3 commits

Author	SHA1	Message	Date
Kai	525fb146d6	feat(vis): full session debugging — tasks/cron, execution timeline, retries & tool progress (#1210) ... * feat(vis): surface background tasks and cron jobs The visualizer read every wire/state/blob artifact a session persists but ignored the two on-demand families agent-core also writes under the session directory: background tasks (tasks/<id>.json + output.log) and cron jobs (cron/<id>.json). Neither is reconstructable from the wire, so there was no way to inspect what a session spawned in the background or scheduled. Server: - task-store / cron-store read-only readers mirroring agent-core's on-disk layout, id-validation guard, and legacy snake_case task normalization - GET /:id/tasks, /:id/tasks/:taskId/output (byte-window paged via an exact nextOffset cursor), and /:id/cron routes - re-export the public background-task types from agent-core; mirror the non-exported CronTask shape with a fixture-backed drift test Web: - Tasks tab: process/agent/question kinds with status, timing, kind-specific fields, raw JSON, and a progressively paged output.log viewer - Cron tab: expression, prompt, recurring/one-shot, created/last-fired - count badges on both tabs Tests: +20 (lib + route), all 113 vis-server tests green; web typecheck and build clean. * feat(agent-core): persist step retries and tool progress summary Two transient signals were only ever emitted as live-only loop events, so nothing survived in the agent record for post-hoc analysis: - step retries: chatWithRetry gains an onRetry callback; turn-step collects the recovered attempts and attaches them to step.end as an optional `retries` array (previously only the live `step.retrying` event). - tool progress: tool-call distills a tool's sparse status/percent updates into a bounded `progress` summary (updateCount / lastStatus / maxPercent) on tool.result. Streamed stdout/stderr is excluded — it would bloat the wire and is already reflected in the result output. Both are additive optional fields, so the wire protocol version is unchanged and existing records keep loading. New public types: LoopStepRetryRecord, LoopToolProgressSummary. * feat(vis): add execution-analysis timeline and surface retries/progress Turn the debugger from a flat record viewer into an analysis tool. New Timeline tab: folds the wire into turns → steps → tool calls (client-side, no extra round-trip) and derives the metrics the raw list hides — per-turn / per-step / per-tool duration, per-turn token cost, a context-window fill sparkline with cache-hit rate, a tool usage table, idle-gap detection, and a config-change timeline. Inline elsewhere: - Wire rows show tool.call → tool.result elapsed time; tool.result detail shows truncation, output size, retries, and the progress summary. - Issues drawer gains tool-error, truncation, filtered, max_tokens, and retried categories. - Tasks tab links agent-kind tasks to the subagent's wire. Wires up vitest for the web package and adds analysis/issues unit tests. * feat(vis): import debug zips with a logs view and imported-session filtering A `/export-debug-zip` bundle is just `manifest.json` plus a flattened session directory, which vis already knows how to read. Importing one therefore lights up every existing tab for a session that lives on someone else's machine. Server: - zip-import: yauzl extraction with zip-slip path guards and entry-count / uncompressed-size caps for untrusted uploads. - import-store: extract a bundle into <home>/imported/<imp_…>/, validate it has a main wire, and record an import-meta.json sidecar. - session-store resolves imp_-prefixed ids against imported/, so wire / context / tasks / cron / blobs / logs all work on imported sessions; agent homedirs are re-derived locally (the bundle holds foreign absolute paths). - POST /api/imports (raw zip body) and GET /api/sessions/:id/logs (structured log lines — also available for local sessions). Web: - session rail: import button + all/local/imported filter + imported badge. - new Logs tab: virtualized, level filter, search, session/global toggle. - manifest card atop the State tab for imported sessions. SessionSummary/SessionDetail gain `imported` + `importMeta`. Tests cover extraction, the zip-slip guard, list merge, reading an imported wire through the existing route, and log parsing. * fix(vis): read tasks/cron from agent homedirs and stop persisting tool status text Addresses review feedback on the debug-tooling changes: - Background tasks and cron jobs are persisted under each agent's homedir (<session>/agents/<id>/tasks and /cron), not the session root. The Tasks and Cron tabs read the session root, so they showed nothing for normal sessions. Both routes now aggregate across detail.agents homedirs; task entries carry the owning agentId. The route-test fixtures were writing to the wrong (session-root) location too — corrected to the real agents/main layout so they actually exercise the path. - tool.result progress no longer keeps free-form status text, only updateCount and maxPercent. A tool's status string can contain sensitive data (e.g. an MCP OAuth authorization URL) that must not leak into persisted wire files or exported debug bundles. * fix(vis): stop the main content area from overflowing horizontally The <main> flex child lacked min-w-0, so it defaulted to min-width:auto and refused to shrink below its content's intrinsic width. Tabs that lay out in normal flow with flex-wrap rows (the Timeline tab) then got unbounded width, never wrapped, and blew the layout out to thousands of pixels wide. Adding min-w-0 lets the column shrink to the available width so its content wraps, truncates, or scrolls within its own container. * fix(vis): resolve local global log path and imported-state agent fallback - Logs tab: for non-imported sessions the shared global log lives at <KIMI_CODE_HOME>/logs/kimi-code.log, not under the session dir (that path is only used inside exported bundles). The route now reads the home path for local sessions, so the global-log toggle works for them. - Imported detail: a bundle's state.json is best-effort and may omit the agents map. When the inventory is empty, fall back to discovering agents from disk so routes that require an agent (wire/context) still resolve main. * fix(vis): harden imported manifest and task parsing against corrupt input An imported debug zip is untrusted, so a syntactically valid but type-corrupt file could crash whole views: - manifest.json: a non-string field (e.g. workspaceDir: 123) flowed into SessionSummary.workDir, where the session rail calls .split('/') and crashed the entire list. readManifest/readImportMeta now sanitize declared string fields, keeping only strings. - task JSON: a record that passed the shape guard but held a non-string legacy field (e.g. stop_reason: 5) threw in normalization, failing GET /tasks with a 500 and hiding all of a session's tasks. optionalNonEmptyString now tolerates non-strings, and listBackgroundTasks skips any record that still fails to normalize — honouring the reader's documented silently-skips contract. * fix(vis): discover rotated logs; keep tool progress on thrown failures - Logs tab: the diagnostic log can rotate (kimi-code.log.1, .2, …) and an exported bundle may contain only the archives. The route now discovers the active file plus its rotated siblings and concatenates them oldest-first, so a rotated-away log still surfaces (covered by node-sdk's rotated-export case). - agent-core: a tool that reported sparse progress and then threw lost its progress summary, because the catch path built the error tool.result without it. Thread progressSummary through that path too, matching the success and malformed-return paths. * fix(vis): skip type-corrupt agent entries in imported state readImportedDetail's empty-inventory fallback never ran when a bundle's state.json had a non-empty but type-corrupt agents map (e.g. `{ "agents": { "main": null } }`): inventoryAgents dereferenced the null entry and threw, so readSessionDetail returned 500 instead of recovering main from the on-disk agents/main/wire.jsonl. inventoryAgents now skips non-object entries, letting the disk-discovery fallback take over. * fix(vis): reset timeline agent on session change; preserve context on zero-usage steps - Timeline tab kept the previously-selected agent id across session navigation, so a subagent selection would 404 against the next session. Reset it to main on sessionId change, mirroring WireTab/ContextTab. - A zero-usage step.end (e.g. a content-filtered response) reset the context-window fill to 0, pushing a false drop into the Timeline chart and the Context tab. agent-core's ContextMemory keeps the prior count in that case; the analysis lib and the context projector now do the same. * revert: drop agent-core retries/tool-progress persistence These were the only changes in this branch that touched agent-core. They persisted two previously live-only signals (step retries, tool progress) to the wire purely so the visualizer could display them — marginal features that did not justify modifying the core loop or extending the wire surface. Reverts the agent-core loop/type/export changes (restored to main, keeping #1209) and its changeset, and removes the vis-side rendering and types that consumed step.end.retries / tool.result.progress. The rest of vis is unchanged and reads only data agent-core already persists.	2026-06-30 13:40:37 +08:00
Kai	efdf8a1b2d	feat(vis): faithful wire.jsonl rendering + built-in kimi vis command (#788) ... * feat: polish vis * feat: add 'kimi vis' command for session visualization * fix(vis): drop metadata app_version/resumed removed upstream #786 stopped recording resume version metadata, so those fields no longer exist on the metadata wire record. The vis-into-typecheck wiring caught the stale field reads after merging main; drop them from the metadata headline. * fix(vis): drop unnecessary return-await in startVisServer oxlint typescript-eslint(return-await) flags returning an awaited promise outside try/catch; return the promise directly. * fix(vis): green CI — tolerate unbuilt embedded asset + bump nix pnpmDeps hash - handleVis: wrap the embedded-SPA dynamic import in try/catch. The value module is generated at build time (prebuild); in contexts without a build (tests run pnpm test, not build) only the .d.ts type stub exists, so the runtime import throws. Tolerate it and fall back to filesystem serving. - flake.nix: update the fetchPnpmDeps hash after adding the vis-web / vis-server / vite-plugin-singlefile dependencies. * refactor(vis): drop redundant alwaysBundle in tsdown config #775's single-entry build (codeSplitting: false) already bundles everything not declared in dependencies/peerDependencies. hono / @hono/node-server (transitive via vis-server) and @moonshot-ai/vis-server (a devDependency) are all undeclared there, so they bundle by default — the explicit alwaysBundle was redundant. Verified the emitted main.mjs is still fully self-contained and 'kimi vis' serves. * fix(vis): address review — context-token resets, IPv6 url, marker-safe indexing - contextTokens now mirrors agent-core on lifecycle records: 0 on context.clear, tokensAfter on context.apply_compaction (was only updated from step.end.usage, leaving a stale live fill after a clear/compaction). - start.ts brackets IPv6 hosts in the returned url (http://[::1]:port/); hostForUrl moved to config.ts and shared with the startup banner. - compaction slice + micro-compaction blanking now index over real history entries only, so synthetic undo/clear UI markers no longer offset agent-core's compactedCount / cutoff. * chore: add changeset for kimi vis command * fix(vis): cross-platform single-file build + history-count micro clamp - build-vis-asset.mjs sets VIS_SINGLEFILE via the spawn env and runs 'vite build' directly (cross-platform), instead of the POSIX-inline-env 'build:single' script that broke on Windows cmd; removed the now-unused build:single script. Fixes the win32 build path (the asset generator runs in the kimi-code prebuild + native bundle). - context.undo now clamps the micro-compaction cutoff by history-entry count (excluding synthetic undo/clear markers) instead of messages.length, mirroring agent-core undo() -> microCompaction.reset(_history.length); a surviving marker no longer leaves the cutoff one too high and wrongly blanks a later-appended tool result. * fix(vis): run the single-file build through a shell for Windows pnpm The win32 native binary is built on Windows runners (.github/workflows/_native-build.yml), which run this generator. pnpm's launcher there is pnpm.cmd, which a bare argv exec can't resolve without a shell. Use execSync with a single command string so the platform shell (cmd on Windows) resolves the shim; a command string (not an args array) avoids the args+shell deprecation. Args are static. * fix(vis): show model-facing tool result content in the context view agent-core normalizes tool results via toolResultOutputForModel before they enter history (error -> '<system>ERROR: ...' prefix, empty -> '<system>Tool output is empty.' sentinel). The projector was using the raw ev.result.output, so the Context tab's model view showed content the model never saw for failed/empty tool calls. Replicate that normalization (the upstream helper is module-private) so the projected tool message matches what the model received.	2026-06-16 16:54:14 +08:00
Kaiyi	842e699a64	Kimi For Coding	2026-05-22 15:54:50 +08:00