fix(agent-core): refuse multi-line empty Edit deletions - #2
Draft
mangeshraut712 wants to merge 21 commits into
Draft
fix(agent-core): refuse multi-line empty Edit deletions#2mangeshraut712 wants to merge 21 commits into
mangeshraut712 wants to merge 21 commits into
Conversation
…de highlighting (MoonshotAI#2415) * fix(web): upgrade markstream-vue to 1.0.9-beta.1 and enable Monaco code highlighting * fix(nix): update pnpm deps hash for markstream-vue 1.0.9-beta.1
…file registry extension point (MoonshotAI#2366) * feat(agent-core-v2): insert Workspace lifecycle scope and remove mutable cwd paths - Insert LifecycleScope.Workspace between App and Session - Delete session/workspaceCommand domain (addAdditionalDir) and node-sdk RPC - Remove profile cwd mutation; cwd is fixed at creation - Make ISessionWorkspaceContext read-only; seed additionalDirs at creation - Remove TUI and vscode /add-dir commands (to return workspace-scoped) * feat(agent-core-v2): add Workspace scope with handler-owned session lifecycle - Add IWorkspaceLifecycleService (App scope): handler registry, create-or-get handlerFor with inflight join - Add workspace/workspaceContext seed and workspace/workspaceHandler (session create/resume/fork as handler child scopes) - Delete App-level ISessionLifecycleService; callers compose index -> handlerFor -> handler via sessionLookup helpers - Slim IBootstrapService; persistence addressing via handler chain (disk layout byte-identical) - kap-server routes rewire internally; /api/v1 wire unchanged, debug surface gains workspace addressing - Pin red line in domain lint: session/agent must not import workspace domains * feat(agent-core-v2): collect workspace resources into the handler scope - Add Workspace-scope catalogs for skills and agent profiles, instructions service, and a shared MCP connection manager (built at materialization, refreshed by watch/plugin events) - Session catalogs keep their APIs but read seeded snapshots and refresh via change events; ISessionMcpService removed - Session create options carry no mcpServers; MCP sources are config file (wins on name conflicts) and plugins only - Agent profile/mcp consume the seeded providers * feat(agent-core-v2): restore add-dir as a workspace-level capability - Add workspace/workspaceDirs: shared additional-dir set with addDir({path, persist}); persist=true writes .kimi-code/local.toml, local.toml watch drives cross-process refresh - ISessionWorkspaceContext becomes a live read view fed by the ISessionWorkspaceInfo seed contract and change events - Restore Session.addAdditionalDir in kimi-code-sdk 1:1, mapping to the workspace service; restore TUI/vscode /add-dir verbatim * feat(agent-core-v2): collect os-level services into the workspace scope - Move fs service, fs watch (shared subscription fan-out), process runner, and a git facade to Workspace scope; sessionFs domain removed - Add IWorkspaceToolPolicy with workspace veto wired through tool activation, execution guard, composed evaluation, and profile prompt projection; injected via ISessionToolPolicyGate seed - kap-server fs routes and fs.watch bridge remap to the workspace services; wire unchanged * refactor(agent-core-v2): clean up workspace-domain leftovers and docs - Drop dead code: v2 mergeCallerMcpServers, the transitional ISessionContext.additionalDirs field, an unreachable guard - Fix stale domain references in comments; correct test names - Give the fs-watch refresh test a realistic wait budget under load - Document the four-scope model and workspace domain in AGENTS.md, agent-core-v2 docs, and the agent-core-dev skill * test(node-sdk): wait for the initial MCP connect to settle in the parity list test v1 connects in the background after create resolves while v2 awaits it inside create, so an immediate list can catch either side still pending under CI load * refactor(agent-core-v2): extract git work-tree discovery into the git domain - add the pure findGitWorkTree probe in app/git/workTree and expose it as IGitService.findWorkTree - switch the git permission policies off the local findLocalGitWorkTreeMarker helper to the DI service - reuse findGitWorkTree for AGENTS.md project-root discovery in agent/profile/context.ts - add findWorkTree coverage to gitService.test.ts * feat(kimi-inspect): add Workspace Services view - add WorkspaceServicesView rail view with a workspace picker on top; proxies resolve workspace-scope Services on the /workspace/:id route - extend ChannelScope, ServiceTarget, and ServicePanelDef scope with 'workspace', routed via client.workspace(id).service - wire the new view into NavRail and App * refactor(agent-core-v2): extract mcpCore and workspaceMcpConfig domains - move the scope-agnostic MCP connection layer (stdio/http/sse clients, connection manager, oauth, config schema, tool naming) from agent/mcp to the new mcpCore domain - move the [mcp] config section to app/mcpConfig and OAuth credential persistence to app/mcpConfig/oauthStore - introduce the workspace/workspaceMcpConfig domain owning the effective MCP server set (mcp.json files + plugin contributions, refreshed by fs watch); workspaceMcp keeps pure connection orchestration - update the plugin domain, session MCP handle, klient/node-sdk contracts, and tests accordingly * refactor(agent-core-v2): remove the fault-injection experimental feature - delete the faultInjection domain (flag definition, IFaultInjectionService contract, FaultInjectionService implementation) - drop the requester-side take() injection point and the constructor dependency from llmRequester - remove the flag-gated test cases and the IFlagService stub they needed - regenerate the state manifest without the faultInjection state keys * feat(agent-core-v2): gate project-level MCP config behind workspace trust Add the Workspace-scope IWorkspaceTrust service: an explicit, per-workspace trust marker persisted under the home (IAtomicDocumentStore, keyed by encodeWorkDirKey(root)) so a checked-out tree cannot pre-trust itself. While a workspace is untrusted, workspaceMcpConfig skips the project-level .mcp.json and .kimi-code/mcp.json files (user-level config and plugin contributions still load); a trust flip reuses the reload path, so project servers connect on trust and disconnect on untrust. Expose the state over kap-server REST: GET /workspaces/{id}/trust, POST /workspaces/{id}/trust, POST /workspaces/{id}/untrust. * feat(kimi-inspect): replace the workspace picker with a directory browser The Workspace Services view now keeps a server-side directory browser in a left sidebar (over IHostFolderBrowser) instead of a <select> of registered workspaces. Entries that are registered workspaces carry a workspace badge plus their IWorkspaceTrust trust state; selecting an unregistered folder registers it on demand via IWorkspaceService.createOrTouch. * fix(agent-core-v2): resolve the effective cwd into the profile binding A default-bound agent recorded no cwd in its profile.bind payload, and no caller configures ProfileServiceOptions.cwd, so the profile service's cwd getter fell through to '' and refreshSystemPrompt() rebuilt the prompt from the server process's cwd: an AGENTS.md edit dropped the workspace instructions (or swapped in unrelated ones). bind() now persists the resolved effective cwd (the input's, or the session's when the input omits it) into profile.bind — the Model's cwd stays creation-fixed and is always set. The getter's last resort is the session's own cwd (the value legacy bindings resolved against) instead of a bare ''. * refactor(agent-core-v2): introduce the contribution/registry/catalog extension point for agent profiles - App-scope IAgentProfileRegistry: any scope can register an AgentProfileContribution keyed by (sourceId, workspaceKey); dedup per source id, change events drive catalog re-projection - workspaceAgentProfileLoader domain owns agent-file discovery end to end (parse / roots / SYSTEM.md / explicit runtime files) with five Workspace-scope loaders (workspace / user / plugin / extra / explicit) tagged with the handler's workspaceId; internals live under internal/ - SessionAgentProfileCatalog projects the registry directly (name dedup, priority adjudication, builtin override rule, inspect()); the workspace-catalog + sessionData seed relay is gone - builtin code contributions register as the 'builtin' entry via BuiltinAgentProfileLoader; plugin agent roots are provided by the plugin domain as PluginAgentRoot - remove cwd from the profile binding chain (BindAgentInput / ProfileBindingSnapshot / AgentConfigData / ProfileModelState / profile.bind op) — it is always the session's frozen cwd; legacy wire.jsonl records replay fine (the schema strips the field) - share markdown frontmatter parsing via _base/text/frontmatter * fix(agent-core-v2): reconcile the workspace refactor with main - restore the branch's klient workspaceId scope extension lost to a file-level conflict resolution (main had no further changes there) - stub the plugin system-prompt dependencies main added to the profile service in the profileOps / skillCatalog tests - correct PLUGIN_SKILL_SOURCE_ID to the App skillSource domain (Agent scope must not import the Workspace domain) - kap-server workspaceLayout test supplies the now-required hostIdentity - regenerate wire/state/config manifests * fix(agent-core-v2): export the agent-file parse primitives the v2 print CLI consumes The internal/ split kept parseAgentFileText / resolveAgentPath off the package entry, but apps/kimi-code's v2 print runner imports them from @moonshot-ai/agent-core-v2 for --agent-file. Export the two symbols by name; everything else under internal/ stays domain-private. * feat(agent-core-v2): return cwd listing for empty fs:search query An empty fs:search query used to fail request validation (query had a minimum length of 1), so @-mention pickers had no starting set right after typing "@". The workspace fs service now answers an empty query with the workspace root's top-level entries — directories first, hidden entries excluded, gitignore and exclude_globs honored — mapped into the search-hit shape (score 1, empty match positions) and capped by limit. The mirrored protocol wire schema is relaxed in sync. * test: cover cron-fired steer context and titled session creation - agent-core-v2: e2e asserting a cron-fired steer turn carries earlier tool results (the CronCreate job id) into the provider request - klient: conformance case creating a titled session through implicit workspace materialization
…oonshotAI#2437) * feat(kap-server): let fs:search resolve a workspace ref for draft sessions - fs:search accepts a workspace id or absolute root in the session_id slot so the @ file mention works before the session exists - kimi-web searchFiles falls back to the active workspace id in draft state * fix(agent-core-v2): report empty thinking level for unbound main agent - sessionLegacyService.status returns thinking_level '' when the main agent has no bound model (mirroring model: undefined), so clients fall back to the catalog default instead of folding in the wire model's 'off' zero value - add regression test for a never-bound main agent status - add web changesets: draft @ file mention, new-session thinking level * perf(minidb): make text index rebuilds async and non-blocking - TextIndex.build() yields to the event loop during tokenization and batches postings writes (~1 MiB), so large rebuilds no longer hard-block the host process - writes landing mid-build are queued and replayed onto the new base at swap time, keeping the rebuilt index exact - PostingsFile.rebuildSync renamed to async rebuild with a synchronous commit section (beforeRename hook + atomic rename) - onCompacted hook is now awaited (sync or async); open-time compaction runs in the background so open() returns without blocking on the snapshot rewrite and postings rebuild - compaction skips the postings rebuild when the index's write buffer is clean (needsRebuild) - createTextIndex registers before building so concurrent writes feed the build queue; dropTextIndex throws while a build is in flight * refactor(agent-core-v2): rename workspaceHandler to sessionLifecycle - rename IWorkspaceHandlerService to ISessionLifecycleService and move src/workspace/workspaceHandler/ to src/workspace/sessionLifecycle/; update all consumers (gateway, sessionExport, sessionLegacy, sessionLookup, kap-server, klient, node-sdk, kimi-inspect, kimi-code) - rename IStateService to IAppStateService and add the Workspace-scope IWorkspaceStateService, so the state domain spans all four scope tiers - add cascading StateRegistry.inspect(): each tier injects the parent tier's registry and folds App to current scope into one StateInspection tree; check-domain-layers gains a Rule 2b exemption for state-on-state imports * feat(kap-server): add session-less POST /workspace/fs:search route Carry the workspace reference (registered id or absolute root) in the request body and resolve it to the same Workspace-scope fs service the session route uses, so clients no longer borrow the session route's {session_id} slot. kimi-web's @ file mention now calls this route with the workspace ref instead of a session id; the session-route fallback stays for wire compatibility. * refactor(agent-core-v2): register workspace-scope service state into IWorkspaceStateService - move workspaceDirs / workspaceInstructions / workspaceSkillCatalog / workspaceTrust runtime state from bare instance fields into the workspace state container - extend gen-state-manifest.mts to scan app/workspace scopes, emitting AppStateSnapshot / WorkspaceStateSnapshot alongside Session/Agent - regenerate docs/state-manifest.d.ts and update AGENTS.md + agent-core-dev skill - update affected tests to register the state services and assert the new state keys
…econdary-model experiment is off (MoonshotAI#2449) The Agent/AgentSwarm tool schemas always advertised a \`model\` choice parameter, so the secondary-model concept entered the prompt even with the experiment disabled. Gate the advertised JSON schema on the flag in both engines: off (the default) drops the parameter, on keeps it, and spawn-time resolution already falls back to the caller's model either way. Also scrub ambient KIMI_CODE_EXPERIMENTAL_* env vars in both packages' vitest setup so flag-dependent tool schemas in llm.tools_snapshot stay deterministic regardless of the developer shell.
… surfaces (MoonshotAI#2125) * web: reorder default permission options in Agent settings Align the Agent settings default-permission segmented control with the Composer toolbar order, arranging modes from safest (manual) to most permissive (auto). * web: reorder mobile permission cycle from safest to most permissive The mobile settings sheet still cycled manual → auto → yolo, jumping from the safest mode straight to the most permissive one on a single tap. Align the tap-to-cycle order with the Composer menu and Agent settings (manual → yolo → auto). * web: align permission risk colors with the Composer's progression Both the desktop status panel and the mobile settings sheet mapped yolo → danger and auto → warning, the inverse of the Composer menu (yolo → warning, auto → danger). Since auto is the most permissive mode, it should carry the danger color everywhere. --------- Co-authored-by: qer <wbxl2000@outlook.com>
…p comment conventions (MoonshotAI#2451) * refactor(agent-core-v2): move workspace-domain internals into internal/ dirs - move sessionLifecycle/addressing into internal/ - move workspaceFs errors/fsProcess/fsSearch/rgLocator/runRg into internal/ - move workspaceMcpConfig/config-loader into internal/ - update import paths in services, index.ts, and tests * docs(agent-core-v2): strip non-header comments, make headers file-local - remove all symbol JSDoc and inline // and /* */ comments under src/; file-top header comments and directive comments (eslint, @ts-*) are kept - rewrite file headers to describe only what the file itself does, dropping references to other files and see-X / lives-in / consumed-by relationships - no code changes * refactor(agent-core-v2): remove the L0-L7 domain layering and its lint guard - replace check-domain-layers.mjs with check-import-boundaries.mjs, keeping only the v1-import ban and the kosong subtree rules - rename the lint:domain package script to lint:imports - drop the (Ln) layer label from every file-header identity line - update AGENTS.md, package docs, and the agent-core-dev skill to match
…nshotAI#2453) * feat(node-sdk): expose workspace trust state and trust grant on the v2 client * feat(tui): ask for workspace trust on startup with the v2 engine
…nshotAI#2457) * feat(agent-core-v2): persist the terminal turn.ended wire record - add a persisted turn.ended op (turnId, reason, error, durationMs) dispatched from the loop's runTurn finally block, alongside the event - fold the record back in the transcript cold rebuild: terminal state (blocked folded into failed, mirroring the live wire edge), durationMs, error message and endedAt; journals without the record keep the grouping default - restrict the test harness's snapshot waiters to emit entries so the same-named wire record no longer shadows the turn.ended event * chore(agent-core-v2): stabilize unique-symbol keys in the state manifest The checker names a unique symbol key __@name@NNNN, where NNNN is a compilation-global counter that shifts with unrelated type additions and churns the generated manifest. Render the stable __@name form instead. * fix(transcript): map turn.ended around hidden turns in the cold fold RetryStepRequest opens a real engine turn with origin 'retry' but contributes no context messages, and a queued-then-cancelled reservation consumes an engine id without starting. Both make engine turn ids drift from the grouping ordinals, so matching turn.ended by ordinal could stamp a later visible turn with the wrong terminal state. Replay the loop's turn-clock records (turn.prompt / turn.cancel) and map engine ids to ordinals past the hidden ids; the hidden turns' own end records map nowhere and are dropped.
MoonshotAI#2460) * fix(agent-core-v2): resolve package self-references in check-import-boundaries Imports spelled @moonshot-ai/agent-core-v2/<path> (the legal `./*` export self-reference) were treated as external packages, letting kosong layer violations through that spelling pass the checker. * refactor(agent-core-v2): move host runtime args onto IBootstrapService - Add HostArgs under BootstrapInput.args / IBootstrapService.args (agentFiles, skillDirs, requestHeaders, displayName, replyStyleGuide), mirroring VS Code's NativeParsedArgs on the environment service - Remove the narrow per-domain runtime-options services and their seed functions: IAgentCatalogRuntimeOptions, ISkillCatalogRuntimeOptions, IHostIdentity - Reduce IHostRequestHeaders to a pure kosong port contract and bridge it from bootstrap args via a new app/kosongConfig adapter, keeping kosong free of app-layer imports - Pass host args through bootstrap() at the composition roots (kap-server, v2 print CLI, node-sdk) instead of seeding services - Persist SDK provider removal as one atomic multi-section config replace * fix(config): persist provider refresh updates atomically - expose atomic multi-section config replacement through klient and SDK - stage provider removals before one atomic write in TUI refresh - briefly drain startup refresh during shutdown
… context (MoonshotAI#2326) Co-authored-by: rickgao <rickgao@tencent.com> Co-authored-by: qer <wbxl2000@outlook.com>
…oonshotAI#2400) * feat(agent-core-v2): interruption reminder for user-cancelled turns When the user interrupts a turn with Esc, append a durable <system-reminder> (origin: injection/interruption) to the agent context via a new loop aspect watching turn.ended, so the model learns the previous turn was deliberately cut off. The marker persists to the wire, replays on resume, stays hidden from transcripts, skips non-user aborts and steer, and does not stack on repeated cancels. Two supporting fixes: - An aborted LLM stream now persists its accumulated partial text/thinking as content.part loop events instead of dropping every produced token; gated on the turn signal so retried or step-cancelled attempts keep their partial output out of the record. - The turn.cancel wire op carries an optional reason ('user_cancelled' | 'aborted') so cold readers can tell deliberate interrupts from programmatic aborts. Goal-lifecycle cancels now pass an explicit programmatic reason to keep that field honest. * feat(transcript): mark user-cancelled turns with an interruption marker Project the deliberate user interrupt onto the transcript timeline: the live projector emits an 'interruption' marker when a turn ends with interruptReason 'user_cancelled', and the cold fold consumes the persisted turn.cancel reason into the same marker. Programmatic aborts keep surfacing through their own outlets (errors, goal/task state), and queued cancels that left no visible residue are skipped. * fix(agent-core-v2): make user-turn cancellation idempotent and reconcile interruption reminders on restore * fix(transcript): dedupe user-cancelled interruption markers by turn in the cold fold * chore(agent-core-v2): regenerate state manifest after merging main * refactor(agent-core-v2): split interruptionReminder out of the loop domain The loop domain owns turn execution mechanics; whether an interrupted turn should produce a model-visible reminder is a model-context policy. Move it into its own L4 domain with its own wire model that cross-reduces the loop's turn.cancel fact, and rename the op to interruptionReminder.recorded. --------- Signed-off-by: Haozhe <yanghaozhe@moonshot.ai> Co-authored-by: Haozhe <yanghaozhe@moonshot.ai>
MoonshotAI#2459) * fix(web): restore chat code block styling after the markstream upgrade markstream-vue 1.0.9 renders shiki code blocks through stream-diffs (code-editor-container) instead of <pre>, and drives font size, line height, and font family from monacoOptions applied as inline styles. With only lineNumbers passed, blocks fell back to 12px/18px in the inherited proportional UI font, and the pre/copy-button/content CSS overrides in Markdown.vue no longer matched anything. Pass fontSize/lineHeight/fontFamily/padding through codeBlockProps monacoOptions (the only channel that reaches the shiki renderer), retarget the dead overrides to code-block-shell-content and code-action-btn, and hide the loading fallback's hardcoded line-number gutter so the highlight upgrade no longer shifts layout. * fix(web): keep code block metrics in sync * fix(web): pin chat code font to 13px and align the loading fallback Tying the code font size to the Appearance UI font size setting changed the default rendering from the 13px design token to 14px and broke the 15/14/13 type scale; revert to the fixed token size. Keep the fallback ↔ settled alignment: the restored monaco padding option feeds the fallback pre's inline padding (12px, ignored by the shadow-root renderer), and a relative 1.65 line-height with !important beats the inline 1.5x default upstream stamps on the fallback. * chore(web): pin markstream-vue and its renderer stack to exact versions The markstream family ships breaking rendering changes in patch releases (1.0.8 swapped the code-block engine and renamed its DOM classes), so a floating caret range hands merge control to upstream. Pin markstream-vue, stream-diffs, stream-markdown and stream-monaco exactly — upgrades become deliberate actions with a visual check, same posture as @chenglou/pretext in the same file.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
…oonshotAI#2416) When the remote models.dev catalog cannot be fetched, fall back to the built-in catalog so CLI/TUI model selection keeps working offline or under network failure. Import the shared helper via the #/utils alias.
Co-authored-by: StaR4y <star4y@origin.pw> Co-authored-by: qer <wbxl2000@outlook.com>
Guard Edit against accidental +0/−N wipeouts when new_string is empty across 3+ lines unless allow_large_delete is set. Strengthen the old_string-not-found recovery guidance so the model rereads a large enough region instead of looping short Reads (fixes MoonshotAI#2427).
Update inline tools_snapshot hashes for allow_large_delete on the Edit tool.
cursor
Bot
force-pushed
the
cursor/fix-edit-refuse-large-delete-7813
branch
from
August 1, 2026 18:20
097b177 to
eb224a2
Compare
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
9 participants
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.
Related Issue
Resolve MoonshotAI#2427
Problem
See linked issue. After
old_string not found, the model often retries Edit from a short Read window and can wipe multi-line sections with emptynew_stringreplacements.What changed
allow_large_delete=true(v1 + v2).tools_snapshothashes after the Edit schema change.main.Upstream: MoonshotAI#2511
Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.