The durable-memory demo depends on the Intelligence platform's recall_memory /
save_memory tools, which are served from `${apiUrl}/mcp` and attached to the
local BuiltInAgent run via MCP middleware ONLY when CopilotKitIntelligence is
constructed with `enableEnterpriseLearning: true` (gated in
attachIntelligenceEnterpriseLearning). The banking route never set the flag, so
in any real (non-aimock) run the memory tools never loaded: save_memory was a
no-op during teaching and recall_memory was absent, making the agent re-offer
workflow recording on every over-limit charge instead of recalling the learned
procedure.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The teach-flow's multi-step tool sequencing is the weak spot for the mini model;
the non-mini gpt-5.4 follows the recall->offer->demonstrate->save routing far
more consistently. openai/gpt-5.4 is the alias already used across the repo.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
My collapse fix branched on isRecording, but the render closure captures a stale
isRecording (false), so clicking 'Start recording' wrongly collapsed the card to
'Okay — not recording.'. Branch on the resolved `result` instead (fresh on
complete, like the save card): onDeny resolves 'declined' -> 'not recording';
onApprove resolves the directive -> 'Recording started'. Drops the now-unused
isRecording destructure.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The 'Record a workflow?' card appeared inconsistently because two intro prompt
lines still steered the agent the wrong way on an over-limit approve — 'review
... over-limit charges -> showPendingApprovals' and 'showApprovalFlow -> explain
how an over-limit charge gets cleared' — competing with the recall->offer block.
Scope both to browse/explain only and exclude them from the approve path, and
drop the agent temperature 0.3 -> 0 so it picks the same route every time.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Same lingering-button bug as the offer card: saveLearnedWorkflow and
awaitDashboardDemonstration only special-cased status 'inProgress', so after
clicking 'Save workflow' / 'I'm done' the card kept its button (confusing —
looked like nothing happened, though the save/respond went through). Add a
status 'complete' branch that collapses each to a static line, using the HITL
render's 'result' to show saved vs discarded / finished vs cancelled.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
On 'approve the over-limit charge' with no saved procedure, gpt-5.4-mini
sometimes called showApprovalFlow ('diagram of how to clear an over-limit
charge') or showPendingApprovals ('...including over-limit charges') instead of
recall_memory -> offerWorkflowRecording, so it never asked to record. Scope
those two tools to their real uses (explainer only when asked how it works;
queue only for reviewing pending) and explicitly exclude them from the
over-limit approve path. The approval-flow diagram stays as an informational
tool — just not a response to an approve request.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
After 'Start recording', offerWorkflowRecording resolved a bare 'started', so
gpt-5.4-mini often just SAID awaitDashboardDemonstration's 'go ahead and I'll
watch' line (from its description) instead of CALLING it — leaving the offer
card frozen with the Start-recording button and a confusing text reply, even
though recording (the vignette) had begun.
- Resolve a directive result telling the agent to immediately call
awaitDashboardDemonstration and not reply in prose (mirrors the working
awaitDashboardDemonstration -> saveLearnedWorkflow beat).
- Collapse the offer card to a static line once resolved (status 'complete')
so the button can't linger or be re-clicked; the live 'Recording your
workflow' card takes over.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Generalizes the row-action dropdown fix: every shadcn overlay (Select,
DropdownMenu, Popover, Tooltip) portals to <body> at z-50 and renders behind
the CopilotKit chat sidebar (z-1200) when opened in-chat — the policy-code
Select in the exception form hit this too. One globals.css rule lifts every
Radix popper wrapper to z-1300 (the file's existing 'above the chat panel'
value), fixing the whole class instead of per-component patches.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The 'More actions' menu portals to <body> at z-50, but the CopilotKit chat
sidebar is z-1200 — so the menu opened BEHIND the panel and was invisible
(clicking the three-dots appeared to do nothing). Lift this dropdown's content
to z-[1300] so it renders in front of the panel. Pairs with the earlier
pointer-events-auto fix; together the row's overflow menu works in-chat.
Verified: menu computed z-index is now 1300 vs panel 1200.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
showPendingApprovals is a display-only useComponent, which CopilotKit paints
pointer-events:none on the assistant message. The table is interactive
(Approve / Deny / File policy exception 'More actions' menu), so the inherited
none made every row action unclickable in the chat. Opt the card subtree back
into pointer events.
Verified live: the 'More actions' button's computed pointer-events flips
none -> auto with the fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Re-running the over-limit teach demo mutates the in-memory store (approve +
filed exception flip the charge overLimit→cleared). This endpoint re-seeds the
store in place so the $5,000 Google Ads / Marketing charge (t-1) returns to
pending/over-limit without a server restart. Gated off when NODE_ENV=production.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Drops the non-existent AIMock/MockServer fallback names (TS-flagged once aimock was
installed); LLMock/loadFixtureFile/validateFixtures are the real exports.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
AUTHORED + statically validated (playwright --list compiles spec+config, fixtures/
package JSON valid, launcher syntax OK). NOT yet green-verified — needs aimock
installed (pnpm i), the docker memory stack up, and the dev server in Intelligence
mode (multi-process; not runnable in the current sandbox). Each file carries a
'VERIFY ON FIRST GREEN RUN' checklist for the shakedown.
- e2e/memory-learning.spec.ts: seeds the procedure via REST (recall-half isolation
per the plan), drives a fresh thread, asserts recall->unlock with no recording
offer + the over-limit gate lifted. Save half stays HITL+LLM (drift smoke / manual).
- e2e/fixtures/memory-learning.fixtures.json: pins recall_memory -> openPolicyException
-> finalizePolicyException -> approveTransaction.
- e2e/aimock-server.mjs: aimock launcher (programmatic, CLI fallback documented).
- playwright.config.ts: webServer array (aimock + dev in Intelligence mode, OPENAI_BASE_URL->aimock).
- package.json: +@copilotkit/aimock devDep; test:self-learning -> the spec.
- remove scripts/self-learning-smoke.mjs (dead #192 distill path).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- README: replace dead sl-worker/knowledge/annotate Phase-C section with the
memory runbook (docker compose one-command stack, host-TEI override for Apple
Silicon, 715x ports, .env, cross-thread+cross-persona FOR-149 walkthrough,
aimock E2E + drift-smoke testing notes)
- scripts/memory-drift-smoke.mjs: non-gating real-LLM tripwire that the live model
still emits recall_memory on a fresh-thread over-limit request (save half is
HITL-gated; covered by the manual walkthrough + aimock E2E)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Save action now resolves a string the agent reads as status:saved + an explicit
save_memory(scope:project, kind:operational) instruction with the demonstrated
code, preserving the already-approved/don't-re-run guard. respond() takes a
string in this file, so the result is delivered as text the recall-first prompt
(Task 3) acts on.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Surfaced while verifying Task 0 against a live stack:
- minio-init: retry mc alias set until Docker DNS resolves (idempotent bucket create)
- embedder pluggable: MEMORY_EMBEDDINGS_URL overridable + bundled tei dependency required:false
(point at host/native TEI on RAM-constrained Apple Silicon where the emulated tei OOMs)
- deps default host ports remapped to 715x so a bare `docker compose up` coexists with a dev's Intelligence stack
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve the single conflict in packages/web-inspector/src/index.ts by keeping
both additions: this branch's CpkMemoryList memory-tab element and main's
ɵCpkThreadDetails back-compat alias (independent top-level declarations).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The chart components' descriptions steered the model to answer chart-shaped
questions BY rendering ("do NOT answer in plain text"), which it obeyed too
literally: "which policy is closest to its limit?" produced the right chart
and no answer. Every chart description now carries the same rule — the chart
replaces restating the raw numbers, not the answer itself; follow the render
with one or two grounded sentences. Pending-approvals card gets the matching
"point at what needs attention" line.
Verified live: the budget-usage pill now yields the chart plus "The Marketing
policy is closest to its limit…".
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Dismissal was persisted in sessionStorage, so after one engagement the
demo's opening beat — the copilot noticing breached charges before the
user types or clicks anything — never appeared again for the whole tab
session. Demo-wrong: every fresh load must open with it. Dismissal is now
per-page-load component state; within a load it still never re-nags (the
wrapper stays mounted across client-side navigation).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Click-around feedback fixes on the banking demo:
- In-chat pending approvals are now actually usable: the dashboard's 4-column
approval table is ~550px wide, so inside the chat card its Actions column
rendered past the card edge — visible but unclickable. New
PendingApprovalsChat stacks each charge as a chat-width card with labeled
Approve/Deny/File-exception actions, with exact behavioral parity
(over-limit gating, PolicyExceptionInline form, identical teach-mode
recordUserAction payloads and logStep narration).
- Suggestion bubbles never disappear: the full use-case catalog (12 pills —
the 4 self-learning arc beats plus charts, breakdowns, cash flow, approvals
explainer, report prep, PIN change, team invite) is registered with
available:"always", so the demo stays fully click-drivable after every
exchange. Panel widened 440→560px so pills flow two-per-row instead of
stacking.
- StatisticsChart (dashboard rail + spending-trend gen-UI) is a real chart
now: y-axis dollar gridlines, x-axis labels aligned to the plot area, and
pointer hover showing the exact month + amount with a guide line and
highlighted point. Still hand-rolled SVG, no charting dependency.
Validated with Playwright: approvals filed and approved entirely inside the
chat (Cleared state transition + queue drains), pills persist after
exchanges, tooltip renders on hover.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Make the banking demo pass the click-around test: every moment reachable by
clicking, zero typing, and the dead Analytics/Reports tabs replaced with real
views (FOR-190; claims FOR-178).
Additive modules under src/components/wow/:
- ProactiveNotice: on load, the copilot surfaces overnight policy breaches
unprompted and offers to walk through them (tap-to-accept -> existing
pending-approvals gen-UI). Session-scoped dismissal.
- ChartCard + AnalyticsView: the four brand charts (previously chat-only)
rendered as the dashboard's Analytics tab, each carrying contextual
conversation-starter pills grounded via the existing useAgentContext data.
- createReport tool + ReportsView: "prep the Q2 spend report" files a durable
artifact (summary + highlights + live charts) in the Reports tab through a
new /api/v1/reports REST route and store collection.
- useAskCopilot: shared open-panel + addMessage + runAgent helper (same path
a suggestion-pill click takes).
Correctness fixes found by a full Playwright click-through sweep:
- navigateToPageAndPerform: full-page reload tore down the chat panel mid-run
(conversation and in-flight operation lost); now client-side router.push.
Card operations also targeted /cards, which mirrors the dashboard and has no
card tools — they now land on / where the tools are registered.
- chat-inbox: CSS custom property cast so `next build` compiles again
(production build was failing on main, blocking deploy).
Validated end-to-end with Playwright against a live agent, including the full
teach -> demonstrate -> save -> recall arc in OSS mode.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Address PR review: delete the 4 stray package.json.bak files left by the
version-bump tooling, and restore examples/teams/appPackage/{color,outline}.png
to main (the de-fork commit had rewritten them into raw LFS-pointer text —
incidental fallout unrelated to this PR's scope).
A stray comment edit left langgraph-js's example-layout/index.tsx one line
off from the langgraph-python north-star, tripping the verbatim parity check.
Match it exactly.
The drawer shipped in 1.62.1 (react-core + the previously-missing
web-components package). Move the de-forked examples off the workspace:*
placeholder (and 1.61.0 runtime) onto the published 1.62.1, so they consume
the real SDK CopilotThreadsDrawer. Verified: a standalone install + next build
of pydantic-ai resolves CopilotThreadsDrawer from the published packages.
Rename import + usage from CopilotDrawer to CopilotThreadsDrawer across the
de-forked examples, and drop the now-redundant onUpsell handler: ENT-1027
makes the element open the Intelligence docs URL by default via licenseUrl.
Comments updated; --cpk-drawer-* tokens unchanged. Holds until the drawer
packages are published.
Replace the hand-rolled threads-drawer fork in every threads-enabled
integration example with the SDK <CopilotDrawer> (uncontrolled
CopilotChatConfigurationProvider + reserved-column layout + theme no-flash
where applicable). 16 examples; all browser/build-validated locally.
DRAFT — depends on #5707 and the subsequent npm release; not mergeable until
the SDK publishes @copilotkit/web-components and react-core bumps. Pre-merge
TODOs in the PR description.
## What does this PR do?
This PR fixes build failures on Windows by replacing Unix-only shell
commands (`rm -rf`, `cp`, `mkdir -p`) in `package.json` scripts with
cross-platform Node.js `fs` built-in commands.
This follows the project's existing codebase pattern for cross-platform
operations, as seen in `packages/react-ui/package.json` (line 45).
### 🛠️ Changes:
- **`packages/runtime`**: Replaced `rm -rf` in `generate-graphql-schema`
with `fs.rmSync`.
- **`packages/vue`**: Replaced `cp` in `build:types` and `rm -rf` in
`clean` with `fs.cpSync` and `fs.rmSync`.
- **`packages/angular`**: Replaced `mkdir -p` and `cp` in `build:css`
with `fs.mkdirSync` and `fs.cpSync`.
- **`examples/v1/next-openai`, `next-pages-router`, `state-machine`**:
Replaced `rm -rf` clean commands with a single Node.js loop that deletes
`.turbo`, `node_modules`, `dist`, and `.next`.
All modified packages now build successfully on Windows.
## Related PRs and Issues
- Closes#5601
## Checklist
- [x] I have read the [Contribution
Guide](https://github.com/copilotkit/copilotkit/blob/master/CONTRIBUTING.md)
- [ ] If the PR changes or adds functionality, I have updated the
relevant documentation
- [x] "Allow edits by maintainers" is checked (lets us help iterate on
your PR directly — faster turnaround for everyone)
Adds /a2ui-catalog page and a runtime endpoint with NO a2ui config, so
A2UI switches on purely from the provider's a2ui.catalog (the #5774
path). Also fixes DemoButtonAgent, which never actually rendered: it
emitted the wrong activity content key (operations -> a2ui_operations)
and a non-canonical operation/component format. Rewritten to the A2UI
v0.9 wire format (createSurface/updateComponents, flat components, root
id "root") so the surface paints and the Confirm round-trip works.
Same class as the toggle-theme fix: langgraph-js's 'schedule a meeting' chip
returned text, so the meeting picker never rendered, while langgraph-python emits
the scheduleTime tool call. scheduleTime is a registered langgraph-js frontend
tool (reasonForScheduling/meetingDuration) — swap text -> tool call, mirroring
langgraph-python. Because scheduleTime is Human-in-the-Loop (the user's pick
returns as a tool result and re-invokes the LLM), add a terminating
call_schedule_time_001 result fixture in BOTH templates so the turn doesn't
re-match the user message and loop (langgraph-python lacked it too — latent).
Verified both terminate at 2 steps (tool call -> terminating text).
The langgraph-js Toggle Theme chip returned a text response claiming it toggled
the theme, but emitted no tool call -- so the theme never changed, while the same
chip in langgraph-python emits the toggleTheme frontend tool call and works.
Identical chip, different outcome by template. Swap the text response for the
toggleTheme tool call, mirroring langgraph-python (frontend tool, no terminating
result fixture needed -> no loop). Verified aimock now returns the toggleTheme
tool call for the chip.
The chart-chain fixtures looped under multi-step tool execution: langgraph-python
emitted a 2nd tool call (pieChart/barChart/dashboard) with no terminating
toolCallId result fixture, so it fell through to the still-matching userMessage
fixture and re-called query_data. langgraph-js had its toolCallId result fixtures
ordered after the userMessage fixtures (first array match wins -> re-call).
Add the missing terminating result fixtures (langgraph-python) and reorder so all
toolCallId fixtures precede userMessage fixtures (langgraph-js). Verified termination
via the 2-3 step multi-turn repro; mastra fixtures already terminated.
The 6 OpenAI drop-in integration examples enabled for the CLI's keyless
AIMock mock mode shipped fixtures that did not cover the prompts each
starter's own UI suggests, so a keyless first-run user clicking the demo
suggestions mostly hit the generic catch-all. Re-key/extend each
example's fixtures/default.json (substring, most-specific-first,
catch-all last) so the surfaced suggestions return scripted replies.
ENT-1003.
Ports two fixes from the canonical oracle-cookbook demo into the oracle-agent-memory
showcase agent (server.py was byte-identical to the demo's pre-fix version):
1. Dangling tool-calls: booking conversationally calls the book_flight HITL tool,
which interrupts and emits an assistant tool_call awaiting the UI's Confirm/Cancel.
If the traveler sends another chat message instead, the unanswered tool_call made
the next turn 400 ("tool_call_ids did not have response messages"). _repair_dangling_tool_calls
synthesizes a "not completed" tool result for any dangling call before the history
reaches the graph. (Inverse of the duplicate-tool-block issue the history-replace
already handled — documented in docs/known-issues/agentspec-multiturn-toolcall-correlation.md.)
2. HTML-escaped persistence: the agentspec exporter HTML-escapes streamed deltas
(& < > -> & < >); the SSE generator persisted them raw, so assistant
replies were stored in Oracle Agent Memory as e.g. "fares < $700".
_clean_assistant_text html.unescapes the assembled text before persisting.
Both are reproduced + verified in oracle-cookbook (unit tests + in-browser); the ported
functions are byte-identical to the verified demo code.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Flag-gated (LANGGRAPH_CHECKPOINTER=oracle, default memory) AsyncOracleSaver from
langgraph-oracledb for durable per-thread LangGraph graph state in Oracle,
complementing oracleagentmemory. Default-safe (in-memory fallback). Mirrors
jerelvelarde/oracle-cookbook#4. Draft, stacked on #5563.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Maxim