TavernKeeper Scan Report

patcireamo/ChungusHub

Commit 5e41331 Reviewed Sep 24, 2026

No material or immediate-danger concern was identified in this review.

This advisory report describes what the named tools and review process found at one exact commit. Unknown or unobserved behavior may still exist.

0 immediate danger 0 material 45 low

What this review found

No material or immediate-danger item was identified.

Deterministic technical evidence (41)

Dependency advisory GHSA-vxr8-fq34-vvx9:pkg:8a3c012a263ab8156620fb0e applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/ci.yml:32
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:128
zizmor reported template-injection · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:81
Dependency advisory GHSA-2v37-7h3g-55p8:pkg:a9b17cadf83e3a5de547592b applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-rp9w-3fw7-7cwq:pkg:4e16d185c39b16c1f350ca4f applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-xwg4-73v4-xw9w:pkg:b0abe8c9840bfaafb5747f78 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-qx2v-qp2m-jg93:pkg:d0433ccd51b55fc561da06bf applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-76mc-f452-cxcm:pkg:d0a18325b0cdabed3f35b2c7 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-hgv7-v322-mmgr:pkg:857cc203fb4acdf79b8e7afa applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-r47g-fvhr-h676:pkg:642ceee0c4b2cbc4a2e1b121 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-29g2-3rmr-qm68:pkg:0d943943a3e65d55c4ec32e3 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported template-injection · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:86
Dependency advisory GHSA-c2j3-45gr-mqc4:pkg:42053cd722737fc33c013501 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported artipacked · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:45-49
Dependency advisory GHSA-cmwh-pvxp-8882:pkg:6965d223b6bd576889c01d10 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:50
Dependency advisory GHSA-28wg-ghj8-5hjv:pkg:006e2a19c763cc0fc17b9679 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-9rmh-mm8f-r9h6:pkg:5d32cd47aeaee1205cf18fc6 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:109
Dependency advisory GHSA-fxqj-rqcc-2cmp:pkg:80dc2988b9d15a40674cea67 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/ci.yml:28
Dependency advisory GHSA-wqjv-9729-c5q2:pkg:6699abfbebd5d07abddaa45e applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-6g55-p6wh-862q:pkg:be20184562ed7ac60b9bb3c5 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-866w-xmhq-wj7x:pkg:d613be3ade05d602f01bb313 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-55q2-fjhq-7xh7:pkg:8332ecd5207902f58f4decb3 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-hpcv-96wg-7vj8:pkg:bc90a6f657d85810cfd9cd0b applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:45
Dependency advisory GHSA-fx2h-pf6j-xcff:pkg:7eb19f2c295342271bbc2245 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-r28c-9q8g-f849:pkg:309438d8c981844c76003c01 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-v6wh-96g9-6wx3:pkg:b37ba44174078c9afc2349cb applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-77vg-94rm-hx3p:pkg:91c6e2ad95c2c69b9ed18581 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-rcqx-6q8c-2c42:pkg:6c059b35236f63805cd31009 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-f3cj-j4f6-wq85:pkg:e3a54c277ee81743d557b6f7 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported unpinned-uses · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:92
Dependency advisory GHSA-pr6f-5x2q-rwfp:pkg:1d431e95b842ca17fabc7022 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-9rgm-9g3h-6x36:pkg:4aea48abb5cae4f4aab7ded7 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
Dependency advisory GHSA-x4vx-rjvf-j5p4:pkg:f9e26ced39b613e63f6a02d9 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported artipacked · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/ci.yml:28-31
Dependency advisory GHSA-gvmj-g25r-r7wr:pkg:2163f78fab2fec7de8db16b4 applies · osv-scanner 2.4.0

A dependency has a published security issue, though this scan does not show that the project exposes it to an attacker.

Policy reason: osv-structured-advisory · Execution scope: unknown

Source: bun.lock
zizmor reported cache-poisoning · zizmor 1.28.0

The code has a known weakness, though this scan does not show that anyone can exploit it here.

Policy reason: zizmor-known-workflow-rule · Execution scope: automation

Source: .github/workflows/release.yml:50

Contextual expected matches (4)

JavaScript analysis reported javascript.download-to-execution

Expected behavior · high confidence

The flagged code draws the app's own lock and status pages. The scripts on those pages only talk to the app itself, such as to check an entered password or cancel a restore. Nothing downloaded from anywhere is ever turned into running code, which is what the scanner pattern was looking for.

Technical evidence

Scanner reason: JavaScript analysis matched static JavaScript security signal javascript.download-to-execution. The match applies to this repository.

Contextual assessment: The matched region builds server-rendered HTML gate pages (access denied, wrong host, maintenance, and login) from template literals that contain small inline client scripts. Those scripts read a local paint-cache value from localStorage, submit a password to a same-origin login endpoint, or post a same-origin cancel-restore request. There is no eval, no Function constructor, no dynamic import, and no network-retrieved data flowing into any code-execution sink: the only remote calls are browser fetch calls to the app's own origin, and the values interpolated into the HTML are either developer-authored strings or the request host header, which is explicitly HTML-escaped. The scanner's correlation of a network primitive with a code-execution sink in the same representation is a false positive driven by the presence of both fetch calls and inline script tags in one function, with no data path connecting them.

Impact: none · Exploitability: unlikely

Developer action: none

Scanner: javascript-analysis webcrack-2.16.0_js-x-ray-16.0.0_signatures-1_literals-1_families-1
Rule: javascript.download-to-execution
File role: production
Source: server/index.ts:524-632

OpenGrep reported tavernkeeper.download-and-execute.shell-pipeline

Expected behavior · high confidence

The README simply tells developers how to install the required runtime tool, using the tool maker's own official one-line install command. Nothing in the app itself downloads and runs code; this is just setup instructions a person types themselves.

Technical evidence

Scanner reason: OpenGrep matched static-analysis rule tavernkeeper.download-and-execute.shell-pipeline. The match applies to this repository.

Contextual assessment: The flagged lines are documentation text in the project README showing developers how to install the Bun runtime using Bun's official public installer script. This is the standard, widely used install method published by Bun itself. It is inert prose inside a fenced code block in a documentation file; the project's shipped application code never downloads or executes anything at this location, and no automated pipeline in the supplied evidence executes these lines. Piping a well-known vendor installer to a shell is a common documented install pattern, not a concealed download-and-execute behavior in executable code.

Impact: none · Exploitability: unlikely

Developer action: none

Scanner: opengrep 1.26.0
Rule: tavernkeeper.download-and-execute.shell-pipeline
File role: documentation
Source: README.md:136-137

OpenGrep reported tavernkeeper.download-and-execute.shell-pipeline

Expected behavior · high confidence

The flagged lines are just the standard 'install Bun' instructions copied into the project's setup guide. They fetch Bun's official installer, exactly as the Bun project itself tells everyone to install it. This is documentation a developer reads and types themselves, not hidden or automatic code, and it serves the page's clear purpose of explaining how to run the app from source.

Technical evidence

Scanner reason: OpenGrep matched static-analysis rule tavernkeeper.download-and-execute.shell-pipeline. The match applies to this repository.

Contextual assessment: The scanner flagged a download-and-execute pattern, but the matched lines are inside an installation documentation file, not executable project code. The command shown is the Bun runtime's own official install command, piped to the shell as the vendor documents it, presented as a prerequisite for running the project from source. The file role is documentation, execution scope is test-documentation-data, and the same instruction appears identically in the project README and on the Bun site. There is no project-controlled script being fetched, no custom destination, and no concealment; the instruction is visible to the user, matches the stated purpose of the page, and is invoked manually by the developer choosing to run from source. Piping a vendor's official installer to a shell is a general supply-chain trust consideration of third-party tooling, not a demonstrated exposure created by this repository.

Impact: none · Exploitability: unlikely

Developer action: none

Scanner: opengrep 1.26.0
Rule: tavernkeeper.download-and-execute.shell-pipeline
File role: documentation
Source: docs/installation.mdx:28-29

OpenGrep reported tavernkeeper.persistence.startup-modification

Expected behavior · high confidence

The script adjusts its own search path while running so it can find the Bun tool. It does not change any system startup files or set up anything that persists after it closes. This is a normal convenience for a development launcher.

Technical evidence

Scanner reason: OpenGrep matched static-analysis rule tavernkeeper.persistence.startup-modification. The match applies to this repository.

Contextual assessment: The scanner matched a comment on line 18 that references ~/.zshrc. The actual code on lines 20-22 only prepends a known install directory to PATH within the current process if bun is not already found, a standard fallback for non-interactive Finder launches. No startup file is created, modified, or appended to. The PATH change is process-local and does not persist after the dev launcher exits. There is no cron entry, launchd plist, login hook, or other persistence mechanism anywhere in the supplied script.

Impact: none · Exploitability: unlikely

Developer action: none

Scanner: opengrep 1.26.0
Rule: tavernkeeper.persistence.startup-modification
File role: production
Source: dev.sh:18

Coverage and limitations

Inventory: 854 files · 130019612 bytes
Contextual coverage: 45 of 45 candidates assessed

JavaScript coverage

Status: Incomplete
Candidates: 384 files · 3811665 bytes
X-Ray review families: 0 warning occurrences compacted to 0 evidence-preserving review families
Representations: 384 raw · 30 decoded · 0 normalized · 0 bundle modules
Stage scans: 384 raw signatures · 19 raw AST · 383 raw OpenGrep · 30 derived signatures · 0 derived AST · 30 derived OpenGrep

Unresolved JavaScript stages

scripts/icons.ts — raw-ast / parse
scripts/package.ts — raw-ast / parse
server/about.ts — raw-ast / parse
server/access.ts — raw-ast / parse
server/assistant/files-core.test.ts — raw-ast / parse
server/assistant/files-core.ts — raw-ast / parse
server/assistant/files-ingest.ts — raw-ast / parse
server/assistant/freshness-core.test.ts — raw-ast / parse
server/assistant/freshness-core.ts — raw-ast / parse
server/assistant/freshness.ts — raw-ast / parse
server/assistant/loop.ts — raw-ast / parse
server/assistant/registry/ask.ts — raw-ast / parse
server/assistant/registry/capabilities.ts — raw-ast / parse
server/assistant/registry/chat-reads.ts — raw-ast / parse
server/assistant/registry/entities.ts — raw-ast / parse
server/assistant/registry/entity-ops.ts — raw-ast / parse
server/assistant/registry/files.ts — raw-ast / parse
server/assistant/registry/greetings.ts — raw-ast / parse
server/assistant/registry/groups.ts — raw-ast / parse
server/assistant/registry/images.ts — raw-ast / parse
server/assistant/registry/index.ts — raw-ast / parse
server/assistant/registry/lorebook-entries.ts — raw-ast / parse
server/assistant/registry/navigate.ts — raw-ast / parse
server/assistant/registry/prompt-trace.ts — raw-ast / parse
server/assistant/registry/schema.ts — raw-ast / parse
server/assistant/registry/settings.ts — raw-ast / parse
server/assistant/registry/skills.ts — raw-ast / parse
server/assistant/registry/smoke.ts — raw-ast / parse
server/assistant/registry/types.ts — raw-ast / parse
server/assistant/registry/util.ts — raw-ast / parse
server/assistant/registry/versions.ts — raw-ast / parse
server/assistant/registry/workspace.ts — raw-ast / parse
server/assistant/rows.ts — raw-ast / parse
server/assistant/sessionSettings.ts — raw-ast / parse
server/assistant/systemPrompt.ts — raw-ast / parse
server/assistant/toolProgress.ts — raw-ast / parse
server/assistant/types.ts — raw-ast / parse
server/backup/backup.test.ts — raw-ast / parse
server/backup/inventory.ts — raw-ast / parse
server/backup/job.ts — raw-ast / parse
server/backup/manifest.ts — raw-ast / parse
server/backup/paths.ts — raw-ast / parse
server/backup/restore-swap.test.ts — raw-ast / parse
server/backup/restore.ts — raw-ast / parse
server/backup/retention.test.ts — raw-ast / parse
server/backup/retention.ts — raw-ast / parse
server/backup/schedule.test.ts — raw-ast / parse
server/backup/schedule.ts — raw-ast / parse
server/backup/service.ts — raw-ast / parse
server/backup/snapshot.ts — raw-ast / parse
server/boot-sweeps.ts — raw-ast / parse
server/chatList.test.ts — raw-ast / parse
server/commitGeneratedTurn.test.ts — raw-ast / parse
server/config.test.ts — raw-ast / parse
server/config.ts — raw-ast / parse
server/db.ts — raw-ast / parse
server/default-characters.ts — raw-ast / parse
server/defaultCharacters.test.ts — raw-ast / parse
server/files.ts — raw-ast / parse
server/generationSurvival.test.ts — raw-ast / parse
server/greetingRefresh.test.ts — raw-ast / parse
server/imageFiles.test.ts — raw-ast / parse
server/importChat.test.ts — raw-ast / parse
server/importSources.test.ts — raw-ast / parse
server/index.ts — raw-ast / parse
server/index.ts — raw-opengrep / parse
server/instance-lock.ts — raw-ast / parse
server/instanceLock.test.ts — raw-ast / parse
server/llm/anthropic-native.ts — raw-ast / parse
server/llm/inline-reasoning.test.ts — raw-ast / parse
server/llm/inline-reasoning.ts — raw-ast / parse
server/llm/media.ts — raw-ast / parse
server/llm/net.test.ts — raw-ast / parse
server/llm/net.ts — raw-ast / parse
server/llm/openai-compatible.test.ts — raw-ast / parse
server/llm/openai-compatible.ts — raw-ast / parse
server/llm/providers/anthropic.ts — raw-ast / parse
server/llm/providers/chutes.ts — raw-ast / parse
server/llm/providers/deepseek.ts — raw-ast / parse
server/llm/providers/electronhub.ts — raw-ast / parse
server/llm/providers/googleaistudio.ts — raw-ast / parse
server/llm/providers/index.ts — raw-ast / parse
server/llm/providers/mistral.ts — raw-ast / parse
server/llm/providers/moonshot.ts — raw-ast / parse
server/llm/providers/nanogpt.ts — raw-ast / parse
server/llm/providers/openai-compatible.ts — raw-ast / parse
server/llm/providers/openai.ts — raw-ast / parse
server/llm/providers/openrouter.ts — raw-ast / parse
server/llm/providers/perplexity.ts — raw-ast / parse
server/llm/providers/types.ts — raw-ast / parse
server/llm/providers/util.ts — raw-ast / parse
server/llm/providers/xai.ts — raw-ast / parse
server/llm/providers/zai.ts — raw-ast / parse
server/llm/registry.ts — raw-ast / parse
server/llm/types.ts — raw-ast / parse
server/lorebookCover.test.ts — raw-ast / parse
server/lorebookRows.test.ts — raw-ast / parse
server/messageLorebook.test.ts — raw-ast / parse
server/messageRev.test.ts — raw-ast / parse
server/messageSpriteLabel.test.ts — raw-ast / parse

Tools

inventory 0.1.0 — completed
tavernkeeper-static 5 — completed
gitleaks 8.30.1 — completed
opengrep 1.26.0 — completed
javascript-analysis webcrack-2.16.0_js-x-ray-16.0.0_signatures-1_literals-1_families-1 — completed
osv-scanner 2.4.0 — completed
zizmor 1.28.0 — completed
malcontent 1.25.7 — completed

Limitations

This advisory review cannot prove the absence of unknown behavior.
JavaScript analysis was incomplete, so this first-filter scan supports no clean conclusion about unobserved behavior.

Technical scan identity

Full commit: 5e4133165aa9cddb325bf8c0628c65537d1ffd1f
Completed: Sep 24, 2026
History depth: 20 commits
Method: Deterministic evidence with contextual review
Reviewer: nano-gpt.com · zai-org/glm-latest
Scanner: 0.1.0
Scanner policy: 5
Rule catalog: 2
Contextual policy: 5
Ecosystem context: sillytavern-community-v1
Prompt: contextual-review-v7
Assessment schema: contextual-assessment-v2
Review provenance: 2 fresh / 2 reused groups · 2 fresh / 2 reused candidates
Review source reports: 4e19b00dc2cd6d0d3b2785f9f0e40ee6850b6ede53c62095593275b169a55e1e
Evidence triage: 41 deterministic / 4 contextual candidates · 4 contextual / 11 total behavior cases
Model budget: 1 model call · 2 / 12 fresh cases · 41835 / 200000 estimated input · 32657 / 250000 actual input · 934 / 40000 output tokens
Review batching: 1 model call · up to 2 groups and 2 candidates per call · 0 retry calls · 0 over-budget singleton calls
Review usage: 32657 input · 934 output · 0 cache read · 133 reasoning tokens
Report: 44a91d700003358c005914a672261514be4770b147c2db518d10af4b8bbda264