEEPSEEK_MODEL:-deepseek-v4-pro}"
+DEEPSEEK_MODEL="${DEEPSEEK_MODEL:-deepseek-flash}"
 if [[ -n "${DEEPSEEK_TIMEOUT+x}" ]]; then
     DEEPSEEK_TIMEOUT_SECONDS="$DEEPSEEK_TIMEOUT"
 elif [[ -z "${DEEPSEEK_TIMEOUT_SECONDS+x}" ]]; then
@@ -622,7 +622,7 @@ get_model_for_tier() {
                 gemini)   [[ "$transport" == "api" ]] && echo "gemini-3.1-pro-preview" || echo "Gemini 3.7 Flash (High)" ;;
                 codex)    echo "gpt-6-astra" ;;
                 mistral)  [[ "$transport" == "api" ]] && echo "mistral-large-3" || echo "mistral-medium-3.5" ;;
-                deepseek) echo "deepseek-v4-pro" ;;
+                deepseek) echo "deepseek-flash" ;;
                 glm)      echo "glm-5.3-flash" ;;
                 grok)     echo "grok-4.6" ;;
                 qwen3)    echo "qwen3.8-max" ;;
@@ -637,7 +637,7 @@ get_model_for_tier() {
                 gemini)   [[ "$transport" == "api" ]] && echo "gemini-3.1-pro-preview" || echo "Gemini 3.7 Flash (High)" ;;
                 codex)    echo "gpt-6-astra" ;;
                 mistral)  [[ "$transport" == "api" ]] && echo "mistral-large-3" || echo "mistral-medium-3.5" ;;
-                deepseek) echo "deepseek-v4-pro" ;;
+                deepseek) echo "deepseek-flash" ;;
                 glm)      echo "glm-5.3-flash" ;;
                 grok)     echo "grok-4.6" ;;
                 qwen3)    echo "qwen3.7-max" ;;
@@ -652,7 +652,7 @@ get_model_for_tier() {
                 gemini)   [[ "$transport" == "api" ]] && echo "gemini-3.1-pro-preview" || echo "Gemini 3.7 Flash (High)" ;;
                 codex)    echo "gpt-5.6-terra" ;;
                 mistral)  [[ "$transport" == "api" ]] && echo "mistral-large-3" || echo "mistral-medium-3.5" ;;
-                deepseek) echo "deepseek-v4-flash" ;;
+                deepseek) echo "deepseek-flash" ;;
                 glm)      echo "glm-5.3-flash" ;;  # Same as premium (no mid-tier GLM)
                 grok)     echo "grok-4.5" ;;
                 qwen3)    echo "qwen3.6-35b-a3b" ;;  # Open-weight MoE (35B total, 3B active)
@@ -667,7 +667,7 @@ get_model_for_tier() {
                 gemini)   [[ "$transport" == "api" ]] && echo "gemini-3.1-pro-preview" || echo "Gemini 3.7 Flash (Low)" ;;
                 codex)    echo "gpt-5.6-luna" ;;
                 mistral)  [[ "$transport" == "api" ]] && echo "mistral-large-3" || echo "devstral-small-2" ;;
-                deepseek) echo "deepseek-v4-flash" ;;
+                deepseek) echo "deepseek-flash" ;;
                 glm)      echo "glm-4-flash" ;;
                 grok)     echo "grok-4.5" ;;
                 qwen3)    echo "qwen3-32b" ;;
@@ -1035,4 +1035,4 @@ list_presets() {
 # VERSION
 # =============================================================================
 
-AI_CONSULTANTS_VERSION="5.1.0"
+AI_CONSULTANTS_VERSION="5.1.1"

package/scripts/configure.sh

@@ -335,6 +335,17 @@ if [[ "$(read_value "$WORK_FILE" GROK_MODEL 2>/dev/null || true)" == "grok-4.5"
     echo "Migrated managed Grok default: grok-4.5 -> grok-4.6" >&2
 fi
 
+# Refresh only exact unpinned historical DeepSeek defaults. Environment and
+# --set selections carry pin markers and remain user-owned.
+case "$(read_value "$WORK_FILE" DEEPSEEK_MODEL 2>/dev/null || true)" in
+    deepseek-v4-pro|deepseek-v4-flash)
+        if ! has_value_marker "$WORK_FILE" DEEPSEEK_MODEL "$PIN_MARKER"; then
+            set_value DEEPSEEK_MODEL "deepseek-flash $DEFAULT_MARKER"
+            echo "Migrated managed DeepSeek default to deepseek-flash (V4.1 Flash)" >&2
+        fi
+        ;;
+esac
+
 configure_cli_only() {
     local enable_key="$1" cmd_key="$2" cmd enabled=false
     cmd=$(effective_input_value "$cmd_key")

package/scripts/lib/costs.sh

@@ -136,6 +136,7 @@ get_input_cost_per_1k() {
         gemini-2.5-pro)   echo "0.00125" ;;
         gemini-2.5-flash) echo "0.000075" ;;
         gemini-2.0-flash) echo "0.0001" ;;
+        deepseek-flash|deepseek-v4-flash|deepseek-v4-flash-vision-exp) echo "0.0003" ;;
         gpt-6-astra|claude-fable-5-1) echo "0.01" ;;
         gpt-4)            echo "0.03" ;;
         gpt-4-turbo)      echo "0.01" ;;
@@ -183,6 +184,7 @@ get_output_cost_per_1k() {
         gemini-2.5-pro)   echo "0.005" ;;
         gemini-2.5-flash) echo "0.0003" ;;
         gemini-2.0-flash) echo "0.0004" ;;
+        deepseek-flash|deepseek-v4-flash|deepseek-v4-flash-vision-exp) echo "0.0012" ;;
         gpt-6-astra|claude-fable-5-1) echo "0.05" ;;
         gpt-4)            echo "0.06" ;;
         gpt-4-turbo)      echo "0.03" ;;
@@ -401,7 +403,7 @@ format_cost_caveats() {
     local responses_dir="${1:-}"
     [[ -d "$responses_dir" ]] || return 0
 
-    local estimated=0 unknown=0 priced=0 f astra_estimate=0
+    local estimated=0 unknown=0 priced=0 f astra_estimate=0 deepseek_flash_estimate=0
     local unpriced_models=()
     while IFS= read -r f; do
         [[ -n "$f" ]] || continue
@@ -423,6 +425,13 @@ format_cost_caveats() {
         if [[ "$model" == gpt-6-astra ]] && ! jq -e '.metadata.provider_cost_usd | numbers' "$f" >/dev/null 2>&1; then
             astra_estimate=1
         fi
+        case "$model" in
+            deepseek-flash|deepseek-v4-flash|deepseek-v4-flash-vision-exp)
+                if ! jq -e '.metadata.provider_cost_usd | numbers' "$f" >/dev/null 2>&1; then
+                    deepseek_flash_estimate=1
+                fi
+                ;;
+        esac
         is_unpriced_model "$model" || continue
         seen=false
         for item in "${unpriced_models[@]+"${unpriced_models[@]}"}"; do
@@ -441,6 +450,9 @@ format_cost_caveats() {
     if [[ $astra_estimate -eq 1 ]]; then
         parts="${parts:+$parts; }cost estimated using Astra Standard rates; cache/service adjustments excluded, not an invoice"
     fi
+    if [[ $deepseek_flash_estimate -eq 1 ]]; then
+        parts="${parts:+$parts; }DeepSeek Flash cost estimated at peak cache-miss rates; off-peak/cache discounts excluded, not an invoice"
+    fi
     local unpriced=""
     if (( ${#unpriced_models[@]} > 0 )); then
         unpriced=$(IFS=,; printf '%s' "${unpriced_models[*]}")

package/scripts/query_deepseek.sh

@@ -5,7 +5,7 @@
 #
 # Environment variables:
 #   DEEPSEEK_API_KEY   - API key for DeepSeek (required)
-#   DEEPSEEK_MODEL     - Model to use (default: deepseek-reasoner)
+#   DEEPSEEK_MODEL     - Model to use (default: deepseek-flash (DeepSeek-V4.1-Flash))
 #   DEEPSEEK_TIMEOUT   - Timeout in seconds (default: 180)
 #   ENABLE_PERSONA     - Enable "The Code Specialist" persona (default: true)