@polderlabs/bizar 3.8.0 → 3.9.1

package/README.md

@@ -65,18 +65,18 @@
 ### Agents
 
 | Agent | Rune | Model | Cost | Role |
-|---|---|---|---|---|---|
-| **Odin** | ᛟ | MiniMax-M3 | $0.30/M · $1.20/M out | Primary router — never executes, only delegates |
+|---|---|---|---|---|
+| **Odin** | ᛟ | OpenRouter minimax-m3 | $0.30/M · $1.20/M out | Primary router — never executes, only delegates |
 | **Frigg** | ᚠ | DeepSeek V4 Flash | **Free** | Read-only Q&A — ask questions, get answers, never modifies |
 | **Vör** | ᛢ | DeepSeek V4 Flash | **Free** | Clarifies ambiguous requests — asks questions until task is well-defined |
 | **Mimir** | ᛗ | DeepSeek V4 Flash | **Free** | Research & codebase exploration (Semble-first) |
 | **Heimdall** | ᚹ | DeepSeek V4 Flash | **Free** | Simple tasks, quick edits, file operations |
-| **Hermod** | ᚱ | MiniMax-M2.7 | $0.30/M · $1.20/M out | Git & GitHub operations (commit, PR, merge, rebase) |
-| **Thor** | ᚦ | MiniMax-M2.7 | $0.30/M · $1.20/M out | Moderate implementation, debugging, refactoring |
-| **Baldr** | ᛒ | MiniMax-M2.7 | $0.30/M · $1.20/M out | UI/UX design system (DESIGN.md plans, visual audits) |
-| **Tyr** | ᛏ | MiniMax-M3 | $0.30/M · $1.20/M out | Complex implementation, architecture, deep debugging |
+| **Hermod** | ᚱ | OpenRouter minimax-m2.7 | $0.30/M · $1.20/M out | Git & GitHub operations (commit, PR, merge, rebase) |
+| **Thor** | ᚦ | OpenRouter minimax-m2.7 | $0.30/M · $1.20/M out | Moderate implementation, debugging, refactoring |
+| **Baldr** | ᛒ | OpenRouter minimax-m2.7 | $0.30/M · $1.20/M out | UI/UX design system (DESIGN.md plans, visual audits) |
+| **Tyr** | ᛏ | OpenRouter minimax-m3 | $0.30/M · $1.20/M out | Complex implementation, architecture, deep debugging |
 | **Vidarr** | ᛉ | GPT-5.5 | Subscription | Last resort — GPT-5.5 |
-| **Forseti** | ᚨ | MiniMax-M3 | $0.30/M · $1.20/M out | Adversarial plan reviewer (edit: deny, audit-only) |
+| **Forseti** | ᚨ | OpenRouter minimax-m3 | $0.30/M · $1.20/M out | Adversarial plan reviewer (edit: deny, audit-only) |
 
 ---
 
@@ -257,13 +257,11 @@ After installation, run `/connect` in opencode to add API keys:
 | Provider | Models | Auth |
 |---|---|---|
 | **OpenCode Zen** | `opencode/deepseek-v4-flash-free` | Free API key from [opencode.ai](https://opencode.ai) — create account, get key, no charges |
-| **minimax.io** | `minimax/MiniMax-M2.7`, `minimax/MiniMax-M3` | API key from [minimax.io](https://minimax.io) — **no `baseURL` override** |
+| **OpenRouter** | `openrouter/minimax-m2.7`, `openrouter/minimax-m3` | API key from [openrouter.ai](https://openrouter.ai) |
 | **OpenAI** | `openai/gpt-5.5` | ChatGPT subscription (OAuth) |
 
 Then run `/models` to verify connectivity.
 
-> **Note:** Do not set `baseURL` on the minimax provider. The ai-sdk minimax provider uses its own default URL internally. Setting one causes 404 errors.
-
 ---
 
 ## 🧭 Routing

package/cli/audit.mjs

@@ -78,8 +78,8 @@ export async function runAudit() {
       const model = modelMatch[1].trim();
       const validModels = [
         'opencode/deepseek-v4-flash-free',
-        'minimax/MiniMax-M2.7',
-        'minimax/MiniMax-M3',
+        'openrouter/minimax-m2.7',
+        'openrouter/minimax-m3',
         'openai/gpt-5.5',
       ];
       if (!validModels.includes(model)) {

package/cli/install.mjs

@@ -390,11 +390,12 @@ async function promptAndInstallOptional() {
 }
 
 async function promptGraphifyInstall() {
-  const { spawnSync } = await import('node:child_process');
+  const { spawnSync, execSync } = await import('node:child_process');
 
   console.log();
   sectionHeading('Knowledge Graph (graphify)');
 
+  // 1. Detect graphify already installed
   const detect = spawnSync('python3', ['-c', 'import graphify; print(graphify.__version__)'], {
     cwd: process.cwd(),
     encoding: 'utf8',
@@ -407,40 +408,130 @@ async function promptGraphifyInstall() {
     return;
   }
 
-  // Non-interactive: no TTY means we can't ask, so just print the hint
+  // 2. Non-interactive: print hint and exit
   if (!stdin.isTTY || !stdout.isTTY) {
     console.log(chalk.dim('  graphify not detected. Install later with:'));
+    console.log(chalk.dim('    uv tool install graphifyy   # recommended'));
     console.log(chalk.dim('    pip install graphifyy'));
     console.log(chalk.dim('    pipx install graphifyy'));
-    console.log(chalk.dim('    uv tool install graphifyy'));
     console.log(chalk.dim('  Then run `bizar graph build` to populate .bizar/graph/.'));
     return;
   }
 
+  // 3. Interactive: show options with uv first
   console.log(chalk.dim('  graphify not detected. graphify powers per-project knowledge graphs (bizar graph build).'));
   console.log(chalk.dim('  Install with one of:'));
-  console.log(chalk.dim('    pip install graphifyy       # user-site or venv'));
-  console.log(chalk.dim('    pipx install graphifyy      # isolated CLI tool (recommended on macOS)'));
-  console.log(chalk.dim('    uv tool install graphifyy   # via uv'));
+  console.log(chalk.dim('    uv tool install graphifyy   # recommended'));
+  console.log(chalk.dim('    pip install graphifyy'));
+  console.log(chalk.dim('    pipx install graphifyy'));
 
-  const rl = createInterface({ input: stdin, output: stdout });
-  try {
-    const answer = (await rl.question('  Install graphify now via pip? [Y/n]: ')).trim().toLowerCase();
-    rl.close();
+  const hasUv = await detectUv();
 
-    if (answer === '' || answer.startsWith('y')) {
-      const result = spawnSync('pip', ['install', 'graphifyy'], { stdio: 'inherit', timeout: 120000 });
-      if (result.status === 0) {
-        console.log(chalk.green('  graphify installed. Try: bizar graph build'));
+  if (hasUv) {
+    // 3a. uv is available — ask to install via uv directly
+    const rl = createInterface({ input: stdin, output: stdout });
+    try {
+      const answer = (await rl.question('  Install graphify now via uv? [Y/n]: ')).trim().toLowerCase();
+      rl.close();
+
+      if (answer === '' || answer.startsWith('y')) {
+        console.log('  Installing graphify via uv...');
+        try {
+          execSync('uv tool install graphifyy', { stdio: 'inherit', timeout: 120000 });
+          console.log(chalk.green('  graphify installed. Run `bizar graph build` to populate .bizar/graph/.'));
+        } catch (err) {
+          console.log(chalk.red(`  uv tool install failed: ${err.message}`));
+          console.log(chalk.dim('  Install manually: uv tool install graphifyy'));
+        }
       } else {
-        console.log(chalk.yellow(`  pip install failed (exit ${result.status}). You can install manually later — see options above.`));
+        console.log(chalk.dim('  Skipped. Install manually with one of the commands above when ready.'));
       }
-    } else {
-      console.log(chalk.dim('  Skipped. Install manually with one of the commands above when ready.'));
+    } catch {
+      rl.close();
+      console.log(chalk.dim('  Skipped.'));
+    }
+  } else {
+    // 3b. uv not available — ask if we should install uv first
+    console.log();
+    console.log(chalk.dim('  uv not detected. uv is recommended on Arch/Fedora/macOS (avoids PEP 668).'));
+
+    const rl = createInterface({ input: stdin, output: stdout });
+    try {
+      const answer = (await rl.question('  Install uv first, then graphify? [Y/n]: ')).trim().toLowerCase();
+      rl.close();
+
+      if (answer === '' || answer.startsWith('y')) {
+        if (process.platform === 'win32') {
+          console.log(chalk.yellow('  Automatic uv install not supported on Windows.'));
+          console.log(chalk.dim('  Install from https://docs.astral.sh/uv then run: uv tool install graphifyy'));
+          return;
+        }
+
+        console.log('  Installing uv...');
+        try {
+          execSync('curl -LsSf https://astral.sh/uv/install.sh | sh', { stdio: 'inherit', timeout: 60000 });
+        } catch (err) {
+          console.log(chalk.red(`  uv install failed: ${err.message}`));
+          console.log(chalk.dim('  Install manually from https://docs.astral.sh/uv'));
+          // Fall back to pip
+          const rl2 = createInterface({ input: stdin, output: stdout });
+          try {
+            const pipAnswer = (await rl2.question('  Install graphify via pip instead? [Y/n]: ')).trim().toLowerCase();
+            rl2.close();
+            if (pipAnswer === '' || pipAnswer.startsWith('y')) {
+              console.log('  Installing graphify via pip...');
+              const result = spawnSync('pip', ['install', 'graphifyy'], { stdio: 'inherit', timeout: 120000 });
+              if (result.status === 0) {
+                console.log(chalk.green('  graphify installed. Run `bizar graph build` to populate .bizar/graph/.'));
+              } else {
+                console.log(chalk.red(`  pip install failed (exit ${result.status}).`));
+                console.log(chalk.dim('  Install manually: pip install graphifyy'));
+              }
+            } else {
+              console.log(chalk.dim('  Skipped.'));
+            }
+          } catch {
+            rl2.close();
+            console.log(chalk.dim('  Skipped.'));
+          }
+          return;
+        }
+
+        console.log('  Installing graphify via uv...');
+        try {
+          execSync('uv tool install graphifyy', { stdio: 'inherit', timeout: 120000 });
+          console.log(chalk.green('  graphify installed. Run `bizar graph build` to populate .bizar/graph/.'));
+        } catch (err) {
+          console.log(chalk.red(`  uv tool install failed: ${err.message}`));
+          console.log(chalk.dim('  Install manually: uv tool install graphifyy'));
+        }
+      } else {
+        // User declined uv — fall back to pip
+        const rl2 = createInterface({ input: stdin, output: stdout });
+        try {
+          const pipAnswer = (await rl2.question('  Install graphify via pip instead? [Y/n]: ')).trim().toLowerCase();
+          rl2.close();
+          if (pipAnswer === '' || pipAnswer.startsWith('y')) {
+            console.log('  Installing graphify via pip...');
+            const result = spawnSync('pip', ['install', 'graphifyy'], { stdio: 'inherit', timeout: 120000 });
+            if (result.status === 0) {
+              console.log(chalk.green('  graphify installed. Run `bizar graph build` to populate .bizar/graph/.'));
+            } else {
+              console.log(chalk.red(`  pip install failed (exit ${result.status}).`));
+              console.log(chalk.dim('  Install manually: pip install graphifyy'));
+            }
+          } else {
+            console.log(chalk.dim('  Skipped.'));
+          }
+        } catch {
+          rl2.close();
+          console.log(chalk.dim('  Skipped.'));
+        }
+      }
+    } catch {
+      rl.close();
+      console.log(chalk.dim('  Skipped.'));
     }
-  } catch {
-    rl.close();
-    console.log(chalk.dim('  Skipped.'));
   }
 }
 

package/config/AGENTS.md

@@ -102,6 +102,7 @@ BizarHarness ships always-on coding rules organized by language and concern. All
 | `rules/python.md` | Python conventions |
 | `rules/git.md` | Git and commit conventions |
 | `rules/testing.md` | Test methodology and coverage |
+| `rules/thinking.md` | All agents — concise thinking behavior |
 
 ### How to Use
 
@@ -110,13 +111,17 @@ BizarHarness ships always-on coding rules organized by language and concern. All
 3. All implementation agents (Heimdall, Thor, Tyr, Vidarr) MUST follow these rules
 4. Agents MAY propose additions to the rule files when patterns are discovered
 
+### Thinking Rule
+
+For agents with `reasoning: true` + `variant: "high"`, follow `rules/thinking.md` strictly. Cap reasoning at 2–4 sentences. No informal self-talk, no "what if" loops, no mid-thought self-correction. Think once, decide, act.
+
 ---
 
 ## Model Routing & Agents
 
 This system uses a 5-tier model architecture with a verification gate:
 
-### Odin (default agent, MiniMax-M3)
+### Odin (default agent, OpenRouter minimax-m3)
 
 Odin (`@odin`) is the All-Father and primary/default agent. He analyzes each request and **decomposes it into independent work streams** — **he never executes work himself**:
 - **Identifies parallelizable work** and launches multiple subagent `task` calls in a **single message** (always 2+)
@@ -161,25 +166,25 @@ Odin (`@odin`) is the All-Father and primary/default agent. He analyzes each req
 
 ### Hermod
 
-- **Model**: `minimax/MiniMax-M2.7` (via minimax.io)
+- **Model**: `openrouter/minimax-m2.7` (via OpenRouter)
 - **Use for**: Git and GitHub operations — commit, push, merge, PRs, branches, conflict resolution. The swift messenger.
 - **Cost**: $0.30/M input, $1.20/M output
 
 ### Thor
 
-- **Model**: `minimax/MiniMax-M2.7` (via minimax.io)
+- **Model**: `openrouter/minimax-m2.7` (via OpenRouter)
 - **Use for**: Moderate complexity features, debugging, code review, refactoring
 - **Cost**: $0.30/M input, $1.20/M output — cheaper than Tyr, more capable than Heimdall
 
 ### Baldr
 
-- **Model**: `minimax/MiniMax-M2.7` (via minimax.io)
+- **Model**: `openrouter/minimax-m2.7` (via OpenRouter)
 - **Use for**: Design system creation, DESIGN.md, visual audit, usability planning. Creates design plans — does not implement.
 - **Cost**: $0.30/M input, $1.20/M output
 
 ### Tyr
 
-- **Model**: `minimax/MiniMax-M3` (via minimax.io)
+- **Model**: `openrouter/minimax-m3` (via OpenRouter)
 - **Use for**: Highest complexity implementation, debugging, architecture, multi-step engineering
 - **Cost**: Higher — reserved for the hardest problems
 
@@ -191,7 +196,7 @@ Odin (`@odin`) is the All-Father and primary/default agent. He analyzes each req
 
 ### Forseti
 
-- **Model**: `minimax/MiniMax-M3` (via minimax.io, audit-only, no edit permissions)
+- **Model**: `openrouter/minimax-m3` (via OpenRouter, audit-only, no edit permissions)
 - **Use for**: Adversarial plan review — audits completeness, correctness, consistency, feasibility, security
 - **Always runs before any Tier 4 or Tier 5 implementation begins**
 

package/config/agents/baldr.md

@@ -1,7 +1,7 @@
 ---
 description: Baldr — UI/UX design system specialist. Creates DESIGN.md files using Google's design.md standard (alpha). Focuses on visual consistency, usability, accessibility, and design tokens.
 mode: subagent
-model: minimax/MiniMax-M2.7
+model: openrouter/minimax-m2.7
 color: "#ec4899"
 permission:
   read: allow
@@ -184,6 +184,9 @@ You may be dispatched alongside sibling agents working on the same repository at
 ### Reporting
 End your final summary with: `Siblings: <list>. Conflicts: <list or "none">. Git ops performed: <list or "none">.`
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/forseti.md

@@ -1,7 +1,7 @@
 ---
 description: Forseti — Audits, criticizes, and corrects implementation plans before execution using MiniMax M3. No write permissions — review only.
 mode: subagent
-model: minimax/MiniMax-M3
+model: openrouter/minimax-m3
 color: "#ef4444"
 permission:
   read: allow
@@ -124,6 +124,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be invoked alongside other audit agents (parallel reviews of different files) or alongside implementation agents. The shared `AGENTS.md` baseline rules apply.

package/config/agents/frigg.md

@@ -111,6 +111,10 @@ The injected message you will see is exactly one of:
 - `[loop guard: 8 identical calls to <tool>]. Consider using the task tool to report back to your parent with what you've learned and what you need.`
 - An error containing: `Loop protection: 12 identical calls to <tool>. Use task to escalate.`
 
+
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/heimdall.md

@@ -169,6 +169,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be dispatched alongside sibling agents working on the same repository at the same time. The shared `AGENTS.md` baseline contains the universal rules — read those first. This section adds role-specific guidance.

package/config/agents/hermod.md

@@ -1,7 +1,7 @@
 ---
 description: Hermod — Git and GitHub operations specialist using MiniMax M2.7. Branching, commits, PRs, merge/rebase, conflict resolution, CI/CD, releases, gh CLI.
 mode: subagent
-model: minimax/MiniMax-M2.7
+model: openrouter/minimax-m2.7
 color: "#06b6d4"
 permission:
   read: allow
@@ -144,6 +144,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## PR Review Mode
 
 When dispatched for a `/pr-review`:

package/config/agents/mimir.md

@@ -127,6 +127,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be dispatched alongside sibling agents working on the same repository at the same time. The shared `AGENTS.md` baseline contains the universal rules — read those first. This section adds role-specific guidance.

package/config/agents/odin.md

@@ -1,7 +1,7 @@
 ---
 description: Odin — Pure router that delegates all work to subagents. Routes across Frigg (DeepSeek/Q&A), Vör (DeepSeek/clarify), Mimir (DeepSeek/research), Heimdall (DeepSeek/simple), Hermod (M2.7/git), Thor (M2.7/mid), Baldr (M2.7/design), Tyr (M3/top), Vidarr (GPT-5.5/ultra), Forseti (verifier/M3).
 mode: primary
-model: minimax/MiniMax-M3
+model: openrouter/minimax-m3
 color: "#6366f1"
 permission:
   task: allow
@@ -53,8 +53,8 @@ When you get ANY request:
 4. After all return, synthesize the results
 
 For implementation work, you have two parallel implementation agents:
-- **@thor** (MiniMax-M2.7) — moderate complexity, cheaper
-- **@tyr** (MiniMax-M3) — complex work, more expensive
+- **@thor** (OpenRouter minimax-m2.7) — moderate complexity, cheaper
+- **@tyr** (OpenRouter minimax-m3) — complex work, more expensive
 
 **ALWAYS use both.** Split each implementation task across them. For example:
 - Frontend parts → @thor, Backend parts → @tyr
@@ -100,7 +100,7 @@ For deep codebase research, pattern discovery, documentation analysis:
 ### Simple Tasks & Quick Edits — Route to @heimdall (DeepSeek V4 Flash Free, free)
 For any simple, mechanical, or deterministic work:
 
-### Git Operations — Route to @hermod (MiniMax M2.7 via minimax.io)
+### Git Operations — Route to @hermod (MiniMax M2.7 via OpenRouter)
 For any git or GitHub workflow:
 - Committing, pushing, pulling, branching, merging, rebasing
 - Pull request creation, review, and management
@@ -117,7 +117,7 @@ When the user asks for `@hermod /pr-review` or a PR review:
 2. @hermod waits for both, synthesizes the review, and posts as a PR comment
 3. @hermod has write access to post PR comments via `gh pr comment`
 
-### Design System & Visual Planning — Route to @baldr (MiniMax M2.7 via minimax.io)
+### Design System & Visual Planning — Route to @baldr (MiniMax M2.7 via OpenRouter)
 For any task that touches visuals, usability, or design systems:
 - Creating DESIGN.md files (Google design.md standard — YAML tokens + prose sections)
 - Auditing visual consistency across a codebase (10-dimension scoring)
@@ -129,7 +129,7 @@ For any task that touches visuals, usability, or design systems:
 
 Baldr creates design plans. Baldr does NOT implement code — that goes to @thor or @tyr after the plan is approved.
 
-### Moderate Complexity — Route to @thor (MiniMax M2.7 via minimax.io)
+### Moderate Complexity — Route to @thor (MiniMax M2.7 via OpenRouter)
 For tasks that need more reasoning than DeepSeek but aren't the hardest problems:
 - Implementing new features of moderate complexity
 - Debugging non-trivial issues
@@ -137,7 +137,7 @@ For tasks that need more reasoning than DeepSeek but aren't the hardest problems
 - Writing tests for non-trivial logic
 - Multi-step tasks that are well-scoped and understood
 
-### Complex Work — Route to @tyr (MiniMax M3 via minimax.io)
+### Complex Work — Route to @tyr (MiniMax M3 via OpenRouter)
 For the most demanding engineering work:
 - Complex new feature implementation from scratch
 - Deep debugging of subtle or intermittent bugs
@@ -306,7 +306,7 @@ Call `bizar_spawn_background` with:
 
 - `agent`: the agent name (e.g., "mimir", "thor", "tyr")
 - `prompt`: what to do (specific, with context)
-- `model`: optional, `"<providerID>/<modelID>"` format (e.g., `"minimax/MiniMax-M3"`)
+- `model`: optional, `"<providerID>/<modelID>"` format (e.g., `"openrouter/minimax-m3"`)
 - `timeoutMs`: optional, default 5 min, max 30 min, min 1s
 
 You get an `instanceId` back immediately.

package/config/agents/quick.md

@@ -1,7 +1,7 @@
 ---
 description: Quick (quick) — fast single-shot tasks. No delegation, no parallel streams. Use for small edits, mechanical changes, one-shot questions. Routes to no one.
 mode: primary
-model: minimax/MiniMax-M2.7
+model: openrouter/minimax-m2.7
 color: "#22d3ee"
 permission:
   read: allow
@@ -90,6 +90,10 @@ The injected message you will see is exactly one of:
 - `[loop guard: 8 identical calls to <tool>]. Consider using the task tool to report back to your parent with what you've learned and what you need.`
 - An error containing: `Loop protection: 12 identical calls to <tool>. Use task to escalate.`
 
+
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/semble-search.md

@@ -50,6 +50,9 @@ If `semble` is not on `$PATH`, use `uvx --from "semble[mcp]" semble` in its plac
 
 ---
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Always-On Behavior Baseline
 
 **Follow the global baseline in `config/AGENTS.md` → "General Agent Baseline — Always-On Behavior".** It covers identity, refusal, tone, formatting, lists, user wellbeing, evenhandedness, mistakes, knowledge cutoff and research-first, MCP servers and skills, mandatory skill-read, file creation, file handling, search, copyright, harmful content, citations, images, memory privacy, execution, clarification, and communication.

package/config/agents/thor.md

@@ -1,7 +1,7 @@
 ---
-description: Thor — Handles medium-complexity tasks using MiniMax M2.7 from minimax.io. Strong and reliable, cheaper than Tyr but more capable than Heimdall.
+description: Thor — Handles medium-complexity tasks using MiniMax M2.7 from OpenRouter. Strong and reliable, cheaper than Tyr but more capable than Heimdall.
 mode: subagent
-model: minimax/MiniMax-M2.7
+model: openrouter/minimax-m2.7
 color: "#a855f7"
 permission:
   read: allow
@@ -109,6 +109,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be dispatched alongside sibling agents working on the same repository at the same time. The shared `AGENTS.md` baseline contains the universal rules — read those first. This section adds role-specific guidance.

package/config/agents/tyr.md

@@ -1,7 +1,7 @@
 ---
-description: Tyr — Handles the most complex implementation, debugging, and architectural work using MiniMax M3 via minimax.io. Unmatched wisdom for the hardest problems.
+description: Tyr — Handles the most complex implementation, debugging, and architectural work using MiniMax M3 via OpenRouter. Unmatched wisdom for the hardest problems.
 mode: subagent
-model: minimax/MiniMax-M3
+model: openrouter/minimax-m3
 color: "#f59e0b"
 permission:
   read: allow
@@ -108,6 +108,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be dispatched alongside sibling agents working on the same repository at the same time. The shared `AGENTS.md` baseline contains the universal rules — read those first. This section adds role-specific guidance.

package/config/agents/vidarr.md

@@ -112,6 +112,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ## Parallel Execution
 
 You may be dispatched alongside sibling agents working on the same repository at the same time. The shared `AGENTS.md` baseline contains the universal rules — read those first. This section adds role-specific guidance.

package/config/agents/vor.md

@@ -150,6 +150,9 @@ Be professional and concise. Do not write long essays for every action.
 - One sentence of context beats three paragraphs of preamble.
 - Match the user's register: if they write briefly, reply briefly. If they want depth, they will ask.
 
+## Thinking style
+Follow `config/rules/thinking.md` strictly. Be precise, concise, and decisive in reasoning. No informal self-talk, no "what if" loops, no mid-thought self-correction.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/opencode.json

@@ -334,5 +334,35 @@
       "template": "commands/bizar.md",
       "arguments": "$ARGUMENTS"
     }
+  },
+  "provider": {
+    "minimax": {
+      "models": {
+        "MiniMax-M3": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "MiniMax-M2.7": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        }
+      }
+    },
+    "openrouter": {
+      "models": {
+        "minimax/minimax-m3": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "minimax/minimax-m2.7": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "minimax/owl-alpha": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        }
+      }
+    }
   }
 }

package/config/opencode.json.template

@@ -1,10 +1,23 @@
 {
   "$schema": "https://opencode.ai/config.json",
-  "model": "minimax/MiniMax-M3",
-  "small_model": "minimax/MiniMax-M2.7",
+  "model": "openrouter/minimax-m3",
+  "small_model": "openrouter/minimax-m2.7",
   "default_agent": "odin",
   "permission": "allow",
   "snapshot": false,
+  "provider": {
+    "openrouter": {
+      "npm": "@openrouter/ai-sdk-provider",
+      "name": "OpenRouter",
+      "options": {
+        "apiKey": "{env:OPENROUTER_API_KEY}"
+      },
+      "models": {
+        "minimax-m2.7": {},
+        "minimax-m3": {}
+      }
+    }
+  },
   "mcp": {
     "supabase": {
       "type": "remote",
@@ -53,7 +66,7 @@
     "odin": {
       "description": "Odin — Pure router that delegates all work to subagents.",
       "mode": "primary",
-      "model": "minimax/MiniMax-M3",
+      "model": "openrouter/minimax-m3",
       "color": "#6366f1",
       "permission": {
         "task": "allow",
@@ -67,7 +80,7 @@
     "vor": {
       "description": "Vör — The Questioning One.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#8b5cf6",
       "permission": {
         "read": "allow",
@@ -80,7 +93,7 @@
     "frigg": {
       "description": "Frigg — All-knowing Q&A agent.",
       "mode": "primary",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#06b6d4",
       "permission": {
         "read": "allow",
@@ -98,7 +111,7 @@
     "quick": {
       "description": "Quick — Fast single-shot tasks.",
       "mode": "primary",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#22d3ee",
       "permission": {
         "read": "allow",
@@ -117,7 +130,7 @@
     "mimir": {
       "description": "Mimir — Research and codebase exploration agent.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#0ea5e9",
       "permission": {
         "read": "allow",
@@ -135,7 +148,7 @@
     "heimdall": {
       "description": "Heimdall — Simple, routine, deterministic tasks.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#10b981",
       "permission": {
         "read": "allow",
@@ -152,7 +165,7 @@
     "hermod": {
       "description": "Hermod — Git and GitHub operations specialist.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#06b6d4",
       "permission": {
         "read": "allow",
@@ -168,7 +181,7 @@
     "thor": {
       "description": "Thor — Medium-complexity tasks, strong and reliable.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#a855f7",
       "permission": {
         "read": "allow",
@@ -185,7 +198,7 @@
     "baldr": {
       "description": "Baldr — UI/UX design system specialist.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax-m2.7",
       "color": "#ec4899",
       "permission": {
         "read": "allow",
@@ -202,7 +215,7 @@
     "tyr": {
       "description": "Tyr — Complex implementation, debugging, architecture.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M3",
+      "model": "openrouter/minimax-m3",
       "color": "#f59e0b",
       "permission": {
         "read": "allow",
@@ -236,7 +249,7 @@
     "forseti": {
       "description": "Forseti — Audits and corrects plans before execution.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M3",
+      "model": "openrouter/minimax-m3",
       "color": "#ef4444",
       "permission": {
         "read": "allow",
@@ -306,5 +319,35 @@
       "agent": "odin",
       "template": "commands-bizar/bizar.md\n\n$ARGUMENTS"
     }
+  },
+  "provider": {
+    "minimax": {
+      "models": {
+        "MiniMax-M3": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "MiniMax-M2.7": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        }
+      }
+    },
+    "openrouter": {
+      "models": {
+        "minimax/minimax-m3": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "minimax/minimax-m2.7": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        },
+        "minimax/owl-alpha": {
+          "interleaved": { "field": "reasoning_details" },
+          "reasoning": true
+        }
+      }
+    }
   }
 }

package/config/rules/thinking.md

@@ -0,0 +1,56 @@
+# Concise Thinking Rule
+
+## The Problem
+
+Models with `reasoning: true` + `variant: "high"` produce unbounded self-talk: "oh but what if this... actually let me reconsider... wait..." This is verbose, indecisive, and costly.
+
+## The Rule
+
+**Think in 2–4 sentences. One-shot. No loops.**
+
+### Structure
+
+Every reasoning output must follow this shape:
+
+```
+[Premise — what I know] → [Decision — what I'm doing] → [Next step]
+```
+
+No hedging. No "but what if". No mid-thought self-correction.
+
+### Hard Bans
+
+Never use these phrases in thinking output:
+- "oh but what if..."
+- "actually..."
+- "let me think..."
+- "wait..."
+- "hmm..."
+- "I wonder..."
+- "on second thought..."
+- "alternatively..."
+
+### One-Shot Pattern
+
+Think once. Decide. Act. Move on.
+
+**Forbidden patterns:**
+- "Option A... no wait Option B... actually let's try C..."
+- "I considered X, but then I realized Y, so maybe Z..."
+- "Let me reconsider..." followed by another reconsideration
+
+### What Thinking Should Look Like
+
+**BAD:**
+> "The file is missing a semicolon. Oh but what if it's actually a parsing issue? Let me think... Actually, looking more carefully, the real problem is the import statement is wrong. Wait, I should also check if the export is correct. Actually let me try fixing the import first..."
+
+**GOOD:**
+> "The import path is wrong — `../utils` should be `./utils`. Fixing the path resolves the missing export error. Next: re-run the build."
+
+### Length Cap
+
+Maximum **80 words** of thinking output before the first tool call or response. If you cannot decide in 80 words, state the decision you reached and proceed.
+
+### Enforcement
+
+This rule is injected into every model that supports `reasoning: true`. Non-compliance produces verbose, unhelpful output and is a correctness failure.

package/config/skills/bizar/SKILL.md

@@ -26,14 +26,14 @@ All subagents use Hindsight memory with **per-project banks**. Call `hindsight_l
 
 | Agent | Model | Tier | Cost | When to Route |
 |---|---|---|---|---|
-| **Odin** ᛟ | MiniMax-M3 | Router | $0.30/M · $1.20/M out | Primary entry point. Decomposes and dispatches. |
+| **Odin** ᛟ | OpenRouter minimax-m3 | Router | $0.30/M · $1.20/M out | Primary entry point. Decomposes and dispatches. |
 | **Mimir** ᛗ | DeepSeek V4 Flash | Free | **$0** | Deep codebase research, Semble-first exploration, docs analysis |
 | **Heimdall** ᚹ | DeepSeek V4 Flash | Free | **$0** | Simple edits, file ops, mechanical CRUD, quick answers |
-| **Hermod** ᚱ | MiniMax-M2.7 | Mid | $0.30/M · $1.20/M out | Git ops: commit, push, PR, merge, rebase, branches, `gh` CLI |
-| **Thor** ᚦ | MiniMax-M2.7 | Mid | $0.30/M · $1.20/M out | Moderate implementation, tests, debugging, refactoring |
-| **Tyr** ᛏ | MiniMax-M3 | High | $0.30/M · $1.20/M out | Complex features, architecture, deep debugging, cross-cutting refactor |
+| **Hermod** ᚱ | OpenRouter minimax-m2.7 | Mid | $0.30/M · $1.20/M out | Git ops: commit, push, PR, merge, rebase, branches, `gh` CLI |
+| **Thor** ᚦ | OpenRouter minimax-m2.7 | Mid | $0.30/M · $1.20/M out | Moderate implementation, tests, debugging, refactoring |
+| **Tyr** ᛏ | OpenRouter minimax-m3 | High | $0.30/M · $1.20/M out | Complex features, architecture, deep debugging, cross-cutting refactor |
 | **Vidarr** ᛉ | GPT-5.5 | Ultra | ChatGPT sub | Last resort when Tyr fails or debugging is stuck |
-| **Forseti** ᚨ | MiniMax-M3 | Gate | $0.30/M · $1.20/M out | Plan auditor — reviews Tyr/Vidarr plans before execution. `edit: deny`. |
+| **Forseti** ᚨ | OpenRouter minimax-m3 | Gate | $0.30/M · $1.20/M out | Plan auditor — reviews Tyr/Vidarr plans before execution. `edit: deny`. |
 | **Semble** | — | — | **$0** | MCP search tool, not an agent. Semble-first code search. |
 
 ## Odin Routing Rules
@@ -98,19 +98,19 @@ permission:
 
 **Fix:** Check `~/.config/opencode/agents/<name>.md` for the `model:` field. Valid models:
 - `opencode/deepseek-v4-flash-free` — free
-- `minimax/MiniMax-M2.7` — M2.7 (capital M in model ID)
-- `minimax/MiniMax-M3` — M3 (capital M in model ID)
+- `openrouter/minimax-m2.7` — M2.7
+- `openrouter/minimax-m3` — M3
 - `openai/gpt-5.5` — GPT-5.5
 
-### Minimax 404 Errors
+### OpenRouter 404 Errors
 
-**Symptoms:** 404 errors when calling minimax models.
+**Symptoms:** 404 errors when calling the OpenRouter-hosted MiniMax models.
 
-**Cause:** A `baseURL: "https://api.minimax.io/v1"` was set in the provider config, which conflicts with the ai-sdk minimax provider's internal URL construction.
+**Cause:** A `baseURL` was set on the `openrouter` provider in `opencode.json`, which conflicts with the `@openrouter/ai-sdk-provider`'s built-in URL construction.
 
-**Fix:** Remove any `baseURL` from the minimax provider section. The minimax API key in `auth.json` is sufficient. Example fix:
+**Fix:** Remove any `baseURL` from the openrouter provider section. OpenRouter's URL is built into the SDK. Example fix:
 ```diff
-- "baseURL": "https://api.minimax.io/v1"
+- "baseURL": "https://openrouter.ai/api/v1"
 ```
 The provider uses the correct default URL internally.
 
@@ -132,7 +132,7 @@ The provider uses the correct default URL internally.
 
 | File | Purpose |
 |---|---|
-| `~/.config/opencode/opencode.json` | Main config (no minimax baseURL) |
+| `~/.config/opencode/opencode.json` | Main config (no openrouter baseURL) |
 | `~/.config/opencode/AGENTS.md` | Routing table and conventions |
 | `~/.config/opencode/agents/odin.md` | Primary router agent |
 | `~/.config/opencode/agents/mimir.md` | Research agent |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@polderlabs/bizar",
-  "version": "3.8.0",
+  "version": "3.9.1",
   "description": "Norse-pantheon multi-agent system for opencode — 13 agents across 4 cost tiers with cost-aware routing, plans, and a configurable agent harness.",
   "type": "module",
   "bin": {
@@ -42,5 +42,13 @@
   },
   "devDependencies": {
     "typescript": "^5.0.0"
-  }
+  },
+  "repository": {
+    "type": "git",
+    "url": "git@github.com:DrB0rk/BizarHarness.git"
+  },
+  "bugs": {
+    "url": "https://github.com/DrB0rk/BizarHarness/issues"
+  },
+  "homepage": "https://github.com/DrB0rk/BizarHarness#readme"
 }