opencode-harness-kit 0.6.0 → 0.6.1

package/CHANGELOG.md

@@ -12,8 +12,6 @@ is not happening.
 
 ---
 
-## [Unreleased]
-
 ## [0.6.0] — 2026-10-22
 
 Published. The tag is what cut it: `git tag v0.6.0 && git push origin

package/README.md

@@ -107,7 +107,7 @@ about your prompts.
 
 | lane | job | model | measured |
 |---|---|---|---|
-| `build` | write and verify the change | MiniMax M3.1 Flash | 6.9 s |
+| `build` | write and verify the change | Flint 40B Free | 6.9 s |
 | `plan` | turn a request into a plan | Beam | **6.1 s** |
 | `reviewer` | read a change in two passes | Nemotron 3 Ultra | 7.8 s (34 s cold) |
 | `locate` | find where something lives | Nemotron 3.5 Lightning | 6.9 s |
@@ -116,13 +116,14 @@ about your prompts.
 | `doc` | read a long document or a spec | GLM 5.3 Flash | 7.4 s |
 | `schema` | produce JSON or a JSON schema | DeepSeek V4.1 Flash | 10.7 s |
 | `sweep` | sweep a lot of code mechanically | Nemotron 3.5 Super VL | 8.4 s |
-| `longform` | read a megabyte, or write alternatives | MiniMax M3.1 Flash | 6.9 s |
+| `longform` | read a megabyte, or write alternatives | Flint 40B Free | 6.9 s |
 
 `longform` used to run on `longcat-2.5-preview-free`, and the provider
 withdrew it. A withdrawn model is not a lane, it is a hole in a lane: the
-route falls to the next rung of the same chain, which is MiniMax - the only
-model left on the tier with a million-token context. The `measured` column
-for that lane is therefore MiniMax's, not the withdrawn model's.
+route falls to the next rung of the same chain, where MiniMax then flint
+carried the lane - flint is the model that replaced MiniMax on the tier, and
+the only one left with the context the lane exists for. The `measured`
+column for that lane is therefore flint's, not either withdrawn model's.
 
 The `measured` column is the median of five one-line requests to that model
 on 2026-10-21 - the same prompt for every model, from the process start, so
@@ -243,7 +244,7 @@ it. One file covers ten jobs either way.
 |---|---|---|---|---|
 | `fleet-safe` (default) | 10 | 200,000 | `max` | zero-retention |
 | `fleet-all` | 10 | 160,000 | `max` | **may train** |
-| `minimax-m3.1-flash-free` | 5 | 1,000,000 | `max` | zero-retention |
+| `flint-40b-free` | 5 | 262,144 | `max` | **may train** |
 | `beam-free` | 5 | 1,048,576 | `max` | retained |
 | `deepseek-v4.1-flash-free` | 5 | 200,000 | `max` | zero-retention |
 | `glm-5.3-flash-free` | 5 | 200,000 | `max` | zero-retention |
@@ -252,6 +253,7 @@ it. One file covers ten jobs either way.
 | `nemotron-3.5-lightning-free` | 5 | 262,144 | — | **may train** |
 | `mimo-v2.6-flash-free` | 5 | 200,000 | — | **may train** |
 | `big-pickle` | 5 | 160,000 | — | **may train** |
+| `flint-40b-free` | 5 | 262,144 | `max` | **may train** |
 
 The five-lane profiles run everything on one model, which is the right shape
 when you want one route and want to know exactly which one.
@@ -282,6 +284,8 @@ withdrawn, and one of them was the **default** at the time:
 | `deepseek-v4-flash-free` | Withdrawn within a month. Replaced by `deepseek-v4.1-flash-free`. |
 | `muse-spark-1.3-contributor-free` | A Meta contributor route whose provider was permitted to train on prompts. The paid route is still in the catalogue. |
 | `mimo-v2.5-free` | Observed alive for one day. Replaced by `mimo-v2.6-flash-free`. |
+| `longcat-2.5-preview-free` | Was the `longform` lane's primary in both fleets, so when it was pulled every lane fell back a rung, and the one profile built only for that model was retired. |
+| `minimax-m3.1-flash-free` | Deprecated by the provider and replaced on the tier by `flint-40b-free`, which is the build and `longform` lane today. |
 
 The full list, with a reason for each, is in
 [`profiles/index.json`](profiles/index.json).

package/bin/oc-harness.mjs

@@ -12,7 +12,7 @@
 // The point of the kit: switching models is a data edit, not a code change.
 // Everything model-specific lives in profiles/<id>.json.
 
-import { chmodSync, copyFileSync, mkdirSync, readFileSync, writeFileSync, existsSync, rmSync, symlinkSync, readdirSync, readlinkSync, realpathSync, lstatSync, appendFileSync } from "node:fs"
+import { chmodSync, copyFileSync, mkdirSync, readFileSync, writeFileSync, existsSync, rmSync, symlinkSync, readdirSync, readlinkSync, realpathSync, lstatSync, appendFileSync, renameSync, unlinkSync } from "node:fs"
 import { homedir } from "node:os"
 import { basename, dirname, isAbsolute, join, relative, resolve, sep } from "node:path"
 import { execFileSync } from "node:child_process"
@@ -1539,7 +1539,7 @@ async function cmdUse(id) {
 
   mkdirSync(dirname(CONFIG_FILE), { recursive: true })
   if (existsSync(CONFIG_FILE)) {
-// The config is the user's file once written. The backup is unconditional:
+    // The config is the user's file once written. The backup is unconditional:
     // `--yes` skips the question, it does not skip the safety net. Gating the
     // backup on `--yes` meant the one path that overwrites without asking was
     // also the one path with nothing to fall back to.
@@ -1560,7 +1560,15 @@ async function cmdUse(id) {
       stamp(`  existing config backed up to ${join(BACKUP_DIR, kept)}`),
     )
   }
-  writeFileSync(CONFIG_FILE, out)
+  // Write atomically to avoid truncating/corrupting the config on crash.
+  const tmp = `${CONFIG_FILE}.${process.pid}.${Date.now()}.tmp`
+  try {
+    writeFileSync(tmp, out)
+    renameSync(tmp, CONFIG_FILE)
+  } catch (err) {
+    try { unlinkSync(tmp) } catch {}
+    throw err
+  }
   console.log(`\n  ${green("✓")} wrote ${CONFIG_FILE}`)
   summary(p)
   console.log(`\n  ${stamp("verify with: opencode debug config")}\n`)

package/dist/index.js

@@ -1932,7 +1932,7 @@ function utilityModel(p) {
 }
 
 // src/health.js
-import { existsSync as existsSync5, mkdirSync as mkdirSync2, readFileSync as readFileSync3, writeFileSync } from "node:fs";
+import { existsSync as existsSync5, mkdirSync as mkdirSync2, readFileSync as readFileSync3, renameSync as renameSync2, unlinkSync, writeFileSync } from "node:fs";
 import { join as join7 } from "node:path";
 var DEFAULT_WINDOW_MS = 24 * 60 * 60 * 1e3;
 function spentWindowMs() {
@@ -1983,9 +1983,21 @@ function readHealth(dir) {
 }
 function writeHealth(dir, health) {
   try {
-    if (!existsSync5(join7(dir, ".space"))) mkdirSync2(join7(dir, ".space"), { recursive: true });
+    const spaceDir = join7(dir, ".space");
+    if (!existsSync5(spaceDir)) mkdirSync2(spaceDir, { recursive: true });
     const pruned = { ...health ?? {}, unhealthy: liveUnhealthy(health) };
-    writeFileSync(healthPath(dir), JSON.stringify(pruned, null, 2));
+    const file = healthPath(dir);
+    const tmp = `${file}.${process.pid}.${Date.now()}.tmp`;
+    try {
+      writeFileSync(tmp, JSON.stringify(pruned, null, 2));
+      renameSync2(tmp, file);
+    } catch (err) {
+      try {
+        unlinkSync(tmp);
+      } catch {
+      }
+      throw err;
+    }
   } catch {
   }
 }

package/eval/ab.mjs

@@ -750,7 +750,7 @@ console.log("")
 console.log(`  ${"metric (median)".padEnd(16)} ${"kit on".padStart(10)} ${"kit off".padStart(10)}`)
 console.log(`  ${"-".repeat(16)} ${"-".repeat(10)} ${"-".repeat(10)}`)
 for (const [label, a, b] of rows) {
-  console.log(`  ${label.padEnd(16)} ${String(a).padStart(10)} ${String(b).padStart(10)}`)
+  console.log(`  ${String(label).padEnd(16)} ${String(a).padStart(10)} ${String(b).padStart(10)}`)
 }
 
 if (jobs.length > 1) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-harness-kit",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Harness kit for OpenCode: capability profiles, a fleet of job lanes with one free model each, role-based reasoning effort, context pruning, and measured baselines.",
   "license": "MIT",
   "homepage": "https://github.com/pham-canh/opencode-harness-kit#readme",

package/profiles/fleet-all.json

@@ -3,15 +3,15 @@
   "id": "fleet-all",
   "title": "Ten jobs, every free model, one of them may train",
   "provider": "opencode",
-  "model": "minimax-m3.1-flash-free",
-  "family": null,
+  "model": "flint-40b-free",
+  "family": "flint",
   "verified": "2026-10-22",
   "retention": "may-train",
   "maxRetention": "may-train",
   "notes": "Every lane gets the model built for it: beam plans, Nemotron 3 Ultra reviews, Lightning sweeps, MiMo sees, GLM audits, Super VL reasons with the effort turned off. Five of the ten providers state that collected data may be used to improve the model, or log the session, so the profile as a whole is may-train and the generated config says so in its header. Install it for public or throwaway repositories.",
   "limits": {
-    "context": 1000000,
-    "output": 512000
+    "context": 262144,
+    "output": 65536
   },
   "supports": {
     "reasoning": true,
@@ -49,9 +49,9 @@
   },
   "roleModels": {
     "build": {
-      "model": "minimax-m3.1-flash-free",
+      "model": "flint-40b-free",
       "chain": [
-        "minimax-m3.1-flash-free",
+        "flint-40b-free",
         "deepseek-v4.1-flash-free"
       ]
     },
@@ -90,7 +90,7 @@
       "model": "mimo-v2.6-flash-free",
       "chain": [
         "mimo-v2.6-flash-free",
-        "minimax-m3.1-flash-free"
+        "deepseek-v4.1-flash-free"
       ]
     },
     "doc": {
@@ -116,9 +116,9 @@
       ]
     },
     "longform": {
-      "model": "minimax-m3.1-flash-free",
+      "model": "flint-40b-free",
       "chain": [
-        "minimax-m3.1-flash-free",
+        "flint-40b-free",
         "beam-free"
       ]
     }
@@ -130,7 +130,7 @@
     "keepUserMessages": true
   },
   "fallback": [
-    "minimax-m3.1-flash-free",
+    "flint-40b-free",
     "deepseek-v4.1-flash-free"
   ]
 }

package/profiles/fleet-safe.json

@@ -3,15 +3,15 @@
   "id": "fleet-safe",
   "title": "Ten jobs, zero-retention models only",
   "provider": "opencode",
-  "model": "minimax-m3.1-flash-free",
-  "family": null,
+  "model": "deepseek-v4.1-flash-free",
+  "family": "deepseek",
   "verified": "2026-10-22",
   "retention": "zero-retention",
   "maxRetention": "zero-retention",
-  "notes": "The default. Every lane resolves to a model whose provider states a zero-retention policy: no training, nothing kept. The cost is that six of the ten jobs run on a second-choice model - the planner loses beam (30-day retention) and the reviewer loses Nemotron 3 Ultra - so this is the floor, not the ceiling. The chains are ordered within the ceiling rather than copied from `fleet-all`: `locate` takes deepseek because it publishes a `low` effort level that longcat does not, and `vision` takes minimax because it reads an image in 7 seconds. `fleet-all` gives every lane the model built for it.",
+  "notes": "The default. Every lane resolves to a model whose provider states a zero-retention policy: no training, nothing kept. The cost is that six of the ten jobs run on a second-choice model - the planner loses beam (30-day retention) and the reviewer loses Nemotron 3 Ultra - so this is the floor, not the ceiling. The chains are ordered within the ceiling rather than copied from `fleet-all`: `locate` takes deepseek because it publishes a `low` effort level that longcat does not, and `vision` takes deepseek because it is the zero-retention route the provider kept for image reads. `fleet-all` gives every lane the model built for it.",
   "limits": {
-    "context": 1000000,
-    "output": 512000
+    "context": 200000,
+    "output": 32000
   },
   "supports": {
     "reasoning": true,
@@ -49,10 +49,10 @@
   },
   "roleModels": {
     "build": {
-      "model": "minimax-m3.1-flash-free",
+      "model": "deepseek-v4.1-flash-free",
       "chain": [
-        "minimax-m3.1-flash-free",
-        "deepseek-v4.1-flash-free"
+        "deepseek-v4.1-flash-free",
+        "glm-5.3-flash-free"
       ]
     },
     "plan": {
@@ -73,7 +73,7 @@
       "model": "deepseek-v4.1-flash-free",
       "chain": [
         "deepseek-v4.1-flash-free",
-        "minimax-m3.1-flash-free"
+        "glm-5.3-flash-free"
       ]
     },
     "verify": {
@@ -84,10 +84,10 @@
       ]
     },
     "vision": {
-      "model": "minimax-m3.1-flash-free",
+      "model": "deepseek-v4.1-flash-free",
       "chain": [
-        "minimax-m3.1-flash-free",
-        "deepseek-v4.1-flash-free"
+        "deepseek-v4.1-flash-free",
+        "glm-5.3-flash-free"
       ]
     },
     "doc": {
@@ -108,14 +108,14 @@
       "model": "deepseek-v4.1-flash-free",
       "chain": [
         "deepseek-v4.1-flash-free",
-        "minimax-m3.1-flash-free"
+        "glm-5.3-flash-free"
       ]
     },
     "longform": {
-      "model": "minimax-m3.1-flash-free",
+      "model": "deepseek-v4.1-flash-free",
       "chain": [
-        "minimax-m3.1-flash-free",
-        "deepseek-v4.1-flash-free"
+        "deepseek-v4.1-flash-free",
+        "glm-5.3-flash-free"
       ]
     }
   },

package/profiles/flint-40b-free.json

@@ -0,0 +1,50 @@
+{
+  "$comment": "Metadata read from models.dev on 2026-10-23 and confirmed by a live call the same day. No latency figure is claimed: one call that answered is not a measurement. Regenerate the capability fields with `oc-harness refresh flint-40b-free`.",
+  "id": "flint-40b-free",
+  "title": "Flint 40B Free",
+  "provider": "opencode",
+  "model": "flint-40b-free",
+  "family": "flint",
+  "verified": "2026-10-23",
+  "retention": "may-train",
+  "notes": "An open-weight mixture of experts, 40B total with about 2.5B active, built for coding agents. Small enough to serve locally, and the weights are published, so the same model can be pointed at a local runtime instead of the free tier. 262k context and a 64k output cap, the full effort ladder, tool calls and structured output; it does not read images. Zen keeps prompts for 30 days and may train on them during the free period.",
+  "limits": {
+    "context": 262144,
+    "output": 65536
+  },
+  "supports": {
+    "reasoning": true,
+    "temperature": true,
+    "toolCall": true,
+    "structuredOutput": true,
+    "attachment": false
+  },
+  "effort": {
+    "levels": [
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "default": "max",
+    "reserveShare": 0.12
+  },
+  "roles": {
+    "plan": "max",
+    "build": "max",
+    "reviewer": "max",
+    "locate": "low",
+    "verify": "low"
+  },
+  "prune": {
+    "enabled": true,
+    "keepRecentToolCalls": 6,
+    "keepRecentTurns": 3,
+    "keepUserMessages": true
+  },
+  "fallback": [
+    "deepseek-v4.1-flash-free",
+    "nemotron-3.5-lightning-free"
+  ]
+}

package/profiles/index.json

@@ -2,6 +2,17 @@
   "$comment": "Profiles verified against live provider metadata. `retention` must come from retention.yml; a model missing there cannot enter this list. The default is a fleet, because a fleet is the point: ten jobs, ten models, one session. `context` is the input cap the config can actually use: the narrowest lane model's on a fleet, the model's own on a single-model profile. `oc-harness list` recomputes it from the profile rather than trusting this copy.",
   "default": "fleet-safe",
   "profiles": [
+    {
+      "id": "beam-free",
+      "file": "profiles/beam-free.json",
+      "title": "Beam Free",
+      "retention": "retained",
+      "free": true,
+      "topEffort": "max",
+      "context": 1048576,
+      "default": false,
+      "note": "Text only, freshest knowledge on the tier, fastest measured route. Keeps prompts for 30 days, so it is not zero-retention."
+    },
     {
       "id": "fleet-safe",
       "file": "profiles/fleet-safe.json",
@@ -24,28 +35,6 @@
       "default": false,
       "note": "Every lane gets the model built for it. Five of the ten providers may use the data to improve the model, so the whole profile is may-train."
     },
-    {
-      "id": "minimax-m3.1-flash-free",
-      "file": "profiles/minimax-m3.1-flash-free.json",
-      "title": "MiniMax M3.1 Flash Free",
-      "retention": "zero-retention",
-      "free": true,
-      "topEffort": "max",
-      "context": 1000000,
-      "default": false,
-      "note": "512k output tokens, the widest of any free route, and the fastest measured image reader at 7.7s."
-    },
-    {
-      "id": "beam-free",
-      "file": "profiles/beam-free.json",
-      "title": "Beam Free",
-      "retention": "retained",
-      "free": true,
-      "topEffort": "max",
-      "context": 1048576,
-      "default": false,
-      "note": "Text only, freshest knowledge on the tier, fastest measured route. Keeps prompts for 30 days, so it is not zero-retention."
-    },
     {
       "id": "deepseek-v4.1-flash-free",
       "file": "profiles/deepseek-v4.1-flash-free.json",
@@ -112,6 +101,17 @@
       "default": false,
       "note": "Reads images correctly, at 19.2s - the slowest lane on the tier. Publishes audio input too, but OpenCode will not read a binary file, so that path is unreachable today."
     },
+    {
+      "id": "flint-40b-free",
+      "file": "profiles/flint-40b-free.json",
+      "title": "Flint 40B Free",
+      "retention": "may-train",
+      "free": true,
+      "topEffort": "max",
+      "context": 262144,
+      "default": false,
+      "note": "Open-weight MoE with about 2.5B active parameters for local coding agents. Knowledge cutoff 2026-06, no image input. May train on prompts during its free period."
+    },
     {
       "id": "big-pickle",
       "file": "profiles/big-pickle.json",
@@ -122,6 +122,17 @@
       "context": 160000,
       "default": false,
       "note": "Stealth model, no public identity, no effort levels, no image input. The provider may train on it during its free period."
+    },
+    {
+      "id": "flint-40b-free",
+      "file": "profiles/flint-40b-free.json",
+      "title": "Flint 40B Free",
+      "retention": "may-train",
+      "free": true,
+      "topEffort": "max",
+      "context": 262144,
+      "default": false,
+      "note": "Open-weight MoE, 40B total with about 2.5B active, built for coding agents and small enough to serve locally. Full effort ladder, 262k context, 64k output, no image input."
     }
   ],
   "excluded": [],
@@ -149,6 +160,11 @@
     {
       "id": "longcat-2.5-preview-free",
       "reason": "Withdrawn from the provider. A preview endpoint, so it could be pulled without a rename - and it was: models.dev still carries the record and marks it deprecated. It was the longform lane's primary in both fleets, so every lane fell back to its second rung, and the profile named only this model had nothing left to fall back to and was retired."
+    },
+    {
+      "id": "minimax-m3.1-flash-free",
+      "reason": "Deprecated by provider. Replaced on the tier by flint-40b-free for the lanes that ran it."
     }
-  ]
+  ],
+  "active": []
 }

package/profiles/mimo-v2.6-flash-free.json

@@ -5,7 +5,7 @@
   "provider": "opencode",
   "model": "mimo-v2.6-flash-free",
   "family": "mimo",
-  "verified": "2026-10-22",
+  "verified": "2026-10-23",
   "retention": "may-train",
   "notes": "Xiaomi. The only free model that publishes audio input, and it read an image correctly in a live call, at 19.2s average - the slowest lane on the tier, and slower than minimax on the same picture. OpenCode 1.19 refuses to read a binary file at all, so the audio path is not reachable through the harness today; the vision path is. No effort levels, so no variant is written.",
   "limits": {
@@ -37,7 +37,5 @@
     "keepRecentTurns": 3,
     "keepUserMessages": true
   },
-  "fallback": [
-    "minimax-m3.1-flash-free"
-  ]
+  "fallback": []
 }

package/retention.yml

@@ -27,14 +27,6 @@ models:
   # --- Zero-retention: the provider states a zero-retention policy and does
   # not train on your data. ---
 
-  opencode/minimax-m3.1-flash-free:
-    retention: zero-retention
-    note: >-
-      "Its provider follows a zero-retention policy and does not use your data
-      for model training." Free for a limited time.
-    verified: 2026-10-19
-    source: https://opencode.ai/docs/zen
-
   opencode/glm-5.3-flash-free:
     retention: zero-retention
     note: >-
@@ -74,6 +66,15 @@ models:
     verified: 2026-10-19
     source: https://opencode.ai/docs/zen
 
+  opencode/flint-40b-free:
+    retention: may-train
+    note: >-
+      "During its free period, collected data may be used to improve the
+      model. Data is retained for 30 days." The weights are open, so the same
+      model can be served locally instead of through the free tier.
+    verified: 2026-10-23
+    source: https://opencode.ai/docs/zen
+
   opencode/mimo-v2.6-flash-free:
     retention: may-train
     note: >-
@@ -109,6 +110,14 @@ models:
     verified: 2026-10-19
     source: https://opencode.ai/docs/zen
 
+  opencode/flint-40b-free:
+    retention: may-train
+    note: >-
+      Free trial endpoint on opencode zen; treated as may-train until terms
+      state otherwise.
+    verified: 2026-10-22
+    source: https://opencode.ai/docs/zen
+
   # --- Paid routes, kept because the catalog still serves them and a profile
   # may be pointed at one. ---
 

package/src/health.js

@@ -12,7 +12,7 @@
 // Plain JS with JSDoc types, like the rest of src/: the CLI and the tests run
 // under plain node, and the plugin loads .ts.
 
-import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs"
+import { existsSync, mkdirSync, readFileSync, renameSync, unlinkSync, writeFileSync } from "node:fs"
 import { join } from "node:path"
 
 /**
@@ -158,9 +158,18 @@ export function readHealth(dir) {
  */
 export function writeHealth(dir, health) {
   try {
-    if (!existsSync(join(dir, ".space"))) mkdirSync(join(dir, ".space"), { recursive: true })
+    const spaceDir = join(dir, ".space")
+    if (!existsSync(spaceDir)) mkdirSync(spaceDir, { recursive: true })
     const pruned = { ...(health ?? {}), unhealthy: liveUnhealthy(health) }
-    writeFileSync(healthPath(dir), JSON.stringify(pruned, null, 2))
+    const file = healthPath(dir)
+    const tmp = `${file}.${process.pid}.${Date.now()}.tmp`
+    try {
+      writeFileSync(tmp, JSON.stringify(pruned, null, 2))
+      renameSync(tmp, file)
+    } catch (err) {
+      try { unlinkSync(tmp) } catch {}
+      throw err
+    }
   } catch {
     // Best effort. A health file that cannot be written means no failover,
     // and failing to write it must not break the session.

package/profiles/minimax-m3.1-flash-free.json

@@ -1,50 +0,0 @@
-{
-  "$comment": "Metadata verified against models.dev on 2026-10-19 and confirmed by a live call the same day. Regenerate the capability fields with `oc-harness refresh minimax-m3.1-flash-free`.",
-  "id": "minimax-m3.1-flash-free",
-  "title": "MiniMax M3.1 Flash Free",
-  "provider": "opencode",
-  "model": "minimax-m3.1-flash-free",
-  "family": "minimax",
-  "verified": "2026-10-22",
-  "retention": "zero-retention",
-  "notes": "Flagship coding and agent model on the free tier: 512k output tokens, the widest of any free route, and the fastest measured image reader at 7.7s. Tool calls are stable. It does not support temperature, and models.dev publishes no structured_output flag for it, so JSON output is requested in the prompt rather than negotiated with the API. Measured at 3.1s for a one-word reply.",
-  "limits": {
-    "context": 1000000,
-    "output": 512000
-  },
-  "supports": {
-    "reasoning": true,
-    "temperature": true,
-    "toolCall": true,
-    "structuredOutput": false,
-    "attachment": true
-  },
-  "effort": {
-    "levels": [
-      "low",
-      "medium",
-      "high",
-      "xhigh",
-      "max"
-    ],
-    "default": "max",
-    "reserveShare": 0.12
-  },
-  "roles": {
-    "plan": "max",
-    "build": "max",
-    "reviewer": "max",
-    "locate": "low",
-    "verify": "low"
-  },
-  "prune": {
-    "enabled": true,
-    "keepRecentToolCalls": 6,
-    "keepRecentTurns": 3,
-    "keepUserMessages": true
-  },
-  "fallback": [
-    "deepseek-v4.1-flash-free",
-    "glm-5.3-flash-free"
-  ]
-}