{
  "fixes": {
    "slug": "qwen-code",
    "name": "Qwen Code",
    "listing": "https://www.anchorterminal.com/tools/qwen-code",
    "markdown": "# Fix list: Qwen Code\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/qwen-code, the October 2026 research run, assessed 8 October 2026. Grade BB, 72.4 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Qwen Code: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Security \u0026 auth, 53 out of 100, up to 8.2 more on the total\n\nWhy it scored 53: Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Usage statistics are on by default, documented as tool names, model names, timings and configuration without prompts, responses, file contents or personal information, with a setting and an environment variable to turn them off. Credentials are API keys in environment variables or settings.json (15). Five approval modes with a read-only plan mode and allow, ask and deny rules, but the settings default is Auto, where an LLM classifier approves tool calls, folder trust is disabled by default and sandboxing is opt-in (10). A Linux tool sandbox with `network: closed`, `--safe-mode` and a stderr warning for yolo without a sandbox, but the default macOS Seatbelt profile allows network and we found no guidance on prompt injection in the pages read (7). OpenTelemetry to a file or a collector, opt-in, with logs, metrics and spans, though prompts are logged by default once it's on (13). SECURITY.md gives only an Alibaba Cloud console portal with no response time, the repository has no published advisories, no security.txt was found, and CodeQL and scorecard workflows run in CI (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 2. Reliability, 69 out of 100, up to 6.2 more on the total\n\nWhy it scored 69: Local-package reading. npm with engines node 22 or newer, Homebrew at 0.25.0 and a standalone installer, with stable, preview and nightly channels (20). Public CI, and of the 15 most recent completed CI runs on main on 8 October, 12 passed, 3 were cancelled and none failed, though two issues opened by automation the same day report a failed end-to-end test and a failed Java SDK job on main (22). 1,402 open issues and 334 open pull requests. The ten newest issues each had labels and one to five comments within the day, much of it from the project's own triage automation (15). The changelog states Keep a Changelog and semver and every release has a Breaking Changes heading, but breaking changes shipped in patch releases 0.23.4 and 0.24.1 (12). 0.25.0, pre-1.0 (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Payments \u0026 pricing, 60 out of 100, up to 5 more on the total\n\nWhy it scored 60: Self-hosted rule. No payment protocol (0). The CLI is free under Apache-2.0 with nothing to buy (20). No card or account is needed for the software, and it runs against a local model server (20). An agent can install and run it with no sign-up, given a model endpoint (20). Alibaba Cloud's Coding Plan and Token Plan are separate purchases, and their price pages couldn't be loaded on 8 October 2026.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 4. Transparency \u0026 trust, 63 out of 100, up to 3.2 more on the total\n\nMade of editorial 77, provenance 48.\n\nWhy it scored 63: Apache-2.0 (30). One terms and privacy page maps each sign-in method to the model provider's terms, says the project doesn't train on prompts or code, and lists what usage statistics hold, but gives no retention period, doesn't name the Alibaba Cloud endpoint the statistics go to, and names no legal entity (18). The end of the Qwen OAuth free tier is dated 15 April 2026 and `tools.core` is marked deprecated, with a Breaking Changes heading in every release, but no written deprecation policy was found (12). Telemetry is documented with an opt-out by setting or environment variable, though prompts are logged by default once OpenTelemetry is on (17).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: qwenlm.github.io, no registry record we could read (0 of 15)\n- Terms of service: read, states 1 of the 7 things a reader expects (4.9 of 10)\n- Privacy policy: read, states 2 of the 8 things a reader expects (5.5 of 10)\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 5. Agent ergonomics, 85 out of 100, up to 2.4 more on the total\n\nWhy it scored 85: Framework reading, adapted to a harness driven by a pipeline. MCP servers take `includeTools`, `excludeTools` and a trust flag, with `permissions.allow`, `ask` and `deny` rules and `--exclude-tools` (20). Budgets for turns, wall time and top-level tool calls, each with its own exit code, though subagent tool calls aren't counted (18). Documented exit codes (18). `--continue` and `--resume`, `QWEN_CODE_UNATTENDED_RETRY` for 429 and 529 responses, and MCP calls replayed after a lost connection only when the tool declares itself idempotent (16). A TypeScript SDK on npm at 0.1.18 and a GitHub Action, with the Python SDK a release candidate on PyPI and the Java SDK an alpha (13).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 6. Schema \u0026 documentation, 91 out of 100, up to 1.5 more on the total\n\nWhy it scored 91: Framework reading. A settings.schema.json in the repository, a settings reference with the type and default of each key, and an OpenAPI file for the daemon's REST API (25). llms.txt on the docs site lists the pages with a line each, though it links to HTML and the Markdown path we tried returned 404 (8). The approval-mode page says when to use each mode and the sandbox page what each method and Seatbelt profile allows (15). Approval modes, sandbox backends, filesystem and network policies are enums (13). The headless page documents json and stream-json output, and exit codes 41, 42, 44, 52, 53, 55 and 130 are documented (15). A dated changelog generated from releases (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 7. Maintenance \u0026 community, 88 out of 100, up to 1.1 more on the total\n\nWhy it scored 88: 0.25.0 on 5 October 2026 (30). 39 stable releases since 10 July, plus previews and nightlies (20). Issues are labelled and commented on within a day, largely by automation, against 1,402 open issues and 334 open pull requests (17). A TypeScript SDK released on 5 October, with the Python SDK last published to PyPI as a release candidate on 9 May 2026 and the Java SDK an alpha (11). CI, CodeQL, a monthly scorecard and Dependabot (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- unchecked: Alibaba Cloud Coding Plan and Token Plan prices and quotas. alibabacloud.com and help.aliyun.com couldn't be reached from our network on 8 October 2026\n- unchecked: the Qwen terms of service and privacy policy at qwen.ai, which render only with JavaScript\n- unchecked: security.txt on alibabacloud.com, and the registration date of any vendor domain\n- unchecked: how many of the 1,402 open issues are bugs, and how old the oldest are. GitHub's search API refused us for its rate limit\n- The settings reference gives `auto` as the default approval mode, while the approval-mode page says headless runs default to Ask Permissions. We didn't run it to see which holds\n- The docs don't name where usage statistics go. The source sends them to gb4w8c3ygj-default-sea.rum.aliyuncs.com\n- Whether the Java SDK is published to Maven Central wasn't checked\n- The lead was right on licence, stars (28,362), headless `qwen -p` and MCP. Its docs link was the repository, and the docs site is qwenlm.github.io/qwen-code-docs\n\n## Weaknesses\n\n- The default approval mode is Auto, where an LLM classifier approves tool calls, and sandboxing and folder trust are both off by default\n- Usage statistics are on by default and go to an Alibaba Cloud endpoint that the docs don't name\n- SECURITY.md points only to an Alibaba Cloud console portal, with no response time, and the repository has no published advisories\n- Pre-1.0 at 0.25.0, with breaking changes shipped in patch releases such as 0.23.4 and 0.24.1\n- 1,402 open issues and 334 open pull requests on 8 October 2026\n- The Qwen OAuth free tier ended on 15 April 2026, so every run needs a paid key or a local model\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Pass `--approval-mode` on every run. The settings default is `auto`, and one docs page says headless runs default to asking, so don't rely on either\n- Add `--max-session-turns`, `--max-wall-time` and `--max-tool-calls`. All three are unlimited by default. Exit 53 is the turn limit and 55 a budget\n- `--yolo` doesn't turn on a sandbox. Add `--sandbox`, or on Linux set `tools.executionSandbox` with `network` set to `closed`\n- Set `QWEN_USAGE_STATISTICS_ENABLED=false` to stop usage statistics\n- Authenticate with `OPENAI_API_KEY`, `OPENAI_BASE_URL` and `OPENAI_MODEL` in CI. The browser sign-in is discontinued\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "BB",
    "score": 72.4,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 53,
        "maxGain": 8.2,
        "reason": "Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines. Usage statistics are on by default, documented as tool names, model names, timings and configuration without prompts, responses, file contents or personal information, with a setting and an environment variable to turn them off. Credentials are API keys in environment variables or settings.json (15). Five approval modes with a read-only plan mode and allow, ask and deny rules, but the settings default is Auto, where an LLM classifier approves tool calls, folder trust is disabled by default and sandboxing is opt-in (10). A Linux tool sandbox with `network: closed`, `--safe-mode` and a stderr warning for yolo without a sandbox, but the default macOS Seatbelt profile allows network and we found no guidance on prompt injection in the pages read (7). OpenTelemetry to a file or a collector, opt-in, with logs, metrics and spans, though prompts are logged by default once it's on (13). SECURITY.md gives only an Alibaba Cloud console portal with no response time, the repository has no published advisories, no security.txt was found, and CodeQL and scorecard workflows run in CI (8).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 69,
        "maxGain": 6.2,
        "reason": "Local-package reading. npm with engines node 22 or newer, Homebrew at 0.25.0 and a standalone installer, with stable, preview and nightly channels (20). Public CI, and of the 15 most recent completed CI runs on main on 8 October, 12 passed, 3 were cancelled and none failed, though two issues opened by automation the same day report a failed end-to-end test and a failed Java SDK job on main (22). 1,402 open issues and 334 open pull requests. The ten newest issues each had labels and one to five comments within the day, much of it from the project's own triage automation (15). The changelog states Keep a Changelog and semver and every release has a Breaking Changes heading, but breaking changes shipped in patch releases 0.23.4 and 0.24.1 (12). 0.25.0, pre-1.0 (0).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 60,
        "maxGain": 5,
        "reason": "Self-hosted rule. No payment protocol (0). The CLI is free under Apache-2.0 with nothing to buy (20). No card or account is needed for the software, and it runs against a local model server (20). An agent can install and run it with no sign-up, given a model endpoint (20). Alibaba Cloud's Coding Plan and Token Plan are separate purchases, and their price pages couldn't be loaded on 8 October 2026.",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 63,
        "maxGain": 3.2,
        "reason": "Apache-2.0 (30). One terms and privacy page maps each sign-in method to the model provider's terms, says the project doesn't train on prompts or code, and lists what usage statistics hold, but gives no retention period, doesn't name the Alibaba Cloud endpoint the statistics go to, and names no legal entity (18). The end of the Qwen OAuth free tier is dated 15 April 2026 and `tools.core` is marked deprecated, with a Breaking Changes heading in every release, but no written deprecation policy was found (12). Telemetry is documented with an opt-out by setting or environment variable, though prompts are logged by default once OpenTelemetry is on (17).",
        "blend": "editorial 77, provenance 48",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 85,
        "maxGain": 2.4,
        "reason": "Framework reading, adapted to a harness driven by a pipeline. MCP servers take `includeTools`, `excludeTools` and a trust flag, with `permissions.allow`, `ask` and `deny` rules and `--exclude-tools` (20). Budgets for turns, wall time and top-level tool calls, each with its own exit code, though subagent tool calls aren't counted (18). Documented exit codes (18). `--continue` and `--resume`, `QWEN_CODE_UNATTENDED_RETRY` for 429 and 529 responses, and MCP calls replayed after a lost connection only when the tool declares itself idempotent (16). A TypeScript SDK on npm at 0.1.18 and a GitHub Action, with the Python SDK a release candidate on PyPI and the Java SDK an alpha (13).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 91,
        "maxGain": 1.5,
        "reason": "Framework reading. A settings.schema.json in the repository, a settings reference with the type and default of each key, and an OpenAPI file for the daemon's REST API (25). llms.txt on the docs site lists the pages with a line each, though it links to HTML and the Markdown path we tried returned 404 (8). The approval-mode page says when to use each mode and the sandbox page what each method and Seatbelt profile allows (15). Approval modes, sandbox backends, filesystem and network policies are enums (13). The headless page documents json and stream-json output, and exit codes 41, 42, 44, 52, 53, 55 and 130 are documented (15). A dated changelog generated from releases (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 88,
        "maxGain": 1.1,
        "reason": "0.25.0 on 5 October 2026 (30). 39 stable releases since 10 July, plus previews and nightlies (20). Issues are labelled and commented on within a day, largely by automation, against 1,402 open issues and 334 open pull requests (17). A TypeScript SDK released on 5 October, with the Python SDK last published to PyPI as a release candidate on 9 May 2026 and the Java SDK an alpha (11). CI, CodeQL, a monthly scorecard and Dependabot (10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "qwenlm.github.io, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 1 of the 7 things a reader expects",
        "points": 4.9,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 2 of the 8 things a reader expects",
        "points": 5.5,
        "max": 10
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: Alibaba Cloud Coding Plan and Token Plan prices and quotas. alibabacloud.com and help.aliyun.com couldn't be reached from our network on 8 October 2026",
      "unchecked: the Qwen terms of service and privacy policy at qwen.ai, which render only with JavaScript",
      "unchecked: security.txt on alibabacloud.com, and the registration date of any vendor domain",
      "unchecked: how many of the 1,402 open issues are bugs, and how old the oldest are. GitHub's search API refused us for its rate limit",
      "The settings reference gives `auto` as the default approval mode, while the approval-mode page says headless runs default to Ask Permissions. We didn't run it to see which holds",
      "The docs don't name where usage statistics go. The source sends them to gb4w8c3ygj-default-sea.rum.aliyuncs.com",
      "Whether the Java SDK is published to Maven Central wasn't checked",
      "The lead was right on licence, stars (28,362), headless `qwen -p` and MCP. Its docs link was the repository, and the docs site is qwenlm.github.io/qwen-code-docs"
    ],
    "weaknesses": [
      "The default approval mode is Auto, where an LLM classifier approves tool calls, and sandboxing and folder trust are both off by default",
      "Usage statistics are on by default and go to an Alibaba Cloud endpoint that the docs don't name",
      "SECURITY.md points only to an Alibaba Cloud console portal, with no response time, and the repository has no published advisories",
      "Pre-1.0 at 0.25.0, with breaking changes shipped in patch releases such as 0.23.4 and 0.24.1",
      "1,402 open issues and 334 open pull requests on 8 October 2026",
      "The Qwen OAuth free tier ended on 15 April 2026, so every run needs a paid key or a local model"
    ],
    "agentNotes": [
      "Pass `--approval-mode` on every run. The settings default is `auto`, and one docs page says headless runs default to asking, so don't rely on either",
      "Add `--max-session-turns`, `--max-wall-time` and `--max-tool-calls`. All three are unlimited by default. Exit 53 is the turn limit and 55 a budget",
      "`--yolo` doesn't turn on a sandbox. Add `--sandbox`, or on Linux set `tools.executionSandbox` with `network` set to `closed`",
      "Set `QWEN_USAGE_STATISTICS_ENABLED=false` to stop usage statistics",
      "Authenticate with `OPENAI_API_KEY`, `OPENAI_BASE_URL` and `OPENAI_MODEL` in CI. The browser sign-in is discontinued"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}