feat: add DeepSeek V4 Pro, rename GPT label to match actual model

- Added `deepseek` (DeepSeek V4 Pro) as 9th model via
  `openrouter/deepseek/deepseek-v4-pro` — verified in Kilo's registry
  (smoke test hit upstream provider rate limit 429, path is correct)
- User config label: "GPT 5.4 Codex" -> "GPT 5.5" to match what the
  native codex CLI actually uses (per ~/.codex/config.toml:
  model = "gpt-5.5"). Repo default keeps "GPT 5.4 Codex" since the
  OpenRouter path is `openrouter/openai/gpt-5.4-codex` (gpt-5.5 is not
  yet on OpenRouter).
- Default quorum raised to 10 (100% with 9 models + Claude).
- Added note to setup wizard about native codex using whatever is in
  ~/.codex/config.toml.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: kulvirgit

CHANGELOG.md

@@ -4,7 +4,11 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
-## [1.3.0] - 2026-04-23
+## [1.3.0] - 2026-04-24
+
+### Added
+
+- **DeepSeek V4 Pro** as 9th model (`openrouter/deepseek/deepseek-v4-pro`)
 
 ### Changed
 
@@ -13,7 +17,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
   - Grok 4 -> Grok 4.20 (`openrouter/x-ai/grok-4.20-beta` — Kilo maps OpenRouter's `x-ai/grok-4.20` under the `-beta` suffix in its model registry)
   - Qwen 3.5 Plus -> Qwen 3.6 Plus (`openrouter/qwen/qwen3.6-plus`)
   - GLM-5 -> GLM-5.1 (`zai-coding-plan/glm-5.1`)
-- Default minimum quorum raised to 9 (100% — all 8 models + Claude must respond)
+- Default minimum quorum raised to 10 (100% — all 9 models + Claude must respond)
 
 ### Removed
 

plugins/consensus/commands/consensus-setup.md

@@ -72,7 +72,7 @@ AskUserQuestion:
   header: "Provider"
   options:
     - label: "OpenRouter (Recommended)"
-      description: "1 API key, all 8 models via Kilo CLI. Simplest setup."
+      description: "1 API key, all 9 models via Kilo CLI. Simplest setup."
     - label: "Native CLIs"
       description: "Use codex, gemini, qwen CLIs directly where available. Requires each CLI installed separately."
     - label: "Both"
@@ -117,23 +117,24 @@ If user provides a key, update `~/.claude/.env` idempotently:
 
 Build the model list based on provider choice and detected CLIs.
 
-The 8 supported models and their CLI mappings:
+The 9 supported models and their CLI mappings:
 
 | Model ID | Name | OpenRouter (Kilo) | Native CLI |
 |----------|------|-------------------|------------|
-| `gpt` | GPT 5.4 Codex | `kilo run -m openrouter/openai/gpt-5.4-codex --auto` | `codex` (if codex CLI installed) |
+| `gpt` | GPT 5.4 Codex | `kilo run -m openrouter/openai/gpt-5.4-codex --auto` | `codex` (if codex CLI installed — note: native codex uses whatever model your `~/.codex/config.toml` specifies, e.g. `gpt-5.5`) |
 | `gemini` | Gemini 3.1 Pro | `kilo run -m openrouter/google/gemini-3.1-pro-preview --auto` | `gemini` (if gemini CLI installed) |
 | `kimi` | Kimi K2.6 | `kilo run -m openrouter/moonshotai/kimi-k2.6 --auto` | OpenRouter only |
 | `grok` | Grok 4.20 | `kilo run -m openrouter/x-ai/grok-4.20-beta --auto` | OpenRouter only |
 | `minimax` | MiniMax M2.7 | `kilo run -m openrouter/minimax/minimax-m2.7 --auto` | OpenRouter only |
 | `glm5` | GLM-5.1 | `kilo run -m zai-coding-plan/glm-5.1 --auto` | Z.ai direct only |
 | `qwen` | Qwen 3.6 Plus | `kilo run -m openrouter/qwen/qwen3.6-plus --auto` | `qwen` (if qwen CLI installed) |
 | `mimo` | MiMo V2 Pro | `kilo run -m openrouter/xiaomi/mimo-v2-pro --auto` | OpenRouter only |
+| `deepseek` | DeepSeek V4 Pro | `kilo run -m openrouter/deepseek/deepseek-v4-pro --auto` | OpenRouter only |
 
 **Note on native CLIs**: For `codex`, `gemini`, and `qwen`, set the config's `command` field to just `codex`, `gemini`, or `qwen`. The teammate template in the review/plan commands detects these and uses the correct native invocation patterns automatically (e.g., `codex exec -s read-only` for reviews, `codex exec resume --last` for convergence, `gemini -p` for reviews, `gemini --resume latest` for convergence, `qwen --approval-mode plan -p` with `-o text` for reviews, `qwen -c -p` for convergence). The `resume_flag` field is ignored for native CLIs.
 
 Determine which models are available:
-- **OpenRouter path**: All 8 available if `kilo` installed + API key set
+- **OpenRouter path**: All 9 available if `kilo` installed + API key set
 - **Native path**: Only `gpt` (if codex installed), `gemini` (if gemini installed), and `qwen` (if qwen installed)
 - **Both path**: Native CLI where available, OpenRouter/Kilo for the rest
 
@@ -159,9 +160,11 @@ AskUserQuestion:
       description: "{available via OpenRouter / available via qwen CLI / not available}"
     - label: "MiMo V2 Pro"
       description: "{available via OpenRouter / not available}"
+    - label: "DeepSeek V4 Pro"
+      description: "{available via OpenRouter / not available}"
 ```
 
-(Show all 8 models. Mark unavailable ones clearly. Pre-select available ones.)
+(Show all 9 models. Mark unavailable ones clearly. Pre-select available ones.)
 
 **Enforce: at least 1 external model must be selected.** If user selects none, tell them: "At least 1 external model is required for consensus reviews."
 
@@ -193,7 +196,7 @@ Constraints:
 
 Build the config JSON based on selections from Steps 3-6.
 
-For each of the 8 models:
+For each of the 9 models:
 - If the model was selected: set `enabled: true` and populate `command`/`resume_flag` based on provider choice
 - If the model was NOT selected: set `enabled: false` with the default OpenRouter command (so users can re-enable later)
 
@@ -226,7 +229,7 @@ Write the config to `~/.claude/consensus.json` using the Write tool:
 }
 ```
 
-All 8 models are always written to the config — enabled or disabled.
+All 9 models are always written to the config — enabled or disabled.
 
 ## Step 8: Smoke Test
 
@@ -287,12 +290,12 @@ Print the final summary:
 
 ## Rules
 
-1. **8 fixed models only.** Do not offer custom model configuration. The wizard supports exactly the 8 models listed above.
+1. **9 fixed models only.** Do not offer custom model configuration. The wizard supports exactly the 9 models listed above.
 2. **Idempotent .env updates.** When writing API keys, preserve all existing keys in the file. Only add/update the `OPENROUTER_API_KEY` line.
 3. **Native CLI support for codex, gemini, and qwen.** When a user selects native CLIs, set the config's `command` field to `codex`, `gemini`, or `qwen`. The teammate template in the review/plan commands handles the full invocation patterns automatically. All other models use OpenRouter/Kilo only.
-4. **OpenRouter is the recommended path.** 1 key = 8 models. Emphasize this as the simplest setup.
+4. **OpenRouter is the recommended path.** 1 key = 9 models. Emphasize this as the simplest setup.
 5. **Enforce minimum 1 external model.** Claude alone is not a consensus.
 6. **Hard-stop on quorum failure.** Never finalize a config that can't meet its own quorum.
 7. **User config location is `~/.claude/consensus.json`.** The plugin default at `plugins/consensus/consensus.config.json` is the fallback only.
-8. **Write all 8 models to config.** Include disabled models with `enabled: false` so users can re-enable them later without re-running setup.
+8. **Write all 9 models to config.** Include disabled models with `enabled: false` so users can re-enable them later without re-running setup.
 9. **Targeted API key sourcing.** Only export `OPENROUTER_API_KEY` from `~/.claude/.env`, never export all variables.

plugins/consensus/consensus.config.json

@@ -56,8 +56,15 @@
       "command": "kilo run -m openrouter/xiaomi/mimo-v2-pro --auto",
       "resume_flag": "-c",
       "enabled": true
+    },
+    {
+      "id": "deepseek",
+      "name": "DeepSeek V4 Pro",
+      "command": "kilo run -m openrouter/deepseek/deepseek-v4-pro --auto",
+      "resume_flag": "-c",
+      "enabled": true
     }
   ],
-  "min_quorum": 9,
+  "min_quorum": 10,
   "performance_tracking": false
 }