@polderlabs/bizar 3.10.0 → 3.11.1

package/cli/graph.mjs

@@ -150,13 +150,39 @@ function ensureGitignore(graphDir) {
 /**
  * Spawn a graphify command with GRAPHIFY_OUT set to GRAPH_DIR.
  * Streams stdout/stderr to the terminal. Returns the exit code.
+ *
+ * Resolution order:
+ *   1. If the `graphify` binary is on PATH (the uv-tool shim), invoke it
+ *      directly. This is what `checkGraphify` already verified — we don't
+ *      need to know about its venv.
+ *   2. Otherwise fall back to `python -m graphify` for pip/pipx installs.
  */
 function runGraphify(python, subArgs, extraEnv = {}) {
-  const env = { ...process.env, [GRAPHIFY_OUT_ENV]: GRAPH_DIR };
+  const env = { ...process.env, [GRAPHIFY_OUT_ENV]: GRAPH_DIR, ...extraEnv };
+  const whichCmd = process.platform === 'win32' ? 'where' : 'which';
+  let bin = null;
+  try {
+    const r = spawnSync(whichCmd, ['graphify'], { encoding: 'utf8', timeout: 5000 });
+    if (r.status === 0 && (r.stdout || '').trim().length > 0) {
+      bin = 'graphify';
+    }
+  } catch {
+    // ignore — fall through to python -m
+  }
+
+  if (bin) {
+    const result = spawnSync(bin, subArgs, {
+      stdio: 'inherit',
+      env,
+      timeout: 0, // no timeout — user may run long builds
+    });
+    return result.status ?? 1;
+  }
+
   const result = spawnSync(python, ['-m', 'graphify', ...subArgs], {
     stdio: 'inherit',
     env,
-    timeout: 0, // no timeout — user may run long builds
+    timeout: 0,
   });
   return result.status ?? 1;
 }

package/config/agents/baldr.md

@@ -187,6 +187,8 @@ End your final summary with: `Siblings: <list>. Conflicts: <list or "none">. Git
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/forseti.md

@@ -127,6 +127,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -115,6 +115,8 @@ The injected message you will see is exactly one of:
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/heimdall.md

@@ -172,6 +172,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -147,6 +147,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## PR Review Mode
 
 When dispatched for a `/pr-review`:

package/config/agents/mimir.md

@@ -130,6 +130,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -368,6 +368,11 @@ You are the All-Father. Concise by default, but you are permitted dry humor, a w
 - Match the user's register: terse when they're terse, thorough when they want depth.
 - When delegating, be specific about what you want. Other agents follow your instructions literally.
 
+## 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.
+
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/quick.md

@@ -94,6 +94,8 @@ The injected message you will see is exactly one of:
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/agents/semble-search.md

@@ -53,6 +53,8 @@ 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -112,6 +112,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -111,6 +111,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -115,6 +115,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ## 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

@@ -153,6 +153,8 @@ Be professional and concise. Do not write long essays for every action.
 ## 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.
 
+When uncertain or stuck, follow `config/rules/uncertainty.md` — stop and research, do not keep retrying variations.
+
 ---
 
 ## Always-On Behavior Baseline

package/config/opencode.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://opencode.ai/config.json",
-  "model": "minimax/MiniMax-M3",
-  "small_model": "minimax/MiniMax-M2.7",
+  "model": "openrouter/minimax/minimax-m3",
+  "small_model": "openrouter/minimax/minimax-m2.7",
   "default_agent": "odin",
   "permission": "allow",
   "snapshot": false,
@@ -53,7 +53,7 @@
     "odin": {
       "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/minimax-m3",
       "color": "#6366f1",
       "permission": {
         "task": "allow",
@@ -102,7 +102,7 @@
     "quick": {
       "description": "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/minimax-m2.7",
       "color": "#22d3ee",
       "permission": {
         "read": "allow",
@@ -162,7 +162,7 @@
     "hermod": {
       "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/minimax-m2.7",
       "color": "#06b6d4",
       "permission": {
         "read": "allow",
@@ -180,7 +180,7 @@
     "thor": {
       "description": "Thor — Handles medium-complexity tasks using MiniMax M2.7 from minimax.io. Strong and reliable, cheaper than Tyr but more capable than Heimdall.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax/minimax-m2.7",
       "color": "#a855f7",
       "permission": {
         "read": "allow",
@@ -199,7 +199,7 @@
     "baldr": {
       "description": "Baldr — UI/UX design system specialist. Creates DESIGN.md files using Google's design.md standard. Focuses on visual consistency, usability, accessibility, and design tokens.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M2.7",
+      "model": "openrouter/minimax/minimax-m2.7",
       "color": "#ec4899",
       "permission": {
         "read": "allow",
@@ -218,7 +218,7 @@
     "tyr": {
       "description": "Tyr — Handles the most complex implementation, debugging, and architectural work using MiniMax M3 via minimax.io. Unmatched wisdom for the hardest problems.",
       "mode": "subagent",
-      "model": "minimax/MiniMax-M3",
+      "model": "openrouter/minimax/minimax-m3",
       "color": "#f59e0b",
       "permission": {
         "read": "allow",
@@ -256,7 +256,7 @@
     "forseti": {
       "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/minimax-m3",
       "color": "#ef4444",
       "permission": {
         "read": "allow",
@@ -357,10 +357,6 @@
         "minimax/minimax-m2.7": {
           "interleaved": { "field": "reasoning_details" },
           "reasoning": true
-        },
-        "minimax/owl-alpha": {
-          "interleaved": { "field": "reasoning_details" },
-          "reasoning": true
         }
       }
     }

package/config/opencode.json.template

@@ -342,10 +342,6 @@
         "minimax/minimax-m2.7": {
           "interleaved": { "field": "reasoning_details" },
           "reasoning": true
-        },
-        "minimax/owl-alpha": {
-          "interleaved": { "field": "reasoning_details" },
-          "reasoning": true
         }
       }
     }

package/config/rules/uncertainty.md

@@ -0,0 +1,70 @@
+# Stop and Research Rule
+
+## The Problem
+
+LLM agents default to a "try again with a slight variation" loop when they are uncertain. They guess file paths, invent API names, mutate code they do not understand, and burn tokens retrying near-identical tool calls. The fix is always available: stop, use a research tool, learn something, then act.
+
+## The Rule
+
+**When uncertain or stuck, STOP. Research. Then act.**
+
+### The Three Phases
+
+Every stuck situation must move through these phases in order:
+
+1. **Attempt (max 2 tries).** Try your best guess once or twice. If both fail or you are not confident in the result, stop. Do not attempt a third variation.
+2. **Research (mandatory before retry #3).** Use the available tools to learn:
+   - `semble search "<concept>"` for codebase patterns
+   - `webfetch` for official documentation
+   - `read` for related files in the repo
+   - `hindsight_recall` for prior project context
+   - `skill <name>` for domain-specific guidance
+   - Ask the user if you are still uncertain after research
+3. **Act with confidence.** After research, make one decisive attempt. If it still fails, return to phase 2 with the new information. Never return to phase 1.
+
+### Recognition Triggers
+
+You are stuck if any of these are true:
+
+- You are about to make the same tool call with slightly different arguments
+- You do not know which file contains the relevant code
+- The error message is unfamiliar
+- The user gave a goal but no clear path
+- You are guessing at API signatures, config keys, or command syntax
+- Multiple valid approaches exist and you do not know which is correct
+- Your previous two attempts produced the same outcome
+
+### Hard Bans
+
+Never do any of the following:
+
+- Try the same approach 3 or more times. Research after the second failure.
+- Guess at file paths without searching
+- Invent API names, method signatures, or config keys
+- Modify code you do not understand
+- Continue a plan after the user has corrected you
+- Pretend to be making progress when you are actually looping
+
+### Examples
+
+**BAD:** Agent needs to call the project's authentication helper.
+> "Let me try `auth.login()`. Nope, not exported. Maybe `auth.signIn()`? No. Try `authenticate()`? Hmm. Let me look for `Login`... `User.auth()`? Actually let me try `userLogin()`..."
+
+**GOOD:** Agent needs to call the project's authentication helper.
+> Searched the codebase: `semble search "authentication helper"` returned `src/auth/session.ts` exporting `createSession()`. Calling `createSession({ userId })` next.
+
+**BAD:** Agent is debugging a build failure.
+> "Error: ENOENT: no such file. Let me try creating `./config.json`. Failed. Try `./src/config.json`. Failed. Try `./app/config.json`. Failed. Let me try `process.cwd()`..."
+
+**GOOD:** Agent is debugging a build failure.
+> `semble search "config path"` and `read package.json` both show configs live in `config/`. The build script runs from the repo root, so the path is `config/<name>.json`. Fixing the import next.
+
+### Loop Guard Is The Last Resort
+
+The runtime loop guard in `opencode.json` (`loopThresholdWarn: 5`, `loopThresholdEscalate: 8`, `loopThresholdBlock: 12`) is a safety net for when this rule fails. It is not the primary defense.
+
+If the loop guard fires, the rule failed first. Agents must self-correct before the guard kicks in. A trigger at 5 identical calls means the agent should have stopped at 2 and researched.
+
+## Enforcement
+
+Non-compliance looks like: 3+ similar tool calls in a row, repeated variations of the same failed command, "let me try X... nope... let me try Y..." narration, and increasing token spend with no progress. If you catch yourself doing this, stop, run a research tool, and act on the result.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@polderlabs/bizar",
-  "version": "3.10.0",
+  "version": "3.11.1",
   "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": {
@@ -33,7 +33,7 @@
     "ora": "^8.1.0"
   },
   "peerDependencies": {
-    "@polderlabs/bizar-dash": ">=3.0.0"
+    "@polderlabs/bizar-dash": "^3.10.0"
   },
   "peerDependenciesMeta": {
     "@polderlabs/bizar-dash": {
@@ -45,7 +45,7 @@
   },
   "repository": {
     "type": "git",
-    "url": "git@github.com:DrB0rk/BizarHarness.git"
+    "url": "git+ssh://git@github.com/DrB0rk/BizarHarness.git"
   },
   "bugs": {
     "url": "https://github.com/DrB0rk/BizarHarness/issues"