From 7feaf619cf0ec021d66be14ef535cf2149bec58a Mon Sep 17 00:00:00 2001 From: hugocasa Date: Mon, 7 Sep 2026 19:04:38 +0200 Subject: [PATCH] feat: run a linked AI agent's draft when testing a flow, and offer to deploy it (#10993) * feat(frontend): run a linked agent's draft when testing a flow, and offer to deploy it Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): settle an agent's autosave before reading it, and refresh its card on a draft save Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): deploy the agent draft that was validated, and make the draft-tools flag explicit Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): refuse a stale agent deploy, and warn when a never-deployed agent is kept as a draft Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * docs: record what inlining an agent draft puts in a preview job Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): name the draft-changes dialog after what it lists Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): refuse a draft deploy when the draft row is gone Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): apply the missing-draft refusal to raw apps too Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): stop reading a deployed resource row as a draft on deploy Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): do not mistake an outage or a vanished draft for a deploy Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): refuse an agent read whose pending draft save failed Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): space the trigger badges and right-align the agent actions Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): surface a failed agent-draft read instead of dropping it Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): give the agent draft delete a baseline so a newer edit survives Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): drop the agent draft cell locally instead of deleting twice Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * test(frontend): pass the withDraft flag the guard tests were missing Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * refactor(frontend): deploy agent drafts the way Review & Deploy does Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): give the read-only flow graph its own linked-tools bucket Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): base the resource draft delete on the read that promoted it Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): refresh every step linking an agent when its draft is saved Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * fix(frontend): write nothing at all when a resource draft has gone Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp * test(frontend): pin that the resource draft delete follows its baseline seed Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_017B4omp8dRgmLitbpQEqFMp --------- Co-authored-by: Claude Opus 5 (1M context) --- docs/reusable-ai-agents.md | 48 ++- .../src/lib/components/FlowBuilder.svelte | 150 ++++++-- .../src/lib/components/FlowGraphViewer.svelte | 19 +- .../FlowLoopIterationPreview.svelte | 26 +- .../components/FlowStatusViewerInner.svelte | 4 +- frontend/src/lib/components/ModuleTest.svelte | 40 ++- .../src/lib/components/ScriptBuilder.svelte | 4 +- .../DraftChangesConfirmationModal.svelte | 323 ++++++++++++++++++ .../DraftTriggersConfirmationModal.svelte | 168 --------- .../lib/components/flows/agentDraft.svelte.ts | 177 ++++++---- .../flows/agentEditorStore.svelte.ts | 24 ++ .../lib/components/flows/agentTelemetry.ts | 4 + .../flows/content/AgentEditorHost.svelte | 14 +- .../flows/content/AgentEditorModal.svelte | 4 +- .../flows/content/AgentResourceBar.svelte | 107 +++++- .../src/lib/components/flows/flowState.ts | 34 +- .../flows/linkedAgentDrafts.test.ts | 148 ++++++++ .../lib/components/flows/linkedAgentDrafts.ts | 229 +++++++++++++ .../flows/linkedToolsFetchGuard.test.ts | 12 +- .../src/lib/components/flows/utils.svelte.ts | 16 +- frontend/src/lib/userDraft.svelte.ts | 26 ++ frontend/src/lib/utils_draft_deploy.test.ts | 71 +++- frontend/src/lib/utils_draft_deploy.ts | 60 +++- 23 files changed, 1369 insertions(+), 339 deletions(-) create mode 100644 frontend/src/lib/components/common/confirmationModal/DraftChangesConfirmationModal.svelte delete mode 100644 frontend/src/lib/components/common/confirmationModal/DraftTriggersConfirmationModal.svelte create mode 100644 frontend/src/lib/components/flows/linkedAgentDrafts.test.ts create mode 100644 frontend/src/lib/components/flows/linkedAgentDrafts.ts diff --git a/docs/reusable-ai-agents.md b/docs/reusable-ai-agents.md index 8383bc2836..ede8f64b1d 100644 --- a/docs/reusable-ai-agents.md +++ b/docs/reusable-ai-agents.md @@ -22,22 +22,54 @@ every workspace via the standard cached-resource-type sync, like other built-in or flow expressions), so saving round-trips losslessly. Each host flow overrides what it needs: `tool_inputs` stores per-tool overrides (a diff from the resource tool's own transforms) that overlay onto the matching tools at runtime. Editing on a linked step edits - the flow's use of the agent; editing under the "Editing" banner edits the agent itself. + the flow's use of the agent; editing in the agent editor edits the agent itself. In the flow editor, the AI agent step's **Step Input** tab shows a single read-only card (*linked to *, with the inherited brain + tools and an explanatory tooltip) plus -*Edit* (fork into the editable step, Save changes upserts back and re-links) and *Unlink* -(fork the resolved config — including any `tool_inputs` — back into the step as a one-off). -While editing, the step is the only copy of the edits: Cancel drops them and re-links (asking -first when there is something to drop), and the unsaved-changes badge opens a diff against the -deployed agent whose Discard changes is Cancel without the question. What a fork is an edit of, -and the deployed baseline the edits are judged against, live in `agentEditStore` (in memory), so -a reload brings the step back as a standalone agent with no path to save back to. +*Edit*, which opens the agent editor over the flow, and *Unlink* (fork the resolved config — +including any `tool_inputs` — back into the step as a one-off). A linked agent's tools appear as display-only graph tool nodes (clicking one selects the agent step); below the step's inputs, each tool gets a section with the standard schema-aware input editors (prop picker included) and a read-only view of its code — edits persist into `tool_inputs`. +## Drafts + +The agent editor edits the resource through a **per-user resource draft** (`draft` table, +`item_kind = 'resource'`), autosaved by `useAgentDraft` and deployed by the editor's own Deploy +button. It is the same draft row the generic resource editor writes and the Review & Deploy page +lists, so an agent can be deployed from any of them. + +A flow does not wait for that deploy to see the draft: + +- Testing the flow, or a single linked step, runs the draft. `runFlowPreview` and `ModuleTest` + substitute each linked step for the standalone step the draft would run as + (`linkedAgentDrafts.ts`): `agent` cleared, the draft's brain as static input transforms, the + draft's tools on the step, and the step's own `user_message`/`user_attachments` kept on top — + the same overlay order `ai_executor.rs` applies to a linked step. `tool_inputs` is untouched, + since the worker overlays it in both branches. +- The step's linked card and the graph's tool nodes show the draft, with a *Draft* badge, so the + editor describes what a test would run. Read-only surfaces (the deployed flow page, the run + viewer) stay on the deployed agent: they resolve tools through `publishLinkedAgentTools` without + the draft flag. +- Deploying the flow lists every linked agent that has a draft in the confirmation dialog, beside + the draft triggers. Deploying one writes the resource and drops the draft; leaving one out keeps + its draft untouched, and the flow runs the agent as currently deployed. That is the one place + the two kinds differ: an undeployed draft trigger is deleted, because it belongs to the flow, + while an agent draft belongs to a resource other flows also use. + +Because a draft is per-user, a flow test can behave differently for two people looking at the same +flow. That is the same contract as a flow draft, and deploying the agent is what makes it shared. + +Inlining has a consequence worth knowing: a preview job's `raw_flow` then carries the agent's +config, where a linked step used to carry only the path and leave the resolution to the worker. So +an agent's prompt and tool set are readable by whoever can read that preview job, which is a wider +set than whoever can read the resource when the agent sits in a more restricted folder than the +flow. No credential travels with it — the provider stays a `$res:` reference, resolved at run time +as the runner. The agent editor's own test pane has inlined the same way since drafts existed; +closing the gap would mean the preview carrying a draft *reference* the worker resolves, rather +than the config. + Sharing works through standard resource folder permissions (save agents under `f/...`). Only the agent's brain is interpolated when the step runs. A tool's own `$res:`/`$var:` defaults are diff --git a/frontend/src/lib/components/FlowBuilder.svelte b/frontend/src/lib/components/FlowBuilder.svelte index 52af60d7a7..b8a2d4a9e6 100644 --- a/frontend/src/lib/components/FlowBuilder.svelte +++ b/frontend/src/lib/components/FlowBuilder.svelte @@ -98,7 +98,18 @@ import { invalidateWorkspacePaths } from './PathNameAutocomplete.svelte' import type { Trigger } from './triggers/utils' import { deployTriggers, handleSelectTriggerFromKind } from './triggers/utils' - import DraftTriggersConfirmationModal from './common/confirmationModal/DraftTriggersConfirmationModal.svelte' + import DraftChangesConfirmationModal from './common/confirmationModal/DraftChangesConfirmationModal.svelte' + import { + agentDraftCanWrite, + linkedAgentPaths, + loadLinkedAgentDrafts, + type LinkedAgentDraft + } from './flows/linkedAgentDrafts' + import { agentDraftDeployRefusal } from './flows/agentDraft.svelte' + import { markAgentWritten } from './flows/agentEditorStore.svelte' + import { logReusableAgentUsage } from './flows/agentTelemetry' + import { deployDraft } from '$lib/utils_draft_deploy' + import { getUserExt } from '$lib/user' import { Triggers } from './triggers/triggers.svelte' import { StepsInputArgs } from './flows/stepsInputArgs.svelte' import { aiChatManager } from './copilot/chat/AIChatManager.svelte' @@ -192,8 +203,16 @@ let confirmCallback: () => void = $state(() => {}) // What happens when user clicks `override` in warning let open: boolean = $state(false) // Is confirmation modal open - // Draft triggers confirmation modal - let draftTriggersModalOpen = $state(false) + // Draft changes (triggers + linked agents) confirmation modal + let draftChangesModalOpen = $state(false) + /** The unsaved agent drafts the pending deploy found. Loaded rather than derived: it takes a + * request per linked agent, so it is resolved when the deploy asks. */ + let draftAgents = $state([]) + let agentCanWrite = $state>({}) + let agentRefusal = $state>({}) + + /** What the dialog's confirm hands back to `saveFlow`. */ + type DraftChangesToDeploy = { triggers: Trigger[]; agents: LinkedAgentDraft[] } // Top-bar responsive collapse. Measured via bind:clientWidth — we can't // rely on viewport `md:` because the editor lives inside other panes @@ -224,7 +243,7 @@ ] : [] ) - let confirmDeploymentCallback: (triggersToDeploy: Trigger[]) => void = () => {} + let confirmDeploymentCallback: (toDeploy: DraftChangesToDeploy) => void = () => {} // AI changes warning modal let aiChangesWarningOpen = $state(false) @@ -236,11 +255,57 @@ const job: Job | undefined = $derived(flowPreviewContent?.getJob()) let showJobStatus = $state(false) - async function handleDraftTriggersConfirmed(event: CustomEvent<{ selectedTriggers: Trigger[] }>) { - const { selectedTriggers } = event.detail + async function handleDraftChangesConfirmed( + event: CustomEvent<{ selectedTriggers: Trigger[]; selectedAgents: LinkedAgentDraft[] }> + ) { + const { selectedTriggers, selectedAgents } = event.detail // Continue with saving the flow - draftTriggersModalOpen = false - confirmDeploymentCallback(selectedTriggers) + draftChangesModalOpen = false + confirmDeploymentCallback({ triggers: selectedTriggers, agents: selectedAgents }) + } + + /** Deploy each selected agent's draft, the same way the Review & Deploy page deploys the same + * row: hand the path to `deployDraft` and let it promote whatever the draft holds, with no + * re-read to check it still matches what the dialog listed. Agents left out keep their draft + * untouched. */ + async function deployAgentDrafts(agents: LinkedAgentDraft[]) { + const ws = opWorkspace + if (!ws) return + for (const listed of draftAgents) { + // Only the rows the dialog gave a choice on. A `Read-only` or `Invalid config` agent can + // never be selected, so counting it as "kept" would record a decision the user was never + // offered and bias the pair towards keeping. + const selectable = agentCanWrite[listed.path] !== false && !agentRefusal[listed.path] + if (selectable && !agents.some((a) => a.path === listed.path)) { + logReusableAgentUsage('draft_kept_on_deploy') + } + } + for (const agent of agents) { + // Writes the resource, deletes the draft row, and clears the local hint and the workspace + // drafts cache. A failure aborts the flow save the way a failing trigger does, rather than + // deploying a flow against agents that were meant to change with it. + const deployed = await deployDraft('resource', agent.path, ws, { + draftOnly: agent.noDeployed + }) + if (!deployed.success) { + throw new Error(`Could not deploy agent ${agent.path}: ${deployed.error}`) + } + // Nothing was promoted: the draft had gone by the time the helper read it. Saying the agent + // deployed would be a lie about the one thing the toggle decides. + if (deployed.noop) { + throw new Error( + `The draft for ${agent.path} was deployed or discarded elsewhere while this deploy ran, so nothing was written for it.` + ) + } + // `deployDraft` deletes the server row but leaves any in-memory cell for this key, and that + // cell is what `agentDraftState` prefers — a still-mounted holder would otherwise keep + // feeding a phantom draft to the cards and to the next deploy dialog. Local only: `remove` + // would POST a second delete, debounced and past the baseline the first one cleared. + UserDraft.forgetLocal('resource', agent.path, { workspace: ws }) + // Every linked card and the graph key on this to refetch the agent they display. + markAgentWritten(ws, agent.path) + logReusableAgentUsage('draft_deployed_with_flow') + } } // Inside an AI session pane (SessionEditorTarget injects an aiChatManager via @@ -429,18 +494,53 @@ deployedBy = flow.edited_by } - async function saveFlow(deploymentMsg?: string, triggersToDeploy?: Trigger[]): Promise { - if (!triggersToDeploy) { - // Check if there are draft triggers that need confirmation + async function saveFlow(deploymentMsg?: string, toDeploy?: DraftChangesToDeploy): Promise { + if (!toDeploy) { + // Draft triggers and drafts on the agents this flow links: both are unsaved changes the + // deploy would otherwise leave behind, so they are confirmed together. const draftTriggers = triggersState.triggers.filter((trigger) => trigger.draftConfig) - if (draftTriggers.length > 0) { - draftTriggersModalOpen = true - confirmDeploymentCallback = async (triggersToDeploy: Trigger[]) => { - await saveFlow(deploymentMsg, triggersToDeploy) + try { + draftAgents = [ + ...( + await loadLinkedAgentDrafts(linkedAgentPaths(flowStore.val.value), opWorkspace) + ).values() + ] + } catch (err: any) { + // This runs before the try below, and `withAIChangesWarning` invokes its callback without + // awaiting, so a rejection here would be unhandled: the button would do nothing at all, + // with no toast and no `onDeployError`. Report it the way the rest of the save does. + // Deploying anyway is not the fallback — this throws only when an agent's unsaved changes + // cannot be read, which is exactly when the dialog must not claim there are none. + onDeployError?.({ error: err }) + sendUserToast(`The flow could not be saved: ${err?.body ?? err}`, true) + return + } + agentCanWrite = {} + agentRefusal = {} + if (draftAgents.length > 0) { + // One lookup for the whole list: an agent lives in a folder, and the groups and admin + // flag that answer for it are per workspace, so the nav user would answer for the wrong + // membership when a session editor operates on another workspace. + const user = await getUserExt(opWorkspace ?? '').catch(() => undefined) + agentCanWrite = Object.fromEntries( + draftAgents.map((a) => [a.path, agentDraftCanWrite(a, user ?? $userStore ?? undefined)]) + ) + // The path is passed, so a draft that renames the agent is refused here too: a rename is + // the resource editor's to deploy, and this dialog lists the agent under the path the + // flow links. + agentRefusal = Object.fromEntries( + draftAgents.map((a) => [a.path, agentDraftDeployRefusal(a.state, a.path)]) + ) + } + if (draftTriggers.length > 0 || draftAgents.length > 0) { + draftChangesModalOpen = true + confirmDeploymentCallback = async (confirmed: DraftChangesToDeploy) => { + await saveFlow(deploymentMsg, confirmed) } return } } + const triggersToDeploy = toDeploy?.triggers loadingSave = true try { @@ -471,6 +571,11 @@ // loadingSave = false // del // return + // Ahead of the flow itself, as the update branch deploys its triggers: an agent is a + // resource of its own, so the flow should land on top of the agent set it was tested + // against rather than the other way round. + await deployAgentDrafts(toDeploy?.agents ?? []) + // `newFlow` comes from the embedder, and updating a path that has no // deployed flow 404s. Confirm with the server before taking the update // branch so a first deploy still lands. @@ -648,7 +753,7 @@ const resolved = linkedAgentToolsForScope(to) for (const [moduleId, agentPath] of linkedAgentEntries(linkedAgentRefs)) { if (resolved[moduleId] === undefined) { - publishLinkedAgentTools(agentPath, ws, to, moduleId) + publishLinkedAgentTools(agentPath, ws, to, moduleId, true) } } } @@ -716,7 +821,7 @@ // writing overrides against — the tool ids of the agent that was just replaced. claimLinkedToolsFetch(scope, moduleId) clearLinkedAgentTools(scope, moduleId) - publishLinkedAgentTools(agentPath, ws, scope, moduleId) + publishLinkedAgentTools(agentPath, ws, scope, moduleId, true) } publishedAgentByModule = next }) @@ -1343,14 +1448,17 @@ currentValue={flowStore.val} /> - t.draftConfig)} + {draftAgents} + {agentCanWrite} + {agentRefusal} isFlow={true} on:canceled={() => { - draftTriggersModalOpen = false + draftChangesModalOpen = false }} - on:confirmed={handleDraftTriggersConfirmed} + on:confirmed={handleDraftChangesConfirmed} /> diff --git a/frontend/src/lib/components/FlowGraphViewer.svelte b/frontend/src/lib/components/FlowGraphViewer.svelte index 47da29bb57..945533bcc8 100644 --- a/frontend/src/lib/components/FlowGraphViewer.svelte +++ b/frontend/src/lib/components/FlowGraphViewer.svelte @@ -67,6 +67,14 @@ const dispatch = createEventDispatcher() + // A bucket of this viewer's own, never the editor's. Both are keyed by (workspace, flow path), so + // a viewer mounted over the flow being edited — the version-history drawer, which renders the + // same path — would otherwise publish its deployed tools into the editor's bucket and replace the + // drafted tool nodes there. The editor's graph has to keep showing the tools a preview would + // actually run, and nothing republishes when the drawer closes. `FlowStatusViewerInner` scopes + // itself the same way, with `job:`. + let linkedToolsPath = $derived(`view:${flow?.path ?? ''}`) + // This read-only viewer doesn't run initFlowState, so linked agents' tools would otherwise never // resolve. Resolve them for display, keyed by module id. Best-effort: publishLinkedAgentTools // swallows access errors and publishes [], so an inaccessible agent simply shows no tool nodes @@ -80,7 +88,15 @@ for (const m of modules) { const value = m?.value as { type?: string; agent?: string } | undefined if (value?.type === 'aiagent' && value.agent) { - publishLinkedAgentTools(value.agent, ws, linkedToolsScope(ws, flow?.path), m.id) + // Without the draft: this viewer shows a deployed flow or a past run, both of which + // used the deployed agent. + publishLinkedAgentTools( + value.agent, + ws, + linkedToolsScope(ws, linkedToolsPath), + m.id, + false + ) } } }) @@ -101,6 +117,7 @@ earlyStop={flow?.value?.skip_expr !== undefined} cache={flow?.value?.cache_ttl !== undefined} path={flow?.path} + {linkedToolsPath} {download} minHeight={fillAvailableHeight ? Math.max(minHeight, availableHeight) : minHeight} {workspace} diff --git a/frontend/src/lib/components/FlowLoopIterationPreview.svelte b/frontend/src/lib/components/FlowLoopIterationPreview.svelte index 1378e20f04..0a4f5c60ee 100644 --- a/frontend/src/lib/components/FlowLoopIterationPreview.svelte +++ b/frontend/src/lib/components/FlowLoopIterationPreview.svelte @@ -5,6 +5,7 @@ import { createEventDispatcher, getContext } from 'svelte' import type { FlowEditorContext } from './flows/types' import { runFlowPreview } from './flows/utils.svelte' + import { sendUserToast } from '$lib/toast' import SchemaForm from './SchemaForm.svelte' import FlowStatusViewer from '../components/FlowStatusViewer.svelte' import FlowProgressBar from './flows/FlowProgressBar.svelte' @@ -101,15 +102,22 @@ // The preview flow holds only the loop body, so it inherits none of the flow's settings: // carry the tag over so the iteration lands on the worker group the flow runs on. const newFlow = { value: { modules }, summary: '', tag: flowStore.val.tag } - jobId = await runFlowPreview( - whileLoop ? withWhileLoopIter(args) : args, - newFlow, - $pathStore, - restartedFrom, - undefined, - undefined, - opWorkspace?.() - ) + try { + jobId = await runFlowPreview( + whileLoop ? withWhileLoopIter(args) : args, + newFlow, + $pathStore, + restartedFrom, + undefined, + undefined, + opWorkspace?.() + ) + } catch (err: any) { + // `runFlowPreview` resolves a linked agent's draft first and refuses when it cannot be read. + // Without this the rejection is unhandled and the button just does nothing. + sendUserToast(`Could not run preview: ${err?.body ?? err}`, true) + return + } isRunning = true } diff --git a/frontend/src/lib/components/FlowStatusViewerInner.svelte b/frontend/src/lib/components/FlowStatusViewerInner.svelte index 96b6eed293..3b860dc3a1 100644 --- a/frontend/src/lib/components/FlowStatusViewerInner.svelte +++ b/frontend/src/lib/components/FlowStatusViewerInner.svelte @@ -294,7 +294,9 @@ untrack(() => { for (const entry of refs ? refs.split('\u0001') : []) { const [moduleId, agentPath] = entry.split('\u0000') - publishLinkedAgentTools(agentPath, ws, scope, moduleId) + // Without the draft: this viewer describes a run that has already happened, and it ran + // the deployed agent. + publishLinkedAgentTools(agentPath, ws, scope, moduleId, false) } }) }) diff --git a/frontend/src/lib/components/ModuleTest.svelte b/frontend/src/lib/components/ModuleTest.svelte index b4e82ced2f..64a318acc7 100644 --- a/frontend/src/lib/components/ModuleTest.svelte +++ b/frontend/src/lib/components/ModuleTest.svelte @@ -14,6 +14,14 @@ import JobLoader, { type Callbacks } from './JobLoader.svelte' import { getStepHistoryLoaderContext } from './stepHistoryLoader.svelte' import { loadSchemaFromModule } from './flows/flowInfers' + import { + inlineAgentDraft, + loadLinkedAgentDrafts, + normalizeAgentRef, + type LinkedAgentDraft + } from './flows/linkedAgentDrafts' + import { AGENT_FLOW_LOCAL_KEYS } from './flows/agentResourceUtils' + import { sendUserToast } from '$lib/toast' interface Props { mod: FlowModule @@ -138,7 +146,35 @@ } else if (val.type == 'aiagent') { const { schema } = await loadSchemaFromModule(mod, opWs) - const agentVal = val + // A linked step whose agent has an unsaved draft is tested as the draft, the same way the + // whole-flow preview and the agent editor's own test pane run it. `inlineAgentDraft` + // clears `agent` and moves the draft's brain and tools onto the step, so the branches + // below then treat it as a standalone agent. + let draft: LinkedAgentDraft | undefined + if (val.agent) { + const linked = normalizeAgentRef(val.agent) + try { + draft = (await loadLinkedAgentDrafts([linked], opWs)).get(linked) + } catch (err: any) { + // The load refuses when the agent's unsaved changes cannot be read, and this function's + // caller neither awaits nor catches: without this the rejection is unhandled and the + // button appears to do nothing, with the test already marked as started. + sendUserToast(`Could not run test: ${err?.body ?? err}`, true) + // Guarded like every other access to it here: the entry is only created for steps the + // panel is tracking, and this runs on a path where it may never have been. + if (modulesTestStates.states[mod.id]) { + modulesTestStates.states[mod.id].loading = false + } + return + } + } + const agentVal = draft ? inlineAgentDraft(val, draft.args) : val + + // `args` is built from the whole AI agent schema whatever the step is, so on a linked step + // it carries every brain key as undefined even though the form renders only the flow-local + // ones (`flowLocalAgentSchema`). Overlaying those would shadow the brain the draft just + // supplied with nothing, so an inlined step takes only the inputs its form actually offers. + const formKeys = draft ? (AGENT_FLOW_LOCAL_KEYS as readonly string[]) : Object.keys(args) // The test form only covers the schema it was given, and for a standalone agent that may be // the flow-local one (the agent editor shows the brain in its own form, not here). Take the @@ -150,7 +186,7 @@ ? {} : ((agentVal.input_transforms ?? {}) as Record)), ...Object.fromEntries( - Object.keys(args).map((key) => [ + formKeys.map((key) => [ key, { expr: `flow_input.${key}`, diff --git a/frontend/src/lib/components/ScriptBuilder.svelte b/frontend/src/lib/components/ScriptBuilder.svelte index e069fe50b8..393744dbca 100644 --- a/frontend/src/lib/components/ScriptBuilder.svelte +++ b/frontend/src/lib/components/ScriptBuilder.svelte @@ -102,7 +102,7 @@ import type { SavedAndModifiedValue } from './common/confirmationModal/unsavedTypes' import DeployButton from './DeployButton.svelte' import { type Trigger, deployTriggers, handleSelectTriggerFromKind } from './triggers/utils' - import DraftTriggersConfirmationModal from './common/confirmationModal/DraftTriggersConfirmationModal.svelte' + import DraftChangesConfirmationModal from './common/confirmationModal/DraftChangesConfirmationModal.svelte' import { Triggers } from './triggers/triggers.svelte' import type { ScriptBuilderProps } from './script_builder' import WorkerTagSelect from './WorkerTagSelect.svelte' @@ -1149,7 +1149,7 @@ currentValue={script} /> - t.draftConfig)} on:canceled={() => { diff --git a/frontend/src/lib/components/common/confirmationModal/DraftChangesConfirmationModal.svelte b/frontend/src/lib/components/common/confirmationModal/DraftChangesConfirmationModal.svelte new file mode 100644 index 0000000000..dadf814a80 --- /dev/null +++ b/frontend/src/lib/components/common/confirmationModal/DraftChangesConfirmationModal.svelte @@ -0,0 +1,323 @@ + + + dispatch('canceled')} + on:confirmed={() => dispatch('confirmed', { selectedTriggers, selectedAgents })} +> +
+ {#if draftTriggers.length > 0} +
+
+ {`Your ${runnable} has draft triggers. Select which draft triggers to deploy with the ${runnable}. Undeployed draft triggers will be permanently deleted.`} +
+ +
5 ? 'h-[300px]' : ''}> + + + + Triggers to deploy + + + + + {#each draftTriggers as trigger} + {@const SvelteComponent = triggerIconMap[trigger.type]} + {@const permission = checkSavePermissions(trigger)} + {@const isSelectedTrigger = isSelected(selectedTriggers, trigger)} + + +
+
+ + {#if trigger.isPrimary} + + {/if} +
+ +
+ +
+
+ + + + {#if permission === 'deploy'} +
+ toggleTrigger(trigger, e.detail)} + > + {#snippet children({ item })} + + + {/snippet} + +
+ {:else if permission === 'admin-only'} + Admin only + {:else if permission === 'invalid-config'} + Invalid config + {/if} + + + {/each} + + +
+
+ {/if} + + {#if draftAgents.length > 0} +
+
+ Saved agents this flow uses have unsaved changes. Select which ones to deploy with the + flow. An agent kept as a draft stays editable, and the flow runs the agent as currently + deployed. +
+ +
5 ? 'h-[300px]' : ''}> + + + + Agents to deploy + + + + + + {#each draftAgents as agent (agent.path)} + {@const permission = checkAgentPermissions(agent)} + {@const isSelectedAgent = selectedAgents.some((a) => a.path === agent.path)} + + + +
+ +
+
+ + + {agent.path} + + {#if agent.noDeployed} + Never deployed + {/if} +
+ {#if agent.noDeployed && !isSelectedAgent} + + + Never deployed, so the flow will not run until this agent is deployed. + + {/if} +
+
+ + + + + {#if permission.state === 'deploy'} +
+ toggleAgent(agent, e.detail)} + > + {#snippet children({ item })} + + + {/snippet} + +
+ {:else if permission.state === 'read-only'} + + Read-only + + {:else} + Invalid config + {/if} + + + {/each} + + +
+
+ {/if} +
+ diff --git a/frontend/src/lib/components/common/confirmationModal/DraftTriggersConfirmationModal.svelte b/frontend/src/lib/components/common/confirmationModal/DraftTriggersConfirmationModal.svelte deleted file mode 100644 index cfebae0e9f..0000000000 --- a/frontend/src/lib/components/common/confirmationModal/DraftTriggersConfirmationModal.svelte +++ /dev/null @@ -1,168 +0,0 @@ - - - dispatch('canceled')} - on:confirmed={() => dispatch('confirmed', { selectedTriggers })} -> -
-
- {`${isFlow ? 'Your flow' : 'Your script'} has draft triggers. Select which draft triggers to deploy with the ${isFlow ? 'flow' : 'script'}. Undeployed - draft triggers will be permanently deleted.`} -
- -
5 ? 'h-[300px]' : ''}> - - - - Triggers to deploy - - - - - {#each draftTriggers as trigger} - {@const SvelteComponent = triggerIconMap[trigger.type]} - {@const permission = checkSavePermissions(trigger)} - {@const isSelectedTrigger = isSelected(selectedTriggers, trigger)} - - -
-
- - {#if trigger.isPrimary} - - {/if} -
-
- -
-
- - - - {#if permission === 'deploy'} -
- toggleTrigger(trigger, e.detail)} - > - {#snippet children({ item })} - - - {/snippet} - -
- {:else if permission === 'admin-only'} - Admin only - {:else if permission === 'invalid-config'} - Invalid config - {/if} - - - {/each} - - {#if draftTriggers.length === 0} - - - No draft triggers found - - - {/if} - - -
-
- diff --git a/frontend/src/lib/components/flows/agentDraft.svelte.ts b/frontend/src/lib/components/flows/agentDraft.svelte.ts index 5a6a67ccb8..d4f8fa35de 100644 --- a/frontend/src/lib/components/flows/agentDraft.svelte.ts +++ b/frontend/src/lib/components/flows/agentDraft.svelte.ts @@ -6,6 +6,7 @@ import { sendUserToast } from '$lib/toast' import { canWrite } from '$lib/utils' import { userStore } from '$lib/stores' import { getUserExt } from '$lib/user' +import { UserDraftDbSyncer } from '$lib/userDraftDbSyncer.svelte' import { useTriggerDraftSync, type TriggerDraftSync } from '../triggers/useTriggerDraftSync.svelte' import { logReusableAgentUsage } from './agentTelemetry' import { @@ -84,6 +85,95 @@ export interface AgentResourceState { wsSpecific: boolean } +/** + * Why writing this draft to its resource would be refused, if it would. Shared with the flow's + * deploy dialog, which lists the drafts of the agents a flow links: an agent the editor's own + * Deploy button rejects must not be deployable from a flow either. + * + * `currentPath` is the path the draft is being deployed to; pass undefined where the caller has + * none of its own to compare against. + */ +export function agentDraftDeployRefusal( + state: AgentResourceState, + currentPath: string | undefined +): string | undefined { + // The editor offers only values, but a transform can arrive from a step that was forked + // before this existed, or from the generic resource editor: say so rather than writing it. + const transformValued = transformValuedBrainKeys(state.args) + if (transformValued.length > 0) { + const fields = transformValued.map((key) => AGENT_BRAIN_LABELS[key] ?? key) + const many = fields.length > 1 + return `${fields.join(', ')} ${many ? 'are' : 'is'} set to an expression or an AI-filled value, which a saved agent cannot store. Replace ${many ? 'them' : 'it'} with a plain value before deploying.` + } + // The resource endpoint takes any JSON, so nothing downstream stops an agent that cannot run: + // the worker needs a provider to call and rejects a tool whose name it cannot pass to the + // model. Deploying one would break every flow linking it, so it is refused here. + const blocked = agentConfigRunError(state.args) + if (blocked) { + return blocked + } + // Renaming is not the agent editor's to do: moving the resource leaves every step that links to + // it naming a path that no longer exists, and reconciling those is a feature of its own. A + // renamed path can still reach here, the generic editor writing the same draft row and offering + // a path field, so refuse it rather than performing half of a rename. + if (currentPath && state.path !== currentPath) { + return `This draft renames the agent to ${state.path}. Deploy it from the resource editor instead.` + } + // Only a draft naming another type: the load refuses a resource that is not an agent, while a + // draft the generic resource editor wrote names no type at all and inherits the loaded one. + if (state.resource_type && state.resource_type !== 'ai_agent') { + return `This draft is a ${state.resource_type} resource, not an agent.` + } + return undefined +} + +/** + * Write an agent to its resource from the state the editor holds, which can be ahead of the + * persisted draft row: the form stays editable while a deploy is in flight. Surfaces that deploy + * the row itself go through `deployDraft` instead. + * + * `notAnAgent` separates the one failure that invalidates the caller's whole view of the path, its + * holding something else now, from a write that merely failed. + */ +type AgentWriteResult = { ok: true } | { ok: false; error: string; notAnAgent?: true } + +async function writeAgentResource( + workspace: string, + state: AgentResourceState, + noDeployed: boolean +): Promise { + const body = { + path: state.path, + value: state.args, + description: state.description, + labels: state.labels, + ws_specific: state.wsSpecific + } + try { + if (noDeployed) { + // A create needs a type, and every caller proved this path is an agent before offering it. + await ResourceService.createResource({ + workspace, + requestBody: { ...body, resource_type: state.resource_type ?? 'ai_agent' } + }) + } else { + // The type the caller proved is as old as its own load, and an update carries no type of + // its own: were the path deleted and recreated as something else meanwhile, this write + // would put an agent config inside that resource. Reading it again narrows the window to + // the request rather than to however long the editor or the dialog stayed open. + const current = await ResourceService.getResource({ workspace, path: state.path }) + const refused = agentEditorRefusal(state.path, current.resource_type) + if (refused) { + return { ok: false, error: refused, notAnAgent: true } + } + await ResourceService.updateResource({ workspace, path: state.path, requestBody: body }) + } + } catch (err) { + return { ok: false, error: `Could not save agent: ${err}` } + } + return { ok: true } +} + export interface AgentDraftOptions { /** The `ai_agent` resource being edited. */ path: () => string | undefined @@ -219,6 +309,16 @@ export function useAgentDraft(opts: AgentDraftOptions): AgentDraftHandle { // config before the autosave lands. state = ((r as any).draft as AgentResourceState | undefined) ?? structuredClone(deployedState) + // Adopt the row's timestamp as this tab's baseline. Without it the first save from + // each tab goes out with no `last_sync`, which the backend treats as unconditional + // and so silently overwrites another tab's newer draft. It also clears any parked + // conflict or failure for the key: a conflict is deliberately sticky (the retry + // keeps the same baseline), and nothing else mounts a resolver for `resource` + // drafts, so re-opening the agent is the only place it can be resolved. + UserDraftDbSyncer.recordRemoteSync( + { workspace: ws, itemKind: 'resource', path }, + (r as { draft_saved_at?: string }).draft_saved_at + ) loading = false await sync.maybeRestore() }, @@ -237,42 +337,9 @@ export function useAgentDraft(opts: AgentDraftOptions): AgentDraftHandle { const ws = opts.workspace() const s = state if (!ws || !s) return false - // The editor offers only values, but a transform can arrive from a step that was forked - // before this existed, or from the generic resource editor: say so rather than writing it. - const transformValued = transformValuedBrainKeys(s.args) - if (transformValued.length > 0) { - const fields = transformValued.map((key) => AGENT_BRAIN_LABELS[key] ?? key) - const many = fields.length > 1 - sendUserToast( - `${fields.join(', ')} ${many ? 'are' : 'is'} set to an expression or an AI-filled value, which a saved agent cannot store. Replace ${many ? 'them' : 'it'} with a plain value before deploying.`, - true - ) - return false - } - // The resource endpoint takes any JSON, so nothing downstream stops an agent that cannot run: - // the worker needs a provider to call and rejects a tool whose name it cannot pass to the - // model. Deploying one would break every flow linking it, so it is refused here. - const blocked = agentConfigRunError(s.args) - if (blocked) { - sendUserToast(blocked, true) - return false - } - // Renaming is not this editor's to do: moving the resource leaves every step that links to it - // naming a path that no longer exists, and reconciling those is a feature of its own. A - // renamed path can still reach here, the generic editor writing the same draft row and - // offering a path field, so refuse it rather than performing half of a rename. - const currentPath = opts.path() - if (currentPath && s.path !== currentPath) { - sendUserToast( - `This draft renames the agent to ${s.path}. Deploy it from the resource editor instead.`, - true - ) - return false - } - // Only a draft naming another type: the load refuses a resource that is not an agent, while a - // draft the generic resource editor wrote names no type at all and inherits the loaded one. - if (s.resource_type && s.resource_type !== 'ai_agent') { - sendUserToast(`This draft is a ${s.resource_type} resource, not an agent.`, true) + const refused = agentDraftDeployRefusal(s, opts.path()) + if (refused) { + sendUserToast(refused, true) return false } // The form stays editable while the request is in flight, so everything below works from a @@ -280,39 +347,15 @@ export function useAgentDraft(opts: AgentDraftOptions): AgentDraftHandle { // made during the request as saved, and the banner would clear on a value the server never // received; against the snapshot it stays a draft, which is what it is. const submitted = structuredClone($state.snapshot(s)) as AgentResourceState - const body = { - path: submitted.path, - value: submitted.args, - description: submitted.description, - labels: submitted.labels, - ws_specific: submitted.wsSpecific - } - try { - if (noDeployed) { - await ResourceService.createResource({ - workspace: ws, - // A create needs a type, and the load proved this path is an agent before opening. - requestBody: { ...body, resource_type: submitted.resource_type ?? 'ai_agent' } - }) + const written = await writeAgentResource(ws, submitted, noDeployed) + if (!written.ok) { + // A path that is no longer an agent tears this editor down; anything else is a plain error + // the user can retry from the form as it stands. + if (written.notAnAgent) { + refuse(written.error) } else { - // The type this editor proved is as old as the load, and an update carries no type of - // its own: were the path deleted and recreated as something else meanwhile, this write - // would put an agent config inside that resource. Reading it again narrows the window - // to the request rather than to however long the editor stayed open. - const current = await ResourceService.getResource({ workspace: ws, path: submitted.path }) - const refused = agentEditorRefusal(submitted.path, current.resource_type) - if (refused) { - refuse(refused) - return false - } - await ResourceService.updateResource({ - workspace: ws, - path: submitted.path, - requestBody: body - }) + sendUserToast(written.error, true) } - } catch (err) { - sendUserToast(`Could not save agent: ${err}`, true) return false } // The counter the step card's write-back used to report, from the surface that now owns the diff --git a/frontend/src/lib/components/flows/agentEditorStore.svelte.ts b/frontend/src/lib/components/flows/agentEditorStore.svelte.ts index 83660212b3..025a426d28 100644 --- a/frontend/src/lib/components/flows/agentEditorStore.svelte.ts +++ b/frontend/src/lib/components/flows/agentEditorStore.svelte.ts @@ -6,6 +6,8 @@ * resources page. Module-level rather than a context value because what opens it — a step's card, * a list row — unmounts the moment the selection moves. */ +import { UserDraftDbSyncer } from '$lib/userDraftDbSyncer.svelte' + export interface AgentEditorTarget { path: string /** The workspace the opener operates on; the nav workspace when absent. */ @@ -61,3 +63,25 @@ export function markAgentWritten(workspace: string | undefined, path: string) { export function agentWriteCount(workspace: string | undefined, path: string | undefined): number { return agentWrites[writeKey(workspace, path)] ?? 0 } + +/** How many times each agent's DRAFT has been saved, for the surfaces that display an agent by + * fetching it. A draft write moves no deployed version, so `agentWriteCount` never sees it, and a + * card keyed on that alone would keep describing the config a test no longer runs. */ +let agentDraftSaves = $state>({}) + +/** Every writer in this document goes through the draft syncer — this editor, the generic resource + * editor — so one subscription answers for them all, firing when the write lands rather than on + * each keystroke. `resource` is the item kind agent draft rows use. In-memory: a save in another + * tab never arrives here, so a card lags it until reload, while what a test runs is read live. */ +UserDraftDbSyncer.onAnySaved(({ workspace, itemKind, path }) => { + if (itemKind !== 'resource') return + const key = writeKey(workspace, path) + agentDraftSaves[key] = (agentDraftSaves[key] ?? 0) + 1 +}) + +export function agentDraftSaveCount( + workspace: string | undefined, + path: string | undefined +): number { + return agentDraftSaves[writeKey(workspace, path)] ?? 0 +} diff --git a/frontend/src/lib/components/flows/agentTelemetry.ts b/frontend/src/lib/components/flows/agentTelemetry.ts index fcfad440ff..87fcb0dad4 100644 --- a/frontend/src/lib/components/flows/agentTelemetry.ts +++ b/frontend/src/lib/components/flows/agentTelemetry.ts @@ -13,6 +13,10 @@ export type ReusableAgentEvent = | 'linked' /** A linked step was forked back into a standalone agent. */ | 'unlinked' + /** A linked agent's unsaved draft was deployed alongside the flow that uses it. */ + | 'draft_deployed_with_flow' + /** A linked agent's unsaved draft was left as a draft when its flow was deployed. */ + | 'draft_kept_on_deploy' export function logReusableAgentUsage(event: ReusableAgentEvent): void { logFeatureUsage('ai_agent', 'reusable', { key: event }) diff --git a/frontend/src/lib/components/flows/content/AgentEditorHost.svelte b/frontend/src/lib/components/flows/content/AgentEditorHost.svelte index 79db0cedb3..a7c867a6f4 100644 --- a/frontend/src/lib/components/flows/content/AgentEditorHost.svelte +++ b/frontend/src/lib/components/flows/content/AgentEditorHost.svelte @@ -29,6 +29,7 @@ inputTransformsToAgentConfig, type AIAgentConfig } from '../agentResourceUtils' + import { agentArgsToTransforms } from '../linkedAgentDrafts' import { AGENT_TOOLS_ROW } from '../agentFormFields' import { toolDisplayName, type AgentTool } from '../agentToolUtils' import { useAgentDraft } from '../agentDraft.svelte' @@ -223,19 +224,6 @@ }) }) - /** Every argument the resource carries, as a static transform. `tools` is the roster rather than - * a field, so it rides on the module's own key instead. Not only the keys the form renders: a - * run reads them all, and an agent holding its own `user_message` answers with it when nothing - * overrides it, so a test here has to run the configuration a linked step would. */ - function agentArgsToTransforms(args: AIAgentConfig): Record { - const it: Record = {} - for (const [key, value] of Object.entries(args ?? {})) { - if (key === 'tools' || value === undefined) continue - it[key] = { type: 'static', value } as InputTransform - } - return it - } - /** Everything the form does not model. `inputTransformsToAgentConfig` rebuilds the value from * `AGENT_BRAIN_KEYS` alone, so a key this editor never renders — one a newer backend added, or * the `user_message` default a resource may carry, which the runtime does read when the step diff --git a/frontend/src/lib/components/flows/content/AgentEditorModal.svelte b/frontend/src/lib/components/flows/content/AgentEditorModal.svelte index 3ded2deb9f..22ac424144 100644 --- a/frontend/src/lib/components/flows/content/AgentEditorModal.svelte +++ b/frontend/src/lib/components/flows/content/AgentEditorModal.svelte @@ -183,7 +183,9 @@ const moduleIds = new Set(linkedModulesForAgent(scope, path)) moduleIds.add(at.host.moduleId) return Promise.all( - [...moduleIds].map((moduleId) => publishLinkedAgentTools(path, at.ws, scope, moduleId)) + // With the draft: a deploy leaves none, but a version restore leaves the draft standing and + // it is still what a test of the host step would run. + [...moduleIds].map((moduleId) => publishLinkedAgentTools(path, at.ws, scope, moduleId, true)) ) } diff --git a/frontend/src/lib/components/flows/content/AgentResourceBar.svelte b/frontend/src/lib/components/flows/content/AgentResourceBar.svelte index 3a870f911d..96548b10af 100644 --- a/frontend/src/lib/components/flows/content/AgentResourceBar.svelte +++ b/frontend/src/lib/components/flows/content/AgentResourceBar.svelte @@ -4,7 +4,7 @@ import Badge from '$lib/components/common/badge/Badge.svelte' import Path from '$lib/components/Path.svelte' import TextInput from '$lib/components/text_input/TextInput.svelte' - import { ResourceService, type InputTransform } from '$lib/gen' + import { ResourceService, type InputTransform, type Resource } from '$lib/gen' import { workspaceStore } from '$lib/stores' import { sendUserToast } from '$lib/toast' import { Bot, ChevronDown, ChevronUp, Save, Unlink, Pencil } from 'lucide-svelte' @@ -19,14 +19,24 @@ type AIAgentConfig, type AgentTool } from '../agentResourceUtils' - import { agentWriteCount, markAgentWritten, openAgentEditor } from '../agentEditorStore.svelte' + import { + agentDraftSaveCount, + agentWriteCount, + markAgentWritten, + openAgentEditor + } from '../agentEditorStore.svelte' import { setLinkedAgentTools, clearLinkedAgentTools, + linkedModulesForAgent, linkedToolsScope } from '../linkedAgentToolsStore.svelte' import { logReusableAgentUsage } from '../agentTelemetry' import { claimLinkedToolsFetch } from '../flowState' + import { AgentDraftUnavailable, fetchAgentWithDraft } from '../linkedAgentDrafts' + import type { AgentResourceState } from '../agentDraft.svelte' + import { getLocalDraftHint } from '$lib/localDraftHints.svelte' + import Tooltip from '$lib/components/meltComponents/Tooltip.svelte' import type { AgentTool as AgentToolStrict } from '../agentToolUtils' import { resource } from 'runed' import { untrack } from 'svelte' @@ -65,6 +75,10 @@ // deploy from the agent editor mounted alongside it. Both reads below key on it, so neither // keeps naming the config and version a write has just replaced. let writes = $derived(agentWriteCount(ws, agent)) + // Draft saves as well, for the link fetch: the card shows what a test of this step would run, + // and that is the draft. Only the deploy moves `writes`, so without this the card would keep + // describing the config the agent held before it was edited. + let draftSaves = $derived(agentDraftSaveCount(ws, agent)) let saveDrawer: Drawer | undefined = $state() let newPath = $state('') @@ -75,14 +89,18 @@ type LinkedInfo = { // What this result was fetched for. runed's resource neither aborts nor tags a superseded // request, so a slow fetch can land after a newer one: every consumer gates on these matching - // the current (ws, agent, writes). `writes` is what covers a refetch of the *same* link after - // a deploy — without it a pre-deploy response is indistinguishable from the current one, and - // accepting it republishes the tools the deploy just replaced. + // the current (ws, agent, writes, draftSaves). `writes` is what covers a refetch of the *same* + // link after a deploy — without it a pre-deploy response is indistinguishable from the current + // one, and accepting it republishes the tools the deploy just replaced. `draftSaves` does the + // same for a draft save, which the card follows just as closely. ws?: string path?: string writes: number + draftSaves: number config: AIAgentConfig tools: AgentTool[] + /** The config shown came from the agent's unsaved draft rather than the deployed resource. */ + fromDraft: boolean providerPath?: string providerOk: boolean } @@ -90,14 +108,37 @@ // A linked agent is rigid and read-only: its brain and tools come from the resource. We // load them here for display, and probe the provider resource so we can warn when it isn't // accessible in this workspace (the user then needs to unlink/fork or gain access). + // The draft when there is one, since that is what a test of this step runs. let linkedResource = resource( - () => ({ ws, path: agent, writes }), - async ({ ws, path, writes }): Promise => { + () => ({ ws, path: agent, writes, draftSaves }), + async ({ ws, path, writes, draftSaves }): Promise => { if (!ws || !path) { - return { ws, path, writes, config: {}, tools: [], providerOk: true } + return { + ws, + path, + writes, + draftSaves, + config: {}, + tools: [], + fromDraft: false, + providerOk: true + } + } + let response: Resource + let draft: AgentResourceState | undefined + try { + ;({ response, draft } = await fetchAgentWithDraft(path, ws)) + } catch (err) { + // Only the DRAFT was unreadable. This card is a display, so fall back to the deployed + // agent rather than rendering one with no brain and no tools, which reads as "the agent + // is empty" while the Draft badge still says it has unsaved changes. Same fallback the + // graph's tool nodes take; the paths that run or deploy the draft still refuse. + if (!(err instanceof AgentDraftUnavailable)) throw err + response = await ResourceService.getResource({ workspace: ws, path }) + } + const cfg = (draft?.args ?? response.value ?? {}) as AIAgentConfig & { + provider?: { resource?: string } } - const res = await ResourceService.getResource({ workspace: ws, path }) - const cfg = (res.value ?? {}) as AIAgentConfig & { provider?: { resource?: string } } const tools = (cfg.tools ?? []) as AgentTool[] const providerRef = cfg.provider?.resource const providerPath = @@ -116,8 +157,10 @@ ws, path, writes, + draftSaves, config: cfg, tools, + fromDraft: draft != undefined, providerPath, providerOk } @@ -129,7 +172,13 @@ let loadedInfo = $state(undefined) $effect(() => { const current = linkedResource.current - if (current && current.ws === ws && current.path === agent && current.writes === writes) { + if ( + current && + current.ws === ws && + current.path === agent && + current.writes === writes && + current.draftSaves === draftSaves + ) { loadedInfo = current } }) @@ -140,6 +189,12 @@ let brainParams = $derived(summarizeAgentBrain(linkedInfo?.config)) let providerPath = $derived(linkedInfo?.providerPath) let providerOk = $derived(linkedInfo?.providerOk ?? true) + // The hint flips on the first keystroke in the agent editor, so the badge does not wait for the + // debounced autosave and the refetch behind it; the fetched answer covers a draft written + // elsewhere, which no editor here has published an opinion about. + let hasDraft = $derived( + getLocalDraftHint(ws, 'resource', agent ?? '') ?? linkedInfo?.fromDraft ?? false + ) /** The agent the card is about: the one this step links to, or the one being edited. */ let cardPath = $derived(agent) // The version eval runs are recorded against. The resource does not hold it; its newest history @@ -190,9 +245,18 @@ } const loaded = linkedInfo if (loaded) { - claimLinkedToolsFetch(toolScope, moduleId) - // linkedResource types tools loosely; they are the same resource tools the store holds. - setLinkedAgentTools(toolScope, moduleId, loaded.tools as AgentToolStrict[], agent) + // Every step of this flow linking this agent, not just this one. Tools belong to the agent, + // so the sibling steps show the same set, and only the selected step mounts this card: + // without them a draft saved from here leaves their nodes on what the flow load resolved, + // while a test of those steps runs the draft. Claimed like this card's own publish, so a + // sibling's in-flight fetch cannot land afterwards and put the old tools back. + const modules = new Set(linkedModulesForAgent(toolScope, agent)) + modules.add(moduleId) + for (const id of modules) { + claimLinkedToolsFetch(toolScope, id) + // linkedResource types tools loosely; they are the same resource tools the store holds. + setLinkedAgentTools(toolScope, id, loaded.tools as AgentToolStrict[], agent) + } publishedFor = agent } else if (publishedFor !== undefined && publishedFor !== agent) { // The link moved and the new agent hasn't resolved, so the stored tools are the old one's. @@ -358,13 +422,15 @@ // `tools` is one array per module value, so it identifies the step itself — the path alone // would not, since a replacement can carry the same link. const stepMarker = tools - const res = await ResourceService.getResource({ workspace: ws, path }) + // The draft, like the card above and like a test of this step: forking the deployed value + // while the card displays a drafted prompt would hand back something the user never saw. + const { response, draft } = await fetchAgentWithDraft(path, ws) // The module may have been replaced while the fetch was in flight (undo, session drafts); // applying a stale fork would overwrite the restored state. if (agent !== path || tools !== stepMarker) { return false } - const cfg = (res.value ?? {}) as AIAgentConfig + const cfg = (draft?.args ?? response.value ?? {}) as AIAgentConfig // Preserve the flow-local inputs already wired in the step. const local: Record = {} for (const key of AGENT_FLOW_LOCAL_KEYS) { @@ -448,6 +514,15 @@ v{version} {/if} + {#if hasDraft} + + Draft + {#snippet text()} + This agent has unsaved changes. Testing this flow runs the draft, and deploying the + flow offers to deploy it. + {/snippet} + + {/if}
{#if brainParams.length > 0 || inheritedTools.length > 0} diff --git a/frontend/src/lib/components/flows/flowState.ts b/frontend/src/lib/components/flows/flowState.ts index 3123396a9d..595227f57d 100644 --- a/frontend/src/lib/components/flows/flowState.ts +++ b/frontend/src/lib/components/flows/flowState.ts @@ -5,6 +5,7 @@ import { get } from 'svelte/store' import { workspaceStore } from '$lib/stores' import { isFlowModuleTool, agentToolToFlowModule, type AgentTool } from './agentToolUtils' import { linkedToolsScope, setLinkedAgentTools } from './linkedAgentToolsStore.svelte' +import { fetchAgentWithDraft, normalizeAgentRef } from './linkedAgentDrafts' import { loadFlowModuleState } from './flowStateUtils.svelte' import { emptyFlowModuleState } from './utils.svelte' import type { StateStore } from '$lib/utils' @@ -90,7 +91,9 @@ async function mapFlowModule( // the graph can render its tool nodes. They are display-only (their inputs are edited in // the step panel, which infers schemas itself), so no per-tool module state is loaded — // resource tool ids are not flow-unique and must not key into the flow state. - await publishLinkedAgentTools(agentRef, workspace, scope, flowModule.id) + // Drafts included: every caller of `initFlowState` is a flow editor, where the graph has + // to show the tools a test would run. Read-only viewers publish for themselves. + await publishLinkedAgentTools(agentRef, workspace, scope, flowModule.id, true) } else { // Shape-checked because `tools` is JSON-authored: throwing here would skip the agent's // own state below, leaving it with no schema rather than with no tool schemas. @@ -119,11 +122,17 @@ export async function publishLinkedAgentTools( agentRef: string, workspace: string | undefined, scope: string, - moduleId: string + moduleId: string, + /** Resolve from the agent's unsaved draft when there is one. Editors pass true so the graph + * shows the tool set a test would run; read-only viewers pass false, since a run they are + * displaying used the deployed agent. Required rather than defaulted: an editor call site that + * forgets it republishes the deployed tools over the drafted ones, which reads as the graph + * spontaneously reverting. */ + withDraft: boolean ) { const genKey = `${scope}:${moduleId}` const gen = claimLinkedToolsFetch(scope, moduleId) - const tools = await resolveLinkedAgentTools(agentRef, workspace) + const tools = await resolveLinkedAgentTools(agentRef, workspace, withDraft) if (linkedToolFetchGen.get(genKey) === gen) { setLinkedAgentTools(scope, moduleId, tools, agentRef) } @@ -155,12 +164,27 @@ export function claimLinkedToolsFetch(scope: string, moduleId: string): number { // resource is missing or inaccessible so a broken link never stalls the flow load. export async function resolveLinkedAgentTools( agentRef: string, - workspace?: string + workspace: string | undefined, + withDraft: boolean ): Promise { const ws = workspace ?? get(workspaceStore) if (!ws) return [] - const path = agentRef.replace(/^\$res:/, '').replace(/^res:\/\//, '') + const path = normalizeAgentRef(agentRef) try { + if (withDraft) { + try { + const { response, draft } = await fetchAgentWithDraft(path, ws) + const value = (draft?.args ?? response.value) as { tools?: AgentTool[] } | undefined + return (value?.tools ?? []) as AgentTool[] + } catch { + // The draft read failed for any reason. This is a display, not a run, so fall through to + // the deployed tools rather than showing an agent with none: an empty node list reads as + // "the agent lost its tools" instead of "we could not reach the server". The paths that + // act on a draft — the previews and the deploy dialog — surface the failure instead. + // Not rethrowing anything here: the outer catch turns every throw into `[]`, so a + // rethrow would skip the very fallback this exists for. + } + } const res = await ResourceService.getResource({ workspace: ws, path }) return ((res.value as { tools?: AgentTool[] } | undefined)?.tools ?? []) as AgentTool[] } catch { diff --git a/frontend/src/lib/components/flows/linkedAgentDrafts.test.ts b/frontend/src/lib/components/flows/linkedAgentDrafts.test.ts new file mode 100644 index 0000000000..563007615f --- /dev/null +++ b/frontend/src/lib/components/flows/linkedAgentDrafts.test.ts @@ -0,0 +1,148 @@ +import { beforeEach, describe, expect, it, vi } from 'vitest' + +import { + inlineAgentDraft, + inlineAgentDrafts, + loadLinkedAgentDrafts, + type LinkedAgentDraft +} from './linkedAgentDrafts' +import { ResourceService, type FlowModule, type FlowValue } from '$lib/gen' + +type AiAgentValue = Extract + +function linkedStep(input_transforms: Record): AiAgentValue { + return { + type: 'aiagent', + agent: 'f/team/support', + tool_inputs: { t1: { query: { type: 'javascript', expr: 'flow_input.q' } } }, + input_transforms + } as unknown as AiAgentValue +} + +describe('inlineAgentDraft', () => { + // The overlay order is the worker's: the resource brain first, the step's flow-local inputs on + // top. Reversing it would run the agent author's own `user_message` instead of the flow's. + it('keeps the step wired to the flow while the brain comes from the draft', () => { + const inlined = inlineAgentDraft( + linkedStep({ + user_message: { type: 'javascript', expr: 'flow_input.question' }, + user_attachments: { type: 'static', value: [] } + }), + { + provider: { kind: 'openai', model: 'gpt-4o', resource: '$res:f/team/openai' }, + system_prompt: 'answer in french', + user_message: 'the default the agent carries', + tools: [{ id: 't1', summary: 'search' }] + } as any + ) + + expect(inlined.agent).toBeUndefined() + expect(inlined.tools).toEqual([{ id: 't1', summary: 'search' }]) + expect(inlined.input_transforms).toEqual({ + provider: { + type: 'static', + value: { kind: 'openai', model: 'gpt-4o', resource: '$res:f/team/openai' } + }, + system_prompt: { type: 'static', value: 'answer in french' }, + user_message: { type: 'javascript', expr: 'flow_input.question' }, + user_attachments: { type: 'static', value: [] } + }) + // Host bindings are the step's, not the agent's, and the worker overlays them either way. + expect(inlined.tool_inputs).toEqual({ + t1: { query: { type: 'javascript', expr: 'flow_input.q' } } + }) + }) + + // A linked step carries only the flow-local inputs, but one persisted before linking existed can + // still hold stale brain transforms. They must not shadow the draft the test is meant to run. + it('drops brain transforms the step still carries', () => { + const inlined = inlineAgentDraft( + linkedStep({ + user_message: { type: 'static', value: 'hi' }, + system_prompt: { type: 'static', value: 'stale' } + }), + { system_prompt: 'from the draft' } as any + ) + + expect(inlined.input_transforms).toEqual({ + system_prompt: { type: 'static', value: 'from the draft' }, + user_message: { type: 'static', value: 'hi' } + }) + }) +}) + +describe('inlineAgentDrafts', () => { + // The index is keyed on the bare path while a step may name its agent `$res:`-prefixed, and the + // walk has to reach inside branches and loops. Miss either and every preview silently runs the + // deployed agent — the failure this whole path exists to prevent, and a silent one. + it('reaches a $res:-prefixed link nested in a branch', () => { + const value = { + modules: [ + { + id: 'b', + value: { + type: 'branchone', + default: [], + branches: [ + { + modules: [ + { + id: 'inner', + value: { + type: 'aiagent', + agent: '$res:f/team/support', + tools: [], + input_transforms: { user_message: { type: 'static', value: 'hi' } } + } + } + ] + } + ] + } + } + ] + } as unknown as FlowValue + + const drafts = new Map([ + ['f/team/support', { args: { system_prompt: 'drafted' } } as unknown as LinkedAgentDraft] + ]) + + const inner = (inlineAgentDrafts(value, drafts).modules[0].value as any).branches[0].modules[0] + expect(inner.value.agent).toBeUndefined() + expect(inner.value.input_transforms.system_prompt).toEqual({ + type: 'static', + value: 'drafted' + }) + // The input the flow supplies survives the rewrite. + expect(inner.value.input_transforms.user_message).toEqual({ type: 'static', value: 'hi' }) + }) +}) + +// A link the user cannot resolve is an ordinary state and must not block the flow; anything else is +// an outage, and answering "no draft" to one would silently test or deploy against the deployed +// agent while the editor shows the draft. +describe('loadLinkedAgentDrafts error handling', () => { + function failWith(status: number | undefined) { + return async () => { + const err: Error & { status?: number } = new Error('boom') + err.status = status + throw err + } + } + + beforeEach(() => { + vi.restoreAllMocks() + }) + + it.each([401, 403, 404])('treats %i as no draft', async (status) => { + vi.spyOn(ResourceService, 'getResource').mockImplementation(failWith(status) as any) + await expect(loadLinkedAgentDrafts(['f/team/support'], 'ws')).resolves.toEqual(new Map()) + }) + + it.each([500, undefined])('propagates %s rather than reporting no draft', async (status) => { + vi.spyOn(ResourceService, 'getResource').mockImplementation(failWith(status) as any) + await expect(loadLinkedAgentDrafts(['f/team/support'], 'ws')).rejects.toThrow( + 'Could not load the agent f/team/support' + ) + }) +}) diff --git a/frontend/src/lib/components/flows/linkedAgentDrafts.ts b/frontend/src/lib/components/flows/linkedAgentDrafts.ts new file mode 100644 index 0000000000..8da732e7ff --- /dev/null +++ b/frontend/src/lib/components/flows/linkedAgentDrafts.ts @@ -0,0 +1,229 @@ +import { + ResourceService, + type FlowModule, + type FlowValue, + type InputTransform, + type Resource +} from '$lib/gen' +import { UserDraft } from '$lib/userDraft.svelte' +import { UserDraftDbSyncer } from '$lib/userDraftDbSyncer.svelte' +import { canWrite } from '$lib/utils' +import type { UserExt } from '$lib/stores' +import { dfs } from './dfs' +import { flowLocalInputs, type AIAgentConfig } from './agentResourceUtils' +import type { AgentResourceState } from './agentDraft.svelte' +import type { AgentTool } from './agentToolUtils' + +/** A step names its agent bare or as `$res:`/`res://`; all three are the same agent, + * and a draft index has to answer for a lookup written any of those ways. Same normalization as + * `linkedAgentToolsStore`, and as the `trim_start_matches` the worker applies. */ +export function normalizeAgentRef(agentRef: string): string { + return agentRef.replace(/^\$res:/, '').replace(/^res:\/\//, '') +} + +/** Every `ai_agent` resource this flow links to, deduped. `dfs` walks agent tool nodes as well as + * branches and loops, so a nested linked agent tool is included. */ +export function linkedAgentPaths(value: FlowValue | undefined): string[] { + if (!value?.modules) return [] + const paths = new Set() + for (const module of dfs(value.modules, (m) => m)) { + const v = module?.value as { type?: string; agent?: string } | undefined + if (v?.type === 'aiagent' && v.agent) { + paths.add(normalizeAgentRef(v.agent)) + } + } + return [...paths] +} + +/** + * The unsaved draft for an agent, freshest first: the cell an open agent editor is writing, then + * what a `get_draft` response carried. + * + * Only the live cell is reliably current, and only while an editor holds it: `releaseEntry` drops + * the cached write at refcount 0 on purpose, so once the agent editor closes the persisted row is + * the sole answer. Read through `fetchAgentWithDraft`, which settles that row first. + */ +export function agentDraftState( + response: { draft?: unknown }, + path: string, + workspace: string | undefined +): AgentResourceState | undefined { + const live = UserDraft.get('resource', path, { workspace }) + return live ?? (response.draft as AgentResourceState | undefined) +} + +/** A refusal that already names the agent and says what is wrong with it, so a caller wrapping it + * would only repeat itself. */ +export class AgentDraftUnavailable extends Error {} + +/** + * An agent's resource together with the draft a run of it would use. + * + * The flush is what makes the answer current. Autosave is debounced by 1.5s (10s ceiling), and + * closing the agent editor releases the in-memory cell without cancelling that pending POST — so + * testing or deploying right after closing would otherwise read a row the last edits have not + * reached yet. `flush` replays the parked save and is a no-op when there is none. + */ +export async function fetchAgentWithDraft( + path: string, + workspace: string +): Promise<{ response: Resource; draft: AgentResourceState | undefined }> { + const query = { workspace, itemKind: 'resource' as const, path } + await UserDraftDbSyncer.flush(query) + // `flush` resolves whether or not the save actually landed: `postSave` catches network and + // server errors into its failure map, and answers a conflicting write by parking a snapshot, + // returning normally in both cases. The row about to be read is then older than the edit still + // held in the browser, and nothing downstream could tell. Running that row is a test of the + // wrong agent; deploying it is worse, because the deploy deletes the draft and takes the newer + // edit with it. Neither is recoverable from here, so refuse the read. + const failure = UserDraftDbSyncer.getState(query).failureMessage + if (failure) { + throw new AgentDraftUnavailable(`The unsaved changes to ${path} could not be saved: ${failure}`) + } + if (UserDraftDbSyncer.getConflict(query).conflict) { + throw new AgentDraftUnavailable( + `The unsaved changes to ${path} could not be saved because it was edited elsewhere. Open the agent to resolve it.` + ) + } + const response = await ResourceService.getResource({ workspace, path, getDraft: true }) + return { response, draft: agentDraftState(response, path, workspace) } +} + +/** One linked agent whose resource the user has an unsaved draft for. */ +export interface LinkedAgentDraft { + path: string + /** The draft's resource value: what a run of this agent would use. */ + args: AIAgentConfig + /** The whole draft row, as the resource editors write it — the deploy payload. */ + state: AgentResourceState + /** No deployed row at this path, so deploying has to create rather than update. */ + noDeployed: boolean + /** Of the deployed resource, for `agentDraftCanWrite`. */ + extraPerms: Record +} + +/** Whether `user` may write this agent's resource. Split from the load so that resolving the + * drafts of a whole flow costs no `whoami` — only the deploy dialog needs the answer, and it + * looks the user up once for every agent it lists. */ +export function agentDraftCanWrite(draft: LinkedAgentDraft, user: UserExt | undefined): boolean { + return canWrite(draft.path, draft.extraPerms, user) +} + +/** A link that cannot resolve for the user rather than because something went wrong: the agent was + * deleted, or sits in a folder they cannot read. Both are ordinary states of a rigid link, and + * neither should stop the caller — the flow still tests and deploys, against the deployed agent. + * Every other failure is an outage, and answering "no draft" to one would quietly run or deploy + * the wrong configuration, which is the whole thing this module exists to prevent. */ +function isExpectedLinkFailure(err: unknown): boolean { + const status = (err as { status?: number } | null | undefined)?.status + return status === 401 || status === 403 || status === 404 +} + +/** + * The unsaved draft of every given `ai_agent` path, for the paths that have one. + * + * Throws when a path fails to load for any reason other than being missing or unreadable, so a + * caller cannot mistake an outage for an agent with nothing unsaved. + */ +export async function loadLinkedAgentDrafts( + paths: string[], + workspace: string | undefined +): Promise> { + const out = new Map() + if (!workspace || paths.length === 0) return out + await Promise.all( + paths.map(async (path) => { + let response: Resource + let draft: AgentResourceState | undefined + try { + ;({ response, draft } = await fetchAgentWithDraft(path, workspace)) + } catch (err) { + if (isExpectedLinkFailure(err)) return + if (err instanceof AgentDraftUnavailable) throw err + throw new Error(`Could not load the agent ${path}: ${err}`) + } + if (!draft) return + out.set(path, { + path, + args: (draft.args ?? {}) as AIAgentConfig, + state: draft, + noDeployed: Boolean((response as { no_deployed?: boolean }).no_deployed), + extraPerms: response.extra_perms ?? {} + }) + }) + ) + return out +} + +/** + * Every argument a saved agent carries, as a static input transform. Not only the keys the agent + * form renders: a run reads them all, and an agent holding its own `user_message` answers with it + * when nothing overrides it. `tools` is the step's own roster rather than an input, so it rides on + * the module's `tools` key instead. + */ +export function agentArgsToTransforms(args: AIAgentConfig): Record { + const it: Record = {} + for (const [key, value] of Object.entries(args ?? {})) { + if (key === 'tools' || value === undefined) continue + it[key] = { type: 'static', value } as InputTransform + } + return it +} + +type AiAgentValue = Extract + +/** + * The standalone step a linked step's draft would run as: the draft's brain and tools inlined, with + * the step's own flow-local inputs kept on top. + * + * The overlay order is the worker's (`ai_executor.rs`): its linked branch interpolates the whole + * resource brain and only then writes `user_message`/`user_attachments` back from the step's own + * args. `tool_inputs` stays untouched — the worker overlays it onto the tools in both branches, so + * an inlined step keeps the host flow's tool bindings. + */ +export function inlineAgentDraft(value: AiAgentValue, args: AIAgentConfig): AiAgentValue { + const { agent: _agent, ...rest } = value + return { + ...rest, + tools: (args.tools ?? []) as AgentTool[], + input_transforms: { + ...agentArgsToTransforms(args), + ...flowLocalInputs(value.input_transforms as Record) + } + } as AiAgentValue +} + +/** + * Replace every linked agent step that has a draft with the draft's own configuration, so a preview + * runs what the agent editor is showing rather than the deployed resource. Returns a new value: the + * flow editor hands its live store object to previews. + */ +export function inlineAgentDrafts( + value: FlowValue, + drafts: Map +): FlowValue { + if (drafts.size === 0) return value + // JSON rather than `structuredClone`: the flow editor's value is a Svelte `$state` proxy, which + // `structuredClone` refuses outright. A flow value is JSON by definition — it is about to be + // posted as one — so the round trip loses nothing this preview would have carried. + const next = JSON.parse(JSON.stringify(value)) as FlowValue + for (const module of dfs(next.modules ?? [], (m) => m)) { + const v = module?.value as AiAgentValue | undefined + if (v?.type !== 'aiagent' || !v.agent) continue + const draft = drafts.get(normalizeAgentRef(v.agent)) + if (!draft) continue + module.value = inlineAgentDraft(v, draft.args) + } + return next +} + +/** Load the drafts this flow's linked agents have and inline them. The whole substitution, for a + * caller holding nothing but the value it is about to preview. */ +export async function withAgentDrafts( + value: FlowValue, + workspace: string | undefined +): Promise { + const paths = linkedAgentPaths(value) + if (paths.length === 0) return value + return inlineAgentDrafts(value, await loadLinkedAgentDrafts(paths, workspace)) +} diff --git a/frontend/src/lib/components/flows/linkedToolsFetchGuard.test.ts b/frontend/src/lib/components/flows/linkedToolsFetchGuard.test.ts index ea1674e0b6..29207f58f7 100644 --- a/frontend/src/lib/components/flows/linkedToolsFetchGuard.test.ts +++ b/frontend/src/lib/components/flows/linkedToolsFetchGuard.test.ts @@ -8,7 +8,9 @@ vi.mock('./agentToolUtils', () => ({ isFlowModuleTool: () => false, agentToolToFlowModule: (t: unknown) => t })) -vi.mock('$lib/stores', () => ({ workspaceStore: { subscribe: (f: (v: string) => void) => (f('ws'), () => {}) } })) +vi.mock('$lib/stores', () => ({ + workspaceStore: { subscribe: (f: (v: string) => void) => (f('ws'), () => {}) } +})) import { claimLinkedToolsFetch, @@ -38,8 +40,8 @@ describe('linked tools fetch guard', () => { ) .mockResolvedValueOnce({ value: { tools: [tool('new')] } } as never) - const stale = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step') - await publishLinkedAgentTools('f/a/new', 'ws', scope, 'step') + const stale = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step', false) + await publishLinkedAgentTools('f/a/new', 'ws', scope, 'step', false) release?.({ value: { tools: [tool('old')] } }) await stale @@ -56,7 +58,7 @@ describe('linked tools fetch guard', () => { () => new Promise((r) => (release = r)) as ReturnType ) - const inFlight = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step') + const inFlight = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step', false) setLinkedAgentTools(scope, 'step', [tool('kept')], 'u/admin/a') invalidateLinkedToolsFetches(scope) @@ -73,7 +75,7 @@ describe('linked tools fetch guard', () => { () => new Promise((r) => (release = r)) as ReturnType ) - const inFlight = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step') + const inFlight = publishLinkedAgentTools('f/a/old', 'ws', scope, 'step', false) claimLinkedToolsFetch(scope, 'step') setLinkedAgentTools(scope, 'step', [tool('direct')], 'u/admin/a') release?.({ value: { tools: [tool('stale')] } }) diff --git a/frontend/src/lib/components/flows/utils.svelte.ts b/frontend/src/lib/components/flows/utils.svelte.ts index 8d8e4366e5..df27960dc7 100644 --- a/frontend/src/lib/components/flows/utils.svelte.ts +++ b/frontend/src/lib/components/flows/utils.svelte.ts @@ -17,6 +17,7 @@ import { get } from 'svelte/store' import type { FlowModuleState } from './flowState' import { type PickableProperties, dfs } from './previousResults' import { forEachFlowModule } from './dfs' +import { withAgentDrafts } from './linkedAgentDrafts' import { NEVER_TESTED_THIS_FAR } from './models' import { sendUserToast } from '$lib/toast' import type { ExtendedOpenFlow } from './types' @@ -187,6 +188,12 @@ export function jobsToResults(jobs: Job[]) { }) } +/** + * Run the flow the editor currently holds. A step linked to a saved agent runs that agent's + * unsaved draft when there is one (`withAgentDrafts`), so testing exercises what the agent editor + * is showing rather than the deployed resource — the same rule the agent editor's own test pane + * follows. The value passed in is left alone; only what goes to the server is substituted. + */ export async function runFlowPreview( args: Record, flow: OpenFlow & { tag?: string }, @@ -198,14 +205,15 @@ export async function runFlowPreview( // editor; falls back to the navigation workspace for full-page previews. workspace?: string ) { - const newFlow = flow + const ws = workspace ?? get(workspaceStore) ?? '' + const value = await withAgentDrafts(flow.value, ws) return await JobService.runFlowPreview({ - workspace: workspace ?? get(workspaceStore) ?? '', + workspace: ws, requestBody: { args, - value: newFlow.value, + value, path: path, - tag: newFlow.tag, + tag: flow.tag, restarted_from: restartedFrom, temp_script_refs: tempScriptRefs }, diff --git a/frontend/src/lib/userDraft.svelte.ts b/frontend/src/lib/userDraft.svelte.ts index 24572ee1ab..7942694f31 100644 --- a/frontend/src/lib/userDraft.svelte.ts +++ b/frontend/src/lib/userDraft.svelte.ts @@ -349,6 +349,32 @@ export const UserDraft = { void UserDraftDbSyncer.save({ workspace: ws, itemKind, path, value: null }) }, + /** + * Drop this key's in-memory cell and cached write WITHOUT touching the + * server. For callers that have already deleted the row by another route + * (a deploy) and only need the local mirror to stop answering `get`/`has` + * with a value that is gone. + * + * MUST be used instead of `remove` there. `remove` POSTs its own + * `value: null`, and that POST is debounced and carries whatever + * `last_sync` is left — which a preceding successful delete has already + * cleared. The backend treats a delete with no `last_sync` as + * unconditional, so the second POST lands ~1.5s later with nothing to + * compare against and removes a draft saved in the meantime. + */ + forgetLocal(itemKind: UserDraftItemKind, path: string, opts?: UserDraftOptions): void { + const ws = resolveWorkspace(opts) + const mk = mapKey(ws, itemKind, path) + const entry = entries.get(mk) + if (entry) { + // Same as `remove`: clear the cell so live observers see the delete, and arm + // `skipNextSync` so the mirror does not turn that write into a POST of its own. + entry.skipNextSync = true + entry.state.val = undefined + } + writtenCache.delete(mk) + }, + clear(itemKind: UserDraftItemKind, path: string, opts?: UserDraftOptions): void { UserDraft.discard(itemKind, path, undefined, opts) }, diff --git a/frontend/src/lib/utils_draft_deploy.test.ts b/frontend/src/lib/utils_draft_deploy.test.ts index 9bed95917b..4495155f24 100644 --- a/frontend/src/lib/utils_draft_deploy.test.ts +++ b/frontend/src/lib/utils_draft_deploy.test.ts @@ -7,7 +7,7 @@ vi.mock('$lib/gen', () => ({ DraftService: { deleteDraft: vi.fn() }, AppService: {}, VariableService: {}, - ResourceService: {}, + ResourceService: { getResource: vi.fn(), updateResource: vi.fn(), createResource: vi.fn() }, ScheduleService: {}, HttpTriggerService: {}, WebsocketTriggerService: {}, @@ -21,7 +21,9 @@ vi.mock('$lib/gen', () => ({ AzureTriggerService: {}, EmailTriggerService: {} })) -vi.mock('$lib/userDraftDbSyncer.svelte', () => ({ UserDraftDbSyncer: { save: vi.fn() } })) +vi.mock('$lib/userDraftDbSyncer.svelte', () => ({ + UserDraftDbSyncer: { save: vi.fn(), recordRemoteSync: vi.fn() } +})) vi.mock('$lib/workspaceDrafts.svelte', () => ({ invalidateWorkspaceDrafts: vi.fn() })) vi.mock('$lib/workspaceComparison', () => ({ invalidateWorkspaceComparison: vi.fn() })) vi.mock('$lib/localDraftHints.svelte', () => ({ setLocalDraftHint: vi.fn() })) @@ -30,7 +32,8 @@ vi.mock('$lib/components/raw_apps/utils', () => ({ canonicalRawAppDiffValue: vi. vi.mock('$lib/appDiffSides', () => ({ classicAppDraftParts: vi.fn() })) vi.mock('$lib/utils_deployable', () => ({ TRIGGER_RUNTIME_IGNORE: [] })) -import { ScriptService, FlowService } from '$lib/gen' +import { ScriptService, FlowService, ResourceService } from '$lib/gen' +import { UserDraftDbSyncer } from '$lib/userDraftDbSyncer.svelte' // draftBaseIsStale compares a draft's base pointer against the deployed head // of the item it was fetched with (`get_draft=true`). Shared by CompareDrafts @@ -124,3 +127,65 @@ describe('deployDraft preserves on_behalf_of', () => { ) }) }) + +// The resource branch reads the item again when the deploy lands, and falls back to the deployed +// row when the draft has gone. That row keeps its value under `value` and carries no `args` at +// all, so reading it as a draft (`value: d.args ?? {}`) would replace a live resource with `{}`. +describe('deployDraft: resource with no draft', () => { + beforeEach(() => vi.clearAllMocks()) + + it('writes nothing rather than `{}` over the deployed value', async () => { + vi.mocked(ResourceService.getResource).mockResolvedValueOnce({ + path: 'f/support/triage_agent', + resource_type: 'ai_agent', + value: { system_prompt: 'deployed' } + } as any) + + // `noop` is what lets a caller deploying one specific draft tell "nothing to promote" apart + // from "deployed", instead of reporting an agent as deployed that was never written. + expect(await deployDraft('resource', 'f/support/triage_agent', 'ws')).toEqual({ + success: true, + noop: true + }) + expect(ResourceService.updateResource).not.toHaveBeenCalled() + expect(ResourceService.createResource).not.toHaveBeenCalled() + // Nor does it touch the draft row. There was none of this user's to delete, so the only row + // the cleanup could reach is one written after the read: an edit destroyed without ever + // having been deployed. Clearing the baseline would be the same bug by another route, since + // a delete with no baseline is the unconditional one. + expect(UserDraftDbSyncer.save).not.toHaveBeenCalled() + expect(UserDraftDbSyncer.recordRemoteSync).not.toHaveBeenCalled() + }) + + it('still deploys normally when the draft is there, and keys the cleanup to the row it read', async () => { + vi.mocked(ResourceService.getResource).mockResolvedValueOnce({ + path: 'f/support/triage_agent', + resource_type: 'ai_agent', + value: { system_prompt: 'deployed' }, + draft_saved_at: '2026-01-01T00:00:00Z', + draft: { path: 'f/support/triage_agent', args: { system_prompt: 'drafted' } } + } as any) + + expect(await deployDraft('resource', 'f/support/triage_agent', 'ws')).toEqual({ success: true }) + expect(ResourceService.updateResource).toHaveBeenCalledWith( + expect.objectContaining({ + requestBody: expect.objectContaining({ value: { system_prompt: 'drafted' } }) + }) + ) + // The draft delete that follows is conditional on this baseline. With no baseline the backend + // deletes unconditionally, destroying a draft saved between the read and the delete without + // ever having deployed it, so the timestamp has to be the one from the row just promoted. + expect(UserDraftDbSyncer.recordRemoteSync).toHaveBeenCalledWith( + { workspace: 'ws', itemKind: 'resource', path: 'f/support/triage_agent' }, + '2026-01-01T00:00:00Z' + ) + expect(UserDraftDbSyncer.save).toHaveBeenCalledWith( + expect.objectContaining({ path: 'f/support/triage_agent', value: null, immediate: true }) + ) + // Order is the whole point: a delete issued before the seed carries whatever baseline the tab + // happened to hold, which for a caller that only read through a listing is none at all. + expect(vi.mocked(UserDraftDbSyncer.recordRemoteSync).mock.invocationCallOrder[0]).toBeLessThan( + vi.mocked(UserDraftDbSyncer.save).mock.invocationCallOrder[0] + ) + }) +}) diff --git a/frontend/src/lib/utils_draft_deploy.ts b/frontend/src/lib/utils_draft_deploy.ts index b322d6adc4..f322bb27b9 100644 --- a/frontend/src/lib/utils_draft_deploy.ts +++ b/frontend/src/lib/utils_draft_deploy.ts @@ -435,8 +435,13 @@ export async function deployDraft( path: string, workspace: string, opts: { draftOnly?: boolean; rawApp?: boolean; deploymentMessage?: string } = {} -): Promise { +): Promise { const { draftOnly = false, rawApp = false, deploymentMessage } = opts + // Set when the branch found nothing to promote and wrote nothing. Success, because the item is + // already at the value a deploy would have left it at and its stale draft state still wants + // clearing — but a caller deploying one specific draft it showed the user has to be able to tell + // that apart from having deployed it. + let noop = false try { if (kind === 'raw_app' || (kind === 'app' && rawApp)) { // Raw apps bundle their source files and deploy via the raw-app @@ -579,10 +584,34 @@ export async function deployDraft( } void deployed } else if (kind === 'resource') { - const { deployed, draft: d } = splitOverlay(await OVERLAY_GETTERS.resource!(workspace, path)) + const overlay = await OVERLAY_GETTERS.resource!(workspace, path) + // Adopt the row this promote is based on as the baseline for the delete below. Without one + // the backend deletes unconditionally, so a draft saved between that read and the delete is + // destroyed having never been deployed — a caller that only ever read through a listing has + // no baseline of its own to supply. With it the delete is refused instead and the newer + // draft survives, which is the recoverable outcome of the two. Only ever seeded, never + // cleared: passing no timestamp drops whatever baseline the tab already held, which would + // turn that same delete back into an unconditional one. + if (overlay?.draft_saved_at) { + UserDraftDbSyncer.recordRemoteSync( + { workspace, itemKind: kind, path }, + overlay.draft_saved_at + ) + } + const { deployed, draft: d, hasDraft } = splitOverlay(overlay) // ResourceEditor's `ResourceState` draft shape: // { path, description, args, resource_type?, labels?, wsSpecific } - if (draftOnly) { + // The deployed row is a different shape (`value`, `ws_specific`, no `args` at all), and + // `splitOverlay` hands it back as the draft side when the draft row has gone — deployed or + // discarded from another tab between the listing and this click. Reading it as a draft is + // what made `value: d.args ?? {}` replace a live resource with `{}`. Nothing to promote + // then, so write nothing and fall through to the cleanup below, which clears the stale + // local draft hint and the drafts listing. The item is already at the value a successful + // deploy would have left it at, so this reports success rather than an error, matching + // what the other kinds end up doing when their own draft is gone. + if (!hasDraft) { + noop = true + } else if (draftOnly) { await ResourceService.createResource({ workspace, requestBody: { @@ -633,8 +662,8 @@ export async function deployDraft( return { success: false, error: `Deploy not supported for draft kind ${kind}` } } // Delete the draft at its STORAGE path (the row key, = the `path` arg). - // Two reasons it must happen here for every kind, mirroring the editors' - // post-deploy `discardDraftAfterDeploy(draftPath)`: + // Two reasons it must happen here for every kind that promoted something, + // mirroring the editors' post-deploy `discardDraftAfterDeploy(draftPath)`: // - Drawer kinds (variable / resource / triggers) aren't deleted by // their create/update endpoints at all. // - script/flow/app/raw_app DO delete server-side, but only the draft at @@ -642,13 +671,18 @@ export async function deployDraft( // synthetic `u/{user}/draft_{uuid}` storage path ≠ `d.path`, so its // draft row survives the deploy and keeps listing. Deleting the // storage-path draft removes it (a no-op when the server already did). - await UserDraftDbSyncer.save({ - workspace, - itemKind: kind, - path, - value: null, - immediate: true - }) + // Skipped when nothing was promoted: the read that set `noop` found no draft of this user's to + // delete, so the only row this could reach is one written after it — destroying an edit that + // was never deployed, and never even listed. + if (!noop) { + await UserDraftDbSyncer.save({ + workspace, + itemKind: kind, + path, + value: null, + immediate: true + }) + } // Mutated the workspace's Server Drafts — refresh every mounted reader. invalidateWorkspaceDrafts(workspace) // The DEPLOYED state moved: cached fork comparisons involving this @@ -659,7 +693,7 @@ export async function deployDraft( // so the syncer-owned hint won't auto-clear — clear it explicitly. // (Idempotent: the drawer-kind delete above already cleared it.) setLocalDraftHint(workspace, kind, path, false) - return { success: true } + return noop ? { success: true, noop: true } : { success: true } } catch (e: any) { return { success: false, error: e?.body ?? e?.message ?? String(e) } }