Repository navigation
feat(web): show compact token usage in model cards - #189
Merged
Merged
Conversation
Open
yulan23333
pushed a commit
to yulan23333/aiscan
that referenced
this pull request
Oct 27, 2026
新增 cmd/wasm:把 pkg/agent 的 loop/evaluator 当"脑"跑进浏览器扩展, 三座 JSON 缝接到 JS host: - Provider -> __aiscanLLM(reqJSON) (host 现有 provider) - Tools -> __aiscanTool(name, args) (host stub,chrome.scripting 在真实 tab 执行) - eventbus -> onEvent(eventJSON) 外加 aiscanRunAgent / aiscanCancelAgent 导出 + aiscanAgentReady 就绪标志。 GATE 结论: - pkg/agent(+evaluator/provider/commands)GOOS=js GOARCH=wasm 直接编过, 无需剥离(只 import pkg/commands,不碰 pkg/tools)。 - 端到端可跑:cmd/wasm/testdata/smoke.mjs 21/21(LLM↔工具↔事件↔取消)。 - 体积:strip 17MB / gzip 4.2MB < 现网 finger.wasm 29MB,体积可接受。 不含:插件 host 侧(agent-manager.js 等)、session 持久化 host 化、TinyGo 瘦身。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Web model cards now show compact input/output token counts and an SVG cache icon with the hit percentage. Hover or keyboard focus reveals exact totals and cache read/write counts; unavailable usage adds no placeholder.
Show the same usage once across reasoning/reply cards and compiler parent/round cards. Update the cyber-ui pin for cumulative card usage and canonical cache counters.
Validation: 40 focused workflow/JEV tests, three cache icon follow-up checks, TypeScript checking, and the production frontend build; desktop and mobile screenshots checked.
Refs #184. Finer attribution across model requests, tools, retries and delegated work, and planned/executed/verified evidence linking are deferred. Path visualization is outside this change.