mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
codex/cloudplot-showcase-migration
15424 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Ben Taylor
|
01550e6358 |
fix(channels-intelligence): classify channel_not_declared as setup-required (#6198)
## What does this PR do?
A runtime that declares a managed channel the Intelligence project does
not have
crashed startup: `ready()` rejected and the channel settled to `error`.
```
realtime gateway session join failed: channel_declaration_unavailable (channel states: runtime_not_declared)
status: { overall: "error", channels: { "managed-teams-probe": "error" } }
```
Creating the channel and attaching credentials is the setup step every
new
channel goes through, so this was the first run of *every* managed
channel,
before anyone reached the happy path.
### Cause
app-api had no declaration-response token for "the project has no
channel by that
name", so it sent `runtime_not_declared`. That token means the inverse
on a join —
a channel exists but no runtime declared it, while on a join the runtime
is the
one declaring. `classifyJoinError` read it literally, which was correct,
and so
treated a benign setup gap as a hard failure.
The fix is split by which side owns the mistake. app-api now sends
`channel_not_declared` for that case (Intelligence#615). This PR teaches
the
classifier the new token.
### Change
- `channel_not_declared` added to `SETUP_REQUIRED_CHANNEL_STATES`, so
the channel
settles to `setup_required` and `ready()` resolves.
- `runtime_not_declared` keeps its literal reading and stays a hard
error, as do
`runtime_conflict`, `platform_setup_failed`, `delivery_failed`,
`egress_failed`
and `runtime_offline`.
- Retired the `TODO (gateway-owner)` the classifier carried, which asked
whether
`runtime_not_declared` was ever benign. It was — but not for the reason
the
comment guessed. The server was overloading the token, not racing a
heartbeat.
Replaced the TODO with what the answer turned out to be.
- Documented that `SETUP_REQUIRED_CHANNEL_STATES` now draws on two
Intelligence
vocabularies: most members are read-model `CHANNEL_STATE_KINDS`, while
`channel_not_declared` is declaration-only and has no read-model
counterpart.
An SDK without this change treats the unknown token as a hard error,
which is the
pre-fix behavior — so old clients are no worse off, they just keep the
bug.
## Related PRs and Issues
- Server side: CopilotKit/Intelligence#615
- OSS-622
## Checklist
- [x] I have read the Contribution Guide
- [x] If the PR changes or adds functionality, I have updated the
relevant documentation
- [x] "Allow edits by maintainers" is checked
## Tests
Added `classifies channel_not_declared as SETUP_REQUIRED (OSS-622)`,
plus an
`error-channel-not-declared` join mode. RED before the fix: the join
produced
`RealtimeGatewayChannelStateError` instead of
`RealtimeGatewaySetupRequiredError`.
`npx vitest run src/realtime-gateway.test.ts` — 21 pass.
33 failures elsewhere in this package reproduce on `origin/main` with
these
changes stashed (a stale `@copilotkit/channels` build missing the
`ɵruntime`
symbol) and are unrelated.
|
||
|
Benjamin Taylor
|
3f0bbe4a7b |
feat(runtime): default the Intelligence platform URLs to the managed service
`CopilotKitIntelligence` required `apiUrl` and `wsUrl` on every construction,
so the two correct hosts had to be found and copied by hand — which is how an
agent came to invent them. Both now default to CopilotKit's managed platform,
making `new CopilotKitIntelligence({ apiKey })` the whole managed-service setup.
Overrides are unchanged for self-hosted and non-production deployments, with two
guards that the previous required-field signature made unnecessary:
- A blank value counts as unset. These URLs are usually wired from env vars, and
a declared-but-empty variable arrives as `""`, which would otherwise produce
host-relative requests instead of falling back to the managed platform.
- Setting only one of the pair warns. The API and realtime planes are separate
hosts, so a lone override silently splits the client across two deployments —
and that failure surfaces as a hang, not an error.
Sweeps the doc, skill, README, and example surfaces to the short form so the
copy-paste path no longer hands anyone URLs to get wrong, and reattaches the
`CopilotKitIntelligence` class JSDoc, which was orphaned above an interface and
so never appeared on hover.
Linear: OSS-638
|
||
|
Benjamin Taylor
|
956c6448a7 |
fix(runtime): non-optional listener.channels and honest lifecycle docs (OSS-646)
`createCopilotNodeListener` now mirrors `createCopilotRuntimeHandler`'s branded overload pair, so a runtime with at least one declared Channel yields a listener whose `.channels` is non-optional and the documented `listener.channels.ready()` call type-checks with no `!` and no `?.`. `activateChannels: false` and channel-less runtimes keep the optional shape. Both listener types are exported from `@copilotkit/runtime/v2/node`. Corrects TSDoc on the node, express, and hono wrappers that still claimed activation happens "at creation time" and labelled `ready()` as optional — stale since activation was deferred to make the Fetch handler serverless-safe. On a long-running host that call is required, not optional. Fixes a live consequence of that stale model: `examples/slack/app/managed.ts` never called `ready()`, so it mounted a listener, logged "started managed Channel", and connected nothing. Covered by a regression assertion. Drops the now-unnecessary `?.` from the examples, READMEs, and channel docs, and adds compile-time contracts for the listener shape alongside the existing handler ones. The examples compile with `strict: true`, so they prove the `?.`-free call under strict null checks, which the runtime package (strict: false) cannot. |
||
|
Benjamin Taylor
|
a9a073e145 |
test(channels): cover fallback run_error egress-failure and partial-text ordering (OSS-491)
Close two assert-without-a-test gaps found in review of the OSS-491 fix: a failed error-post emit on the fallback run_error path propagates (drain rejects → the delivery nacks/retries rather than acking a dropped error), and buffered partial text is flushed before the error post (order preserved, no lost or duplicated output). |
||
|
Benjamin Taylor
|
fc0bb4f498 |
fix(channels): surface run_error on HTTP-fallback path and isolate ack failures (closes OSS-491)
Two pre-existing SDK delivery / terminal-signal defects in the managed channels adapter, surfaced by the pre-merge adversarial CR of #5972 and deliberately left out of that PR's scope. Both bite the HTTP-fallback / self-hosted path (no Connector Outbox); the realtime + Outbox path is unchanged. Finding 1 (HIGH) — run_error swallowed on the HTTP-fallback render path, delivery acked as SUCCESS. `renderSinkFor`'s ad-hoc plain-text sink had no `run_error` branch, so an agent-side failure with no accompanying text (model error, tool crash, upstream 5xx) resolved the run, drained, and acked the delivery as success — no user-visible message and nothing logged ("bot goes silent on every error"). Now the fallback sink logs the raw error via `config.log`, flushes any buffered partial text, and posts a generic user-visible error. Posted + logged + acked (not nacked) on purpose: a run_error is frequently a deterministic agent failure and the Channel path reprocesses redeliveries (skipIngressDedup), so nacking would livelock. A genuine egress failure of the error post itself still nacks (emit throws → drain rejects). Also: `onRunErrorEvent` now calls `ensureRunStarted()` so a run_error that precedes any text/tool event still emits a preceding run_started. Finding 2 (LOW) — a failed ack() nacked an already-processed turn. `ack()` sat inside the same try as `dispatchTo`, so an ack network failure fell into the catch and nacked a completed turn with a misleading reason; because the Channel path reprocesses redeliveries, the whole turn reran (duplicate agent run / posts). Ack is now a distinct phase: a failed ack is logged, never conflated with a turn failure and never nacked. |
||
|
Tyler Slaton
|
2eba274a99 | fix(channels-core): default runAgent prompt from inbound message | ||
|
Benjamin Taylor
|
fdcc0150ab |
fix(channels-intelligence): classify channel_not_declared as setup-required
A runtime that declares a managed channel the Intelligence project does not have crashed startup: ready() rejected and the channel settled to error. Creating the channel and attaching credentials is the setup step every new channel goes through, so this was the first run of every managed channel, before the happy path. app-api had no declaration-response token for "the project has no channel by that name", so it sent runtime_not_declared. That token means the inverse on a join — a channel exists but no runtime declared it, while on a join the runtime is the one declaring. classifyJoinError read it literally, which was correct, and so treated a benign setup gap as a hard failure. app-api now sends channel_not_declared for that case (Intelligence#615). Adding it to SETUP_REQUIRED_CHANNEL_STATES lets the channel settle to setup_required and ready() resolve. runtime_not_declared keeps its literal reading and stays a hard error, as do runtime_conflict, platform_setup_failed, delivery_failed, egress_failed and runtime_offline. This also answers the TODO(gateway-owner) the classifier carried, which asked whether runtime_not_declared was ever benign. It was, but not for the reason the comment guessed: the server was overloading the token, not racing. Replaced the TODO with what the answer turned out to be. npx vitest run src/realtime-gateway.test.ts: 21 pass 33 failures elsewhere in this package are pre-existing on origin/main (a stale @copilotkit/channels build missing the runtime symbol) and unrelated. |
||
|
Benjamin Taylor
|
5c2faac569 |
test(runtime,shared): make telemetry tests control their own env
The OSS-565 workflow env vars leaked into the unit job and turned 17 tests red across @copilotkit/shared and @copilotkit/runtime. Every one of them assumed telemetry was enabled because the ambient environment happened to have no opt-out set — they were asserting on the environment, not the code. A developer with DO_NOT_TRACK exported would have seen the same failures. - shared telemetry-client + runtime get-runtime-info: clear the opt-out vars per test (and restore), so each case sets the state it asserts on. - The three license→sink integration suites need `vi.hoisted`, not a hook: the telemetry singleton latches `telemetryDisabled` at module-import time, which happens before any beforeEach runs. Verified both with the CI env set and with it unset. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ben Taylor
|
3b9d2c27b5 |
fix(channels-intelligence): surface an unreachable gateway host instead of hanging the connect (#6191)
Closes OSS-623 (split out of OSS-621's acceptance item 3).
## The bug
A managed Channel whose `wsUrl` points at a wrong or unreachable host
sat in `connecting` for the caller's full settle budget and then
rejected with `did not settle in time` — no indication that the *host*
was the problem. A wrong **API** host fails fast with a clean HTTP
error; a wrong **WS** host hung.
Three failure modes collapsed into that one opaque timeout: DNS that
does not resolve, a refused/failed TCP or TLS connect, and a host that
serves HTTP with no Phoenix socket mounted at the endpoint (the prod
split-plane trap — `api.intelligence` and `realtime.intelligence` are
separate hosts).
## Why it hung
Two Phoenix behaviors compound, and the second is why the existing join
timeout did not save us:
1. `Socket` retries a failed **first** connect forever and reports
transport errors as reconnect churn, so nothing distinguishes "still
handshaking" from "this host will never work."
2. The join push's own `timeoutMs` is silently defused.
`Channel.onError` calls `joinPush.reset()` while the channel is joining
(phoenix 1.8.4 `channel.js`), which nulls `refEvent` and `off`s the
reply binding — the armed timeout then fires into a dead event name and
no `"timeout"` recHook ever runs.
Net: the connect await hung *indefinitely*; the 30s in the ticket was
purely `ChannelManager.ready({ timeoutMs })`'s deadline, which is why
the message was a stopwatch.
## The fix
**Watch the initial connect separately from reconnects**, keyed off
whether the socket has ever opened (phoenix passes exactly that as
`socket.onError`'s third argument, `establishedConnections`):
- **Never opened** → reject with a new `RealtimeGatewayUnreachableError`
naming the endpoint and the cause, and tear the socket down so it stops
retrying a host that will not answer.
- **Opened, then dropped** → unchanged; the existing `reconnecting` /
`gave_up` machine owns it.
**Get the cause from HTTP, because the socket does not have it.** This
is the part an adversarial review of the first commit corrected. Node's
global WebSocket (undici — the production default) dispatches the *same*
detail-free `ErrorEvent` for all three modes: `"Received network error
or non-101 status code."`, no OS code, an inner `Error` with nothing
more. Browsers are deliberately worse. So on the failure path only, we
probe the same origin **and path** over http(s) with `fetch`, which does
discriminate — verified against the real network:
| target | WebSocket says | `fetch` says |
|---|---|---|
| nonexistent host | network error or non-101 | `cause.code = ENOTFOUND`
|
| closed port | network error or non-101 | `cause.code = ECONNREFUSED` |
| `https://example.com/runner` | network error or non-101 | **HTTP 404**
|
A transport that *does* expose an OS code (the `ws` package, custom
transports) is trusted directly and skips the probe; a successful
connect issues no request at all.
**Failing fast vs. tolerating a boot race** is split by what the
diagnosis found:
- **The host does not resolve** → fail immediately. Measured against the
real network: **25ms**, message `the host does not resolve (getaddrinfo
ENOTFOUND …)`. This is the OSS-621 case (`realtime.copilotkit.ai` has no
DNS record at all).
- **Anything else** → wait out `connectTimeoutMs` (default **30s**,
plumbed through the launcher). A `ChannelManager` marks an activation
failure `error` **permanently, with no retry**, so a shorter window
would convert a rolling restart of the gateway into a dead Channel where
the old forever-retry would have recovered.
Per acceptance item 4, the error deliberately does **not** carry the
`SETUP_REQUIRED` marker. An unreachable host is a config problem, but
`setup_required` is a benign settled state that lets `ready()` resolve —
a typo'd `wsUrl` must reject loudly, not go quiet-green.
## What the messages look like now
```
realtime gateway unreachable: the socket never connected to wss://oss623-does-not-exist.copilotkit.ai/runner
(the host does not resolve (getaddrinfo ENOTFOUND oss623-does-not-exist.copilotkit.ai))
— check that the Intelligence wsUrl points at the gateway host [25ms]
realtime gateway unreachable: the socket never connected to ws://127.0.0.1:45999/runner
(the host refused the connection (connect ECONNREFUSED 127.0.0.1:45999))
— check that the Intelligence wsUrl points at the gateway host [full window]
realtime gateway unreachable: the socket never connected to wss://example.com/runner
(the host answered HTTP 404 for https://example.com/runner, so it resolves and accepts
connections — only the WebSocket handshake failed, so the wsUrl path may not be the
gateway's socket endpoint) [full window]
```
## Tests
Rebuilt around the shapes the real implementations emit, with the undici
shape as the default case (the first version's fake fed a `ws`-shaped
coded error undici never produces, which is what hid the dead code):
- The host does not resolve → fails in <1s despite a 5s window, probes
host **and path**, names the cause, carries `code ===
"GATEWAY_UNREACHABLE"` and the underlying `cause`, is not
`SETUP_REQUIRED`, socket closed.
- Refused → waits out the window, then names `ECONNREFUSED`.
- Host answers HTTP 404 → reported as a handshake/path problem, not a
missing host.
- A transport that exposes an OS code → fails fast with **no** probe
issued.
- A connect that hangs with no transport event at all → bounded by the
connect window (not a 60s join timeout), and the deadline itself starts
the probe so a cause is still reported.
- Neither transport nor probe yields a cause → still names the endpoint.
- **The shipped probe against a real closed loopback port** — no seam,
no DNS, no egress.
- A gateway that fails once and accepts on retry still connects (the
boot race).
- A healthy connect issues no diagnostic request.
- The connect deadline is disarmed after a successful connect — a later
drop is still a reconnect episode.
Before the fix, four of these hang until vitest's own 5s timeout — the
bug reproduced directly.
## Verification
`check-types` clean; full package suite 195/195; oxlint + oxfmt clean;
lefthook pre-commit (whole package suite + `check:packages`) green. All
three failure modes additionally verified end-to-end against the real
network and the real `fetch`, not just fakes.
## Known adjacent case, not in scope
A socket that opens and *then* drops before the initial join reply hits
the same defused-join-timeout behavior (2 above) and still relies on the
caller's settle deadline. That path can genuinely self-heal via
Phoenix's rejoin, so it keeps the retry; bounding it is a separate call
from OSS-623's "never connected once."
🤖 Generated with [Claude Code](https://claude.com/claude-code)
|
||
|
Benjamin Taylor
|
b2c3c49201 |
chore: drop the changeset
Releases go through the release workflow scopes, not per-PR changesets. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Benjamin Taylor
|
749a8fb2b3 |
refactor(web-inspector): move the telemetry egress guard under src
Importing the factory from vitest.setup.ts tripped TS6059 (file outside rootDir) in the package's typecheck. The helper now lives in src/lib/testing/ — test-only, never referenced by the bundle entry, and confirmed absent from dist. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Benjamin Taylor
|
20369b990c |
fix(web-inspector): bound the pre-handshake telemetry queues
An open/close loop against a runtime that never connects would otherwise queue indefinitely and burst on reconnect. Caps both pending queues at 20 events — this is a signal, not a ledger. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Benjamin Taylor
|
9bf283969c |
ci(telemetry): disable CopilotKit telemetry in automated jobs
OSS-565: no CI workflow disabled telemetry, so every job that runs or boots real CopilotKit code emitted `oss.runtime.*` / `oss.inspector.*` events that are indistinguishable from user activity in PostHog. Because the browser-side events come from a real (headless) Chromium, the `$useragent != node` heuristic can't filter them out after the fact — which is what made the `banner_viewed` reach number untrustworthy. Sets COPILOTKIT_TELEMETRY_DISABLED / DO_NOT_TRACK at the workflow level for the jobs that execute app or runtime code (unit, integration, e2e-dojo, e2e-legacy-v1, smoke-starter, showcase eval / frontend-matrix / on-demand). The runtime reads them at startup and reports `telemetryDisabled` on /info, which is also how the Inspector in a CI-booted app learns to stay quiet. The frozen integration container gets them via explicit `--env` because workflow-level env does not cross the container boundary, and the legacy-v1 Playwright webServer defaults them so local e2e runs are covered too. The inspector's own unit tests can't be reached by an env var at all — its telemetry keys off the /info handshake, not process.env — so they were POSTing real events to the live sink on every run. A setup-file guard now swallows requests to the sink and passes everything else through. Out of scope, deliberately: showcase capture-previews drives Playwright against DEPLOYED Railway apps, so no CI-side env can reach them; silencing those would mean disabling telemetry on the deployed services, which would also drop real visitors. Keep-alive needs nothing — /api/health is a static route with no runtime and no browser. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Benjamin Taylor
|
75882820c6 |
feat(web-inspector): add inspector-opened event and banner surface telemetry
OSS-566: there was no event recording that the Inspector panel was opened.
Opens could only be inferred from in-panel activity (a floor) or from
`banner_clicked` cta=body, which misses the floating-button path entirely.
Adds `oss.inspector.opened` with an `open_source` property, queued behind
the runtime handshake so an open is never reported for a runtime that has
telemetry disabled. Restoring a persisted-open panel deliberately does not
count — otherwise every reload / dev-server hot reload would be an "open".
OSS-568: `banner_viewed` fired once at fetch time and could not say which
of the two announcement surfaces the user actually saw — the bubble on the
collapsed widget or the card inside the opened panel. The event now carries
a `surface` stamped at fire time and dedups per (banner, surface), so
opening the panel records the card impression as its own signal. Dismissal
is also promoted to a first-class `oss.inspector.banner_dismissed` event,
emitted alongside the existing `banner_clicked { cta: "dismiss" }` so
dashboards reading the `cta` value keep working.
Both events pass the sink's `oss.inspector.` prefix gate, so no
telemetry-sink deploy is required.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
Lukas Moschitz
|
c70eff232c |
fix(showcase): fix langgraph-typescript a2ui-recovery (dom-missing / flaky heal)
Two langgraph-typescript-scope causes: 1) Fixture prompt drift: the a2ui-recovery.json userMessage keys + suggestions.ts pills still carried langgraph-python's copied prompt while the shared probe sends a langgraph-typescript-UNIQUE prompt -> aimock 404 -> heal surface never mounts. Retarget the 4 keys + 2 pills to the probe's unique prompt (kept distinct: a2ui-recovery fixtures have no x-aimock-context, so per-slug-unique prompts are load-bearing to avoid cross-framework collisions). 2) Flaky heal (green-then-red): TS @ag-ui/langgraph getA2UITools invokes its inner render_a2ui sub-agent via a config-less model.stream(), so config-based header forwarding never reaches it; the inner aimock call carries no x-test-id, its sequenceIndex falls into the never-reset DEFAULT_TEST_ID bucket, and the seq0->seq1 heal staging only works on the first run. Add wrapModelCall/ wrapToolCall middleware + AsyncLocalStorage + a custom OpenAI fetch that forwards inbound x-* headers onto every outbound call (outer emit AND inner render) — mirroring the mechanism the green TS sibling mastra uses. Not the shared Python recovery-loop defect (mastra, also TS getA2UITools, is green — the TS path is fixable). D6 a2ui-recovery now green + STABLE (6 real ~7.7s runs); aimock fixtures test 844 passed. Divergence documented in PARITY_NOTES.md. |
||
|
David McKay
|
b2f4b47a2d |
docs(banking): refresh the demo README to match what shipped
#6136 changed the demo substantially and left the README describing an older build. Corrections: - It documented CopilotPopup; the chat is a left-docked CopilotSidebar rendering two columns (thread rail + conversation) with the app's nav rail on the right. - It called the learned over-limit memory `procedural`; the code writes `operational`. - It said the Glass Engine Memory tab was "top-k semantic recall, not a full enumeration". It is now a complete enumeration ("Stored memories (N)"), aggregated across the demo's identities, with semantic search as a separate box. - It listed per-run reset as a future follow-up. It ships, gated behind PRESENTER_RESET_ENABLED, and also re-seeds memory and returns to the bare root. - It described showTransactions as a useFrontendTool; it is a useComponent so it persists in the transcript. - The "change my Visa PIN from the team page" example described a navigation fallback; PIN entry is now a component in the chat and the agent never sees the digits. Adds what was missing: the eight-pill demo script, the /charges page, the PDF/Q2 multimodal beat, seeded memory (and why the over-limit procedure is deliberately NOT seeded), the components-not-markdown-tables rule, per-team chart colour, and the two incompatible helper families in actions.ts that make destructuring `ok` report a success as a failure. All three screenshots are replaced — they showed the old right-docked chat, so they contradicted the first paragraph. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Tyler Slaton
|
1d1ca9ea8b |
fix(docs): correct the documented Intelligence endpoints for Channels (#6189)
Fixes the Channels docs/examples pointing at an Intelligence host that does not serve the API, and the websocket URL guidance that can never produce a working prod value. Linear: [OSS-621](https://linear.app/copilotkit/issue/OSS-621). ## The two bugs **1. The documented host does not serve the API.** Probed every plausible path, not just `/`: | URL | Result | | --- | --- | | `api.copilotkit.ai` — `/`, `/api`, `/api/health`, `/health`, `/api/threads`, `/api/v1/threads` | **404 on all**, `server: awselb/2.0`, `content-length: 0` — an ALB with no target-group rule behind it | | `realtime.copilotkit.ai` | **no DNS record at all** | | `api.intelligence.copilotkit.ai/` and `/api/health` | 200, `x-powered-by: Express` | | `api.intelligence.copilotkit.ai/api/threads` | **401** — a real, auth-gated endpoint | | `realtime.intelligence.copilotkit.ai/runner/websocket` | **403** — mounted and auth-gated (a 404 would mean unmounted) | So the documented host is not merely returning 404 at the root — nothing is routed there on any path, and it is not the app (no `x-powered-by`). The working pair, matching the CLI's baked-in prod defaults and `gitops/environments/prod/values.yaml`, is `https://api.intelligence.copilotkit.ai` + `wss://realtime.intelligence.copilotkit.ai`. **2. `wsUrl` was documented as derivable from `apiUrl`.** Prod splits the API and realtime planes across *different hosts*, so a scheme-only swap yields `wss://api.intelligence.copilotkit.ai` — wrong host. That failure is silent: a wrong `apiUrl` returns a clean HTTP error, but a wrong `wsUrl` sits in `connecting` until the settle timeout and reports only "did not settle in time". The derive is not even correct locally, where the API and gateway are on different ports (4201 vs 4401) and the swap preserves the port. It is essentially never right, so it is deleted rather than relabelled. Demonstrated end to end rather than asserted — running `examples/teams` with the WS URL unset: ``` # on main: derive(https://api.intelligence.copilotkit.ai) -> wss://api.intelligence.copilotkit.ai (wrong host, 30s hang) # on this branch: exit code: 1 Missing COPILOTKIT_INTELLIGENCE_WS_URL. export COPILOTKIT_INTELLIGENCE_URL=https://api.intelligence.copilotkit.ai export COPILOTKIT_INTELLIGENCE_WS_URL=wss://realtime.intelligence.copilotkit.ai The API and websocket URLs are DIFFERENT hosts (api.… vs realtime.…), so the websocket URL cannot be derived from the API URL — set both. ``` ## Scope note The ticket listed 8 sites; the actual blast radius was 30 across 22 files. Beyond the ticket's list: - **Five more channels package READMEs** — `channels`, `channels-core`, `channels-discord`, `channels-slack`, `channels-teams` (the ticket named only telegram + whatsapp). - **The live product docs** — `showcase/shell-docs/src/content/docs/channels/` taught the broken derive in 8 files. These escaped the ticket's grep because their host was already a `your-intelligence-url` placeholder; only bug 2 was present. This is the surface developers actually read. - **A generated skills mirror** — `skills/runtime/` is produced from `packages/runtime/skills/runtime/` by `pnpm sync:plugin-skills`; fixing one without the other leaves the bug live and fails the `check-plugin-skills` gate. - `skills/copilotkit-debug/references/runtime-debugging.md` and a third occurrence in `client.ts`. ## Acceptance item 4 — resolved, chain verified The ticket flagged a contradiction: `realtime-gateway.ts` documented `wss://gateway.example/socket` while the runtime skill listed `/socket` as a mistake. **The skill is right**, confirmed by tracing the real runtime path rather than inferring it: 1. `channel-activation-config.ts:145` — `const wsUrl = intelligence.ɵgetRunnerWsUrl()`, i.e. base + `/runner`. 2. → `channel-manager.ts:237` `wsUrl: config.wsUrl` → `startChannelsOverRealtimeGateway` → `connectRealtimeGateway`. 3. `realtime-gateway.ts:253` hands that to Phoenix's `Socket`, which appends `/websocket`. 4. The gateway mounts exactly `/runner` and `/client` (`realtime_gateway/endpoint.ex:10,17`). There is no `/socket`. The two docs survived contradicting each other because they describe **different layers**: the public `wsUrl` is a bare base, while `connectRealtimeGateway` receives the already-derived runner URL. Its doc comment and the test fixtures move to `/runner` and now name the layer. Independently, `get-runtime-info.ts:93` uses `ɵgetClientWsUrl()`, which confirms the `/info` sample in the debug skill correctly keeps its `/client` suffix — only the host there was wrong. ## Acceptance item 3 — split out Failing loudly instead of hanging is a behavior change in the launcher's connect path that overlaps OSS-622's error classification, so it is [OSS-623](https://linear.app/copilotkit/issue/OSS-623) rather than smuggled into a docs fix. ## Verification - 44/44 gateway tests in `packages/channels-intelligence`; `examples/slack/app/managed.test.ts` passes; `examples/teams` typechecks clean. - `nx run-many -t test,publint,attw` across the 15 affected projects passed via the pre-commit hook; full CI green (38 checks, including `build-check (shell-docs)`). - Behavior proven by running the example, not by mocks (above). - 45 commits behind `main` at time of review with **zero overlap** on changed files, and the diff covers every dead-host and derive site present on *current* `main`. - No logic changes in either published package — `client.ts` and `realtime-gateway.ts` are JSDoc/field-comment only. Behavior changes are confined to the three example apps. ## Self-review pass An adversarial pass over this PR tried to falsify its central claim (that `api.copilotkit.ai` does not serve the API) by probing non-root paths — the evidence got stronger, not weaker. It also cleared a suspected regression: three `channels-intelligence` files read `COPILOTKIT_INTELLIGENCE_URL` without the WS var, but they are the HTTP-only transport path and need no socket URL. Two genuine gaps it *did* find are fixed in the last commit: the five platform pages had lost deployment neutrality (managed hosts now carry a self-hosted note), and `index.mdx`/`mcp.mdx` referenced the new variable without telling the reader where it comes from. **One product decision for the reviewer:** `api.copilotkit.ai` is a live ALB that routes nothing. If it is meant to become the public API alias, this PR is documenting the wrong long-term string and the ALB wants a listener rule instead. I used the host the product actually hands users today (CLI prod defaults + gitops). 🤖 Generated with [Claude Code](https://claude.com/claude-code) |
||
|
Lukas Moschitz
|
0476fa6f08 |
fix(showcase): stop langgraph-typescript frontend-tools-async D6 loop (stale turnIndex fixture)
frontend-tools-async was flaky-red (done-signal-missing / text-unstable): the fixture carried a legacy duplicate last fixture (userMessage 'project planning', turnIndex:0, content + a query_notes tool call with NO id) that is absent from the canonical D5 source. On iteration 2 (last msg = the query_notes tool result), aimock's selectByTurnIndex prefers the turnIndex-bearing bare fixture (0<=1) over the toolCallId-keyed follow-up, re-emitting query_notes with a fresh id whose result never matches -> infinite re-emit loop -> turn never completes. Remove the stale bare 'project planning' turnIndex:0 fixture so the toolCallId follow-up is the sole iteration-2 candidate and the turn ends cleanly. D6 frontend-tools-async now green and STABLE (4/4 consecutive real runs); aimock fixtures test 844 passed. (Same stale-fixture defect exists on the langgraph-python north star — flagged for a separate fleet-wide follow-up.) |
||
|
Alem Tuzlak
|
9a501d5e0d |
fix(showcase/built-in-agent): repair six real-LLM defects D6 was masking (#6200)
Six defects reported on staging. All six reproduce; five share one cause. ## The shared cause `built-in-agent/src/app/api/copilotkit/route.ts` maps **~20 demos to the same prompt-less `createBuiltInAgent()`**. The reference wires each to its own graph **and its own system prompt** (28 graphs in `langgraph-python/langgraph.json`). aimock replays a scripted tool-call sequence keyed on `userMessage` + `context`, so D6 is green whether or not the model could have reasoned its way there. This is `showcase/GOTCHAS.md` #8 verbatim — including its stated "structural tell": *grep the integration's `route.ts` for demos left in the generic fallthrough that LGP wires to a dedicated graph.* ## Per-defect | Demo | Symptom | Root cause | |---|---|---| | `gen-ui-tool-based` | charts plot zeros | No prompt. The assistant says so itself: *"I used placeholder values since no sales figures were provided."* Nondeterministic — one run gave a real 0..220 axis, the next `0 1 2 3 4` with no bars, which is how it passed review. | | `gen-ui-agent` | wall of text, steps frozen at "step 1 of 4" | `set_steps` + its `/steps` STATE_DELTA already worked; nothing told the model to *walk* pending→in_progress→completed. | | `subagents` | left panel always empty | `grep -rn delegations src/ \| grep -v demos/subagents` → **no output**. Frontend reads `agent.state.delegations`; the converter handles `/steps` and `/notes` and has no `delegations` case. Chat works because the tools do run. | | `declarative-json-render` | raw JSON for pills 2 & 3 | Intercepted the SSE: **the wire is already one closing brace short** — nothing is dropped in transport, and the client parser correctly requires a balanced object. Pill 1 only works because the model copies the prompt's worked example verbatim (`\$1.24M`, `+18% vs Q2`). Model-level JSON enforcement had been removed with the note *"the system prompt already enforces JSON-only output"* — it does not. | | `a2ui-recovery` | 5 identical cards | Reuses declarative-gen-ui's prompt with no "call once" constraint, while the pills literally ask it to *"self-correct a malformed first attempt"*. The retry loop is **inside** the tool and returns on first valid pass, so every supervisor retry is pure duplication. | | `declarative-gen-ui` | D4 though it works live | **The inverse case.** Badges: `UI ✓ BE ✓ 1P ✗ D6 —` (*"gated — blocked by a lower rung"*). Not a live bug — a fixture bug. See below. | ## The D4 cap (`declarative-gen-ui`, `a2ui-recovery`) Both demos' secondary design-call fixtures gated on `match.responseFormat: \"json_object\"`. That matcher **can never match this backend**: - The agent talks to the OpenAI *Responses* API, where JSON mode is `text.format`. - aimock has **no `text.format` handling at all** — `responsesToCompletionRequest` forwards only a top-level `response_format` (absent in 1.19.1, forwarded in 1.37.4), a key the Responses API doesn't accept and this client doesn't send. - So `effective.response_format?.type` is always `undefined` and `router.ts` skips the fixture → the design call never matched → surface never painted → D5 red, D6 never ran. Re-keyed onto `match.toolName`, which aimock *does* normalize out of a Responses request (`responsesToolsToCompletionsTools`): the outer call declares `generate_a2ui`, the in-tool design call declares nothing. Tool-less secondary fixtures moved last, because several pills' brief is a substring of the pill text (`\"Build my Q2 revenue summary …\"` contains `\"Q2 revenue summary\"`) and would otherwise win the outer request. ## Verification **Reproduced live** (staging, real LLM): the zero-axis chart plus its self-incriminating message, the unbalanced JSON on the wire, and the reference rendering the *same pill* correctly for contrast. **Two mutation-verified test suites** — both fail with the fix reverted: - `aimock-a2ui-routing.test.ts` drives aimock's **real `matchFixture`**. On the old fixtures 14/16 cases fail with `no fixture matched the secondary design call for brief \"…\"` — the D5 red, reproduced as a unit test. - `tanstack-factory.test.ts` covers the `/delegations` and `/steps` deltas (3 delegation tests fail with the branch disabled; the 2 controls still pass). **No regressions:** `tsc --noEmit` is 61 errors before *and* after (all pre-existing — `gpt-5.4` missing from the adapter's model union, zod v3/v4 skew); oxlint clean on changed files; the repo-wide fixture validator passes (858 assertions). `text.format` was verified by reading the request mapping in the **pinned** `@tanstack/ai-openai@0.15.6` → `@tanstack/openai-base@0.9.2`: `modelOptions` is spread straight into `responses.create()`, `validateTextProviderOptions` only inspects `metadata`/`conversation`/`previous_response_id`, and the adapter sets `text.format` itself only when an `outputSchema` is passed (none here, so nothing is clobbered). ## What is NOT verified **The four prompt/`text.format` changes have not had a real-LLM click-through** — that needs an OpenAI key this environment doesn't have, and D6/aimock cannot verify them by construction (that's the whole point of gotcha #8). Reasoning is documented inline at each site. This area has burned the repo before: a previous `response_format` attempt made the call return an empty string "verified against real OpenAI", which is why `text.format` — the Responses API's own param — is used instead. **Worth a live click-through on the staging deploy before this is considered closed.** ## Deliberate non-goals - **`a2ui-recovery` only demonstrates recovery under aimock.** The heal/exhaust branches need a designer LLM that emits invalid surfaces on demand; a real one succeeds on attempt 1. The single-call constraint fixes the 5-card bug and makes it honest; making recovery visible live needs deliberate fault injection — a product decision, recorded in `PARITY_NOTES.md`. - **The reference pins `openai:gpt-4o-mini`** (`gen_ui_agent.py:92`). Flagged, not touched. ## Docs `GOTCHAS.md` gains built-in-agent as a second worked instance of #8 (including that the masking runs *both* ways, and that `1P ✗ D6 —` means gated, not failing), plus the `text.format` and dead-`responseFormat` traps. `PARITY_NOTES.md` records that the named-agent registry is **not** prompt-neutral, and that any new `state.<slot>` needs a converter branch. |
||
|
Lukas Moschitz
|
557f6f7318 |
fix(showcase): fix langgraph-typescript tool-rendering (get_weather card missing)
tool-rendering red (expected weather-card, 0 elements): the 'weather in Tokyo' fixture returns assistant content + a get_weather tool call together; langchain-js streamed-chunk reassembly left the tool call only under additional_kwargs.tool_calls (surfacing intermediate chunks as invalid_tool_calls) and produced a bare 'generic' message, so top-level tool_calls stayed empty. shouldContinue then routed to __end__, the tool never ran, no TOOL_CALL_* events, no weather card. LGP's Python create_agent parses the identical fixture correctly. Add normalizeAssistantMessage() in tool-rendering.ts (called in chatNode): when the response isn't a well-formed AIMessage with populated top-level tool_calls, reconstruct a clean AIMessage, promoting additional_kwargs.tool_calls into parsed tool_calls (no-op passthrough when already correct). Restores TS<->Python parity. D6 tool-rendering now green (two real ~5s runs); fixture + frontend untouched (byte-identical to LGP). Only the backend agent changed. |
||
|
Alem Tuzlak
|
1d5cdb35cf |
fix(showcase/built-in-agent): repair six real-LLM defects D6 was masking
Every affected cell was D6-green (or D4-gated) while the deployed demo was visibly broken. The common cause is GOTCHAS #8: aimock replays a scripted tool-call sequence keyed on userMessage + context, so the fixture answers a question the model was never asked. Prompt gaps — ~20 demos shared one prompt-less `createBuiltInAgent()` where the reference wires each to its own graph AND its own system prompt. Adds `createBuiltInAgent({ systemPrompt })` + `demo-prompts.ts`, ported from the reference graphs: - gen-ui-tool-based plotted zeros; the assistant said "I used placeholder values since no sales figures were provided". Nondeterministic — some runs invented real values, which is how it passed review. - gen-ui-agent published its plan once then narrated, freezing the progress card on step 1 of 4. - a2ui-recovery painted five identical cards: nothing constrained the supervisor to one `generate_a2ui` call, and the pills literally ask it to "self-correct". The retry loop lives inside the tool, so supervisor retries are duplication. subagents' delegation panel was permanently empty — the frontend reads `agent.state.delegations` and no code emitted that slot. The converter now emits a `/delegations` delta per sub-agent result (whole-array `add`, since initial state is `{}` and strict fast-json-patch rejects unresolvable paths while @ag-ui/client swallows the throw), and ports the reference's `_MAX_CRITIQUE_ITERATIONS = 1` cap. declarative-json-render dumped raw JSON for any prompt the model couldn't crib from the worked example. Captured the SSE: the wire is already one closing brace short, so nothing is dropped in transport — model-level enforcement had been removed on the grounds that "the system prompt already enforces JSON-only output". It does not. Restores it via the Responses API's `text.format`, the param the removed `response_format` maps to, verified against the pinned @tanstack/ai-openai@0.15.6 -> @tanstack/openai-base@0.9.2 request mapping. declarative-gen-ui and a2ui-recovery were the inverse: capped at D4 (UI ✓ BE ✓ 1P ✗ D6 gated) while working live. Their secondary design-call fixtures gated on `match.responseFormat`, which aimock can never satisfy here — it has no `text.format` handling and only forwards a top-level `response_format` the Responses API doesn't accept. Re-keyed onto `match.toolName` (the outer call declares `generate_a2ui`, the in-tool design call declares nothing) with the tool-less fixtures moved last, since several pills' brief is a substring of the pill text. Tests (both mutation-verified — they fail with the fix reverted): - aimock-a2ui-routing.test.ts drives aimock's real `matchFixture`; 14/16 cases fail on the old fixtures with "no fixture matched the secondary design call". - tanstack-factory.test.ts covers the `/delegations` and `/steps` deltas. Typecheck unchanged at 61 pre-existing errors; oxlint clean on changed files. NOT verified live: the four prompt/`text.format` changes need a real-LLM click-through, which needs a key this environment doesn't have. Reasoning and the exact request mapping are documented inline. |
||
|
Lukas Moschitz
|
629a70d918 |
fix(showcase): fix langgraph-typescript reasoning-display (text-unstable)
reasoning-display red with text-unstable: @langchain/openai@1.4.4's streaming Responses converter pushes the reasoning-summary delta and the answer output_text delta to the same content-block index (both 0), so the streaming reducer collapses them into one reasoning block that swallows the answer. @ag-ui/langgraph then routes the whole turn to REASONING_MESSAGE_* events and no assistant TEXT_MESSAGE renders — the probe never settles. Set disableStreaming:true in reasoning-agent.ts to force the non-streaming Responses converter (processes final output items, yields separate reasoning + text blocks), so reasoning and answer both render, matching langgraph-python's content. Document the one behavioral divergence in PARITY_NOTES.md: the summary no longer token-streams (arrives at once) until the upstream langchain-openai index-collision bug is fixed. D6 reasoning-display now green (real runs, reasoning-custom + reasoning-default); fixture untouched (LGP-identical shape). Only the backend agent changed. |
||
|
Lukas Moschitz
|
9c9cba1dbe |
fix(showcase): stop langgraph-typescript open-gen-ui D6 loop (turnIndex shadowing)
gen-ui-open and gen-ui-open-advanced looped (done-signal-missing): the 7 leg-1 tool-call fixtures for the open pills carried turnIndex:0, which aimock treats as turnIndex-relaxed (default AIMOCK_STRICT_TURN_INDEX off) and keeps as a candidate on the follow-up turn, out-selecting the toolCallId terminal so the done signal never fires. Change those 7 leg-1 fixtures from turnIndex:0 -> hasToolResult:false (the request-shape predicate that excludes them once the tool result is present), mirroring langgraph-python's canonical gen-ui-open.json shape. The 4 single-turn narration fixtures keep turnIndex:0. D6 gen-ui-open + gen-ui-open-advanced now green (two real ~11s/~13s runs each); no aimock no-match/relaxed. |
||
|
Alem Tuzlak
|
7e3d06f0d0 | Merge branch 'main' into ci/showcase-latest-tag-race | ||
|
Alem Tuzlak
|
ffcab5fb64 |
fix(showcase/ms-agent-dotnet): copy manifest.yaml into the runtime image (#6197)
## Symptom Every `ms-agent-dotnet` cell on staging dropped to **D3** after #6130 merged: | Rung | Error | |---|---| | D6 Parity (Reference) | `chat input not found: waitForSelector locator('[role="textbox"]') to be visible` | | D5 1P (Single Pill) | `timeout after 600000ms` | | D4 BE (Agent) | `page.type: Timeout 59981ms exceeded waiting for locator('textarea')` | ## Root cause Not a chat/agent bug — **every `/demos/*` page is a 500 error boundary**, so no chat input ever mounts. Verified live: ``` $ GET https://showcase-ms-agent-dotnet-staging.up.railway.app/demos/agentic-chat Application error: a client-side exception has occurred [showcase] Uncaught error: An error occurred in the Server Components render. ``` `/` still returns 200 (statically prerendered) — which is why the service line stays green and the cells look merely "stuck at D3". #6130 added `src/middleware.ts`, which sets the `x-pathname` header. That header is the thing that makes `src/app/demos/layout.tsx`'s `generateMetadata()` get past its `if (!slug) return` early-out and actually call `loadDemoIndex()` — a request-time `readFileSync(process.cwd()/manifest.yaml)`. The Dockerfile's runner stage never copied `manifest.yaml` → ENOENT on every demo route. Before the middleware existed the header was always absent, so the manifest read never ran. The middleware didn't break the layout; it *activated* a path that had never executed in production. `langgraph-python` hit this exact bug and fixed it with the same one-line `COPY` (its Dockerfile carries a comment describing this failure verbatim). A sweep confirms `ms-agent-dotnet` was the only integration shipping `middleware.ts` without it: ``` langgraph-fastapi middleware=yes copy=yes langgraph-python middleware=yes copy=yes ms-agent-dotnet middleware=yes copy=no <-- broken (all others) middleware=no <-- header absent, read never runs ``` ## Fix 1. `COPY --chown=app:app manifest.yaml ./` in the runner stage, with the same explanatory comment as the reference. 2. `showcase/scripts/__tests__/runtime-manifest-copy.test.ts` — ratchets the invariant: any integration shipping `middleware.ts` whose demos layout reads `manifest.yaml` must copy it into the image. ## Verification - Confirmed the live 500 on `/demos/agentic-chat` and confirmed `langgraph-python` staging renders the manifest-driven title (`LangGraph (Python) - Pre-Built: CopilotChat`) on the same route — isolating the missing COPY as the only difference. - Ratchet test mutation-verified: passes with the fix, fails when the `COPY` line is removed. - Not container-built locally (the .NET SDK stage is expensive and the change mirrors a proven line); the deployed staging image is the real check. ## Note, separate from this PR D3 rendered **green** while every demo page was a 500. Whatever D3 probes, it does not detect an error-boundary page — that is red-masking worth a follow-up. |
||
|
Benjamin Taylor
|
e0c7500d6b |
fix(channels-intelligence): diagnose an unreachable gateway over HTTP, not from the socket
Adversarial review of the previous commit against the real transport found the cause-carrying half of it was dead code. Node's global WebSocket (undici) — the production default — dispatches the SAME detail-free ErrorEvent for a host that does not resolve, a refused port, and a host answering HTTP with no socket mounted: "Received network error or non-101 status code.", no OS code, an inner Error with nothing more. So the non-retryable code set never matched (measured: NXDOMAIN burned the full 8s window instead of failing fast) and the reported transport error was the same useless string for every cause. The tests passed only because their fake fed a ws-package-shaped error undici never produces. Get the cause from a source that has it: on the failure path only, probe the same origin AND path over http(s) with fetch, which does distinguish the modes (verified against the real network: ENOTFOUND / ECONNREFUSED / HTTP 404). A transport that DOES expose an OS code is still trusted directly and skips the probe; a successful connect issues no request at all. NXDOMAIN now fails in ~25ms rather than after the whole window, and the HTTP-answered case reports that the host is up and only the handshake failed — the prod split-plane trap. Also raise the default connect window 10s -> 30s. Because a supervising ChannelManager marks an activation failure `error` permanently with no retry, the old default could convert a rolling restart of the gateway into a permanently dead Channel, where the previous forever-retry would have recovered. Tests are rebuilt around the shapes the real implementations emit, including one that exercises the SHIPPED probe against a closed loopback port (no DNS, no egress), one asserting a healthy connect probes nothing, and coverage for the GATEWAY_UNREACHABLE code and preserved cause. Refs OSS-623 |
||
|
Alem Tuzlak
|
734294155a |
fix(showcase/ms-agent-dotnet): copy manifest.yaml into the runtime image
PR #6130 added `src/middleware.ts`, which sets the `x-pathname` header that `src/app/demos/layout.tsx`'s `generateMetadata()` reads. That header is what makes the layout actually call `loadDemoIndex()` — a request-time `readFileSync(process.cwd()/manifest.yaml)`. The Dockerfile's runner stage never copied `manifest.yaml`, so every `/demos/*` route now 500s with "An error occurred in the Server Components render" (ENOENT), while the statically-prerendered home page keeps returning 200. On the dashboard that reads as "service is up, every cell pinned at D3": D4 fails on `page.type` waiting for `textarea`, D5 times out, D6 fails on `waitForSelector('[role="textbox"]')` — the chat input never mounts because the page is an error boundary. langgraph-python hit this exact bug and fixed it with the same one-line COPY; ms-agent-dotnet is the only integration shipping `middleware.ts` without it. Adds a ratchet test over that invariant (mutation-verified: fails with the COPY removed). |
||
|
Benjamin Taylor
|
ad67e9f4d6 |
docs(channels): keep the Channels pages deployment-neutral and self-sourcing
Two gaps from the previous commit, found reviewing it. The five platform pages previously carried a `your-intelligence-url` placeholder, which was neutral about where Intelligence runs. Replacing it with the managed hosts read as "this is the endpoint" to a self-hosted reader, and only the quickstart said otherwise; every env block now notes that self-hosted deployments substitute their own two hosts. index.mdx and mcp.mdx are code-only pages with no env block, so after requiring a second variable they referenced COPILOTKIT_INTELLIGENCE_WS_URL without ever telling the reader where it comes from. Both now point at the dashboard and the quickstart's env block. Refs OSS-621 |
||
|
Benjamin Taylor
|
c03cb1e215 |
chore(channels-intelligence): drop the changeset
Changesets are no longer part of the release flow for this repo. |
||
|
Lukas Moschitz
|
f6c768344c |
fix(showcase): register gen_ui_tool_based in langgraph-typescript server.mjs
The langgraph-typescript agent runs a custom server.mjs whose hardcoded
graphSpec — NOT langgraph.json — is the runtime graph registry. gen_ui_tool_based
was missing from it, so the langgraph server returned 404 for that graph and the
Tool-Based Generative UI cell fell through. Add gen_ui_tool_based and drop the
three redundant graph ids (reasoning-default-render, tool-rendering-{default,
custom}-catchall) that route.ts now consolidates onto shared graphs, keeping
server.mjs in sync with langgraph.json.
|
||
|
github-actions[bot]
|
cc06f4430d | style: auto-fix formatting | ||
|
Lukas Moschitz
|
267f98ddda |
fix(showcase): align langgraph-typescript to langgraph-python north star
Bring the langgraph-typescript Showcase integration to parity with the reference langgraph-python: byte-identical demo frontends, the same demo set and manifest overview, framework-native TypeScript backend wiring, and canonical mirrored aimock D6 fixtures. Scope is limited to integrations/langgraph-typescript and its aimock/d6 fixtures. Frontend: realign ~25 drifted demo files to the north star; add missing src/components/ui primitives, READMEs, declarative-gen-ui/sales-context, and the threadid-frontend-tool-roundtrip page; remove LGT-only drift; replace the hand-rolled landing page with the manifest-driven one. Only the sanctioned "LangGraph (TypeScript)" identity strings differ. Manifest: rebuild to match langgraph-python's feature order, demo order, names, tags, descriptions, and routes; drop two bogus NSF entries that were never real features (reasoning-default-render, agentic-chat-reasoning); restore shared-state-streaming and tool-rendering-reasoning-chain as supported cells. not_supported_features now matches the north star (gen-ui-interrupt / interrupt-headless — a shared upstream react-core resume-path limitation). Backend: add the dedicated gen-ui-tool-based data-viz graph; consolidate the tool-rendering variants and reasoning cells onto their shared graphs (matching langgraph-python) and drop redundant duplicate graph ids; register threadid-frontend-tool-roundtrip; move the MCP Apps runtime to the [[...slug]] catch-all route. Fixtures: re-mirror all 43 aimock/d6 fixtures from the canonical langgraph-python set with match.context re-keyed, replacing previously drifted per-integration fixtures. |
||
|
Alem Tuzlak
|
809bb72e72 |
feat(showcase): bring ms-agent-dotnet to D6 (frontend parity + shared-state-streaming, a2ui-recovery, threadid) (#6130)
## What
Brings the **ms-agent-dotnet** (Microsoft Agent Framework .NET) showcase
integration from D5 to **D6**, using **langgraph-python** as the
north-star reference.
### 1. Frontend parity with langgraph-python
Restores near-identical frontends where ms-agent-dotnet had drifted,
while **preserving the load-bearing .NET adaptations** (per the showcase
iron rules — differences belong in fixtures/minimal backend, not the
shared frontend):
- Root shell: `globals.css` (Tailwind `@theme` block + brand green),
manifest-driven index `page.tsx`, `layout.tsx`, new `middleware.ts`
(`x-pathname`), `tsconfig` include.
- `declarative-gen-ui` subtree restored (fixes divergent pill testids
the shared probe asserts).
- Doc-snippet `@region` markers, import-style normalization, `subagents`
revert, stale-file cleanup, `auth` inspector flag.
- **Kept** (load-bearing, not reverted): `parse-json-result` 3-layer
unwrap, multimodal legacy-shim, tool-based `hitl` (MAF has no
`interrupt()`), `agent-config` `properties=`.
### 2. shared-state-streaming → per-token (removed from
`not_supported_features`)
`write_document`'s `document` arg now streams into `state.document`
per-token via a `createSharedStateStreamingAgent` route shim (mirrors
the proven `createGenUiAgent` bridge, with a partial-JSON string
decoder), since the .NET AG-UI host has no `predict_state_config`.
### 3. a2ui-recovery cell (new)
First MS-Agent-Framework implementation of the A2UI
validate→retry→`a2ui_recovery_exhausted` recovery loop. Because the MAF
AG-UI adapter can't emit the custom `ACTIVITY_SNAPSHOT{status:"failed"}`
the exhausted card needs, it's a **raw-SSE `MapPost` endpoint**
(`RecoveryAgent.cs`) — the same adapter-bypass pattern already shipped
for `/multimodal`. Adds the demo frontend, API route, deterministic
aimock fixture (heal seq0-invalid→seq1-valid; exhaust always-invalid),
and a unique per-slug `PROMPTS` entry in the shared probe.
### 4. threadid-frontend-tool-roundtrip demo (parity)
Added for demo-set parity (reuses the `frontend_tools` passthrough; not
a D6-scored feature, mirroring the reference).
`gen-ui-interrupt` / `interrupt-headless` remain honestly quarantined
(upstream `@copilotkit/react-core` `useInterrupt` resume-path bug — not
a backend gap).
## Verification
- Code was authored in parallel worktree-isolated slots, each
cross-verified against the reference + the shared probe contracts; the
a2ui-recovery fixture was cross-checked against
`RecoveryAgent.ValidateComponents`.
- Local D6 harness: the image builds and the stack + probes run, but
**full local green was blocked by Windows-only harness friction**
(`core.symlinks=false` breaks `stage_shared`'s `[ -L ]` materialization;
`--direct` doesn't context-scope the `x-aimock-context` header so
context-keyed a2ui fixtures miss). These are environmental, not code
issues. **Relying on CI's Linux harness (real symlinks + fleet worker)
for authoritative D6.**
## Follow-up (not in this PR)
- `stage_shared()` should also materialize Windows symlink-as-file
entries (detect a regular file whose content is a relative path), so
forced local rebuilds work on `core.symlinks=false` checkouts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
|
||
|
lukasmoschitz
|
eca1d741c8 |
fix(showcase): align langgraph-fastapi to north-star langgraph-python (OSS-582) (#6184)
## Summary
Aligns the **langgraph-fastapi** showcase integration to the north-star
**langgraph-python** (OSS-582 — "Align LangGraph (FastAPI) Showcase
demos and code"). Moves the integration onto the product-centric demo
set: backend agent graphs, runtime wiring, frontend chrome, the
demo-browser overview (`manifest.yaml`), and aimock fixtures.
Linear: OSS-582.
## What changed
**Backend agents (`src/agents/src/`)**
- Ported the missing dedicated graphs: `agentic_chat`, `gen_ui_agent`,
`gen_ui_tool_based`, `shared_state_streaming`.
- v2 `create_agent` ports + config alignment for `agent_config_agent`,
`headless_complete`, `reasoning_agent`, `tool_rendering_agent`,
`tool_rendering_reasoning_chain_agent`, `a2ui_dynamic`.
**Runtime wiring**
- `route.ts`: wired the canonical demos to their dedicated graphs and
removed them from the generic `sample_agent` fallthrough loop (this is
what made several demos behave correctly against a real LLM — see
below); added `recursion_limit`.
- `langgraph.json`: registered the 3 new graphs.
- Renamed the dedicated API routes
`copilotkit-byoc-{hashbrown,json-render}` →
`copilotkit-declarative-{hashbrown,json-render}`.
**Overview / content**
- `manifest.yaml`: demos + features aligned to LGP (names, descriptions,
tags, order, canonical ids; deprecated aliases migrated; phantom
`hitl-in-chat-booking` removed; `shared-state-streaming` un-quarantined
now that it works). Integration identity (name/slug/logo) preserved. The
demo-browser overview is now card-for-card identical to
langgraph-python.
- Restored two missing `@region` markers (factory-automation snippet
extraction).
**Frontend chrome**
- `globals.css`, `layout.tsx`, `middleware.ts` (was missing),
`declarative-gen-ui/*` + `sales-context.ts`, `beautiful-chat`;
`Dockerfile` now copies `manifest.yaml` (fixed an RSC crash on every
`/demos/*`).
**aimock fixtures (`aimock/d4|d6/langgraph-fastapi/`)**
- D6 fixture fixes for the previously-red cells (stale `turnIndex`
gates, cross-file substring shadowing, missing `chunkSize`, prompt
narrowing).
**Showcase tooling / docs**
- Fixed harness services racing on a shared image tag
(`docker-compose.local.yml`).
- `GOTCHAS.md` #8: documents that aimock D6 can be green while a demo is
broken against a real LLM (fixtures replay scripted tool calls
regardless of which graph ran), plus how to catch it.
- `PARITY_NOTES.md`: sanctioned divergences (a2ui-recovery per-slug
prompt isolation; declarative-json-render scoped-test divergence).
## Verification
- **D6 sweep: 38 green / 1 red.** The single red is **a2ui-recovery**,
which reproduces **identically on the north star** (shared Python
`ag_ui_langgraph` recovery loop; mastra's TS impl is green). It is not a
fastapi defect and is tracked as a separate PR against the north star.
Documented in `PARITY_NOTES.md`.
- `validate-manifests` (manifest → registry, all 20 integrations) —
green.
- `validate-routes --all` (runtime-route wiring) — green.
- Build + TypeScript typecheck (`next build` via the Docker image build)
— green.
- `@region` audit — all region pairs balanced and LGP-consistent (0
orphans/typos/mismatches).
- Live manual QA against real OpenAI (`:3102` vs `:3100`) confirmed the
key demos (reasoning-custom, shared-state-streaming, gen-ui-tool-based,
agentic-chat).
## Notable finding
Several demos were D6-green but broke against a real model because they
fell back to the generic `sample_agent` instead of their dedicated graph
— the aimock fixture masked the wiring bug by replaying scripted tool
calls. This PR fixes the wiring and documents the gap (GOTCHAS #8).
D6-green is necessary but not sufficient for graph/tool-dependent demos;
a real-LLM click-through is required.
## Deferred / follow-ups
- **a2ui-recovery** — shared north-star defect in the Python
`ag_ui_langgraph` recovery loop; separate PR against the north star.
- **d5-byoc probe** — always sends the hashbrown pill even on the
json-render page (fleet-wide harness limitation); tracked as a
follow-up. The gating `byoc` grid cell is green.
## Scope note
Only `langgraph-fastapi` integration code, its aimock fixtures, and
showcase tooling/docs changed. **langgraph-python (the north star) was
not touched.**
|
||
|
renovate[bot]
|
2732476db3 |
chore(deps): update docker/login-action action to v4.5.2 (#6194)
This PR contains the following updates: | Package | Type | Update | Change | |---|---|---|---| | [docker/login-action](https://redirect.github.com/docker/login-action) | action | patch | `v4.5.1` → `v4.5.2` | --- ### Release Notes <details> <summary>docker/login-action (docker/login-action)</summary> ### [`v4.5.2`](https://redirect.github.com/docker/login-action/compare/v4.5.1...v4.5.2) [Compare Source](https://redirect.github.com/docker/login-action/compare/v4.5.1...v4.5.2) </details> --- ### Configuration 📅 **Schedule**: (in timezone America/Los_Angeles) - Branch creation - "before 9am every weekday" - Automerge - At any time (no schedule defined) 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR is behind base branch, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR was generated by [Mend Renovate](https://mend.io/renovate/). View the [repository job log](https://developer.mend.io/github/CopilotKit/CopilotKit). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4yODAuMCIsInVwZGF0ZWRJblZlciI6IjQzLjI4MC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119--> |
||
|
renovate[bot]
|
a36772ffe5 | chore(deps): update docker/login-action action to v4.5.2 | ||
|
Ran Shemtov
|
b51cfc2725 |
fix(showcase): PNI-100 relaxed-turnIndex re-emit — hitl-in-app + frontend-tools-async (#6183)
## What Under aimock's **default (relaxed) turn-index selection**, a fixture whose emit leg is keyed on `turnIndex:0` gets re-served on the **post-tool-result turn** — `selectByTurnIndex` treats a behind-the-count scripted turn (`turnIndex < assistantCount`) as a stronger signal than an unpositioned narration fixture. So returning a frontend-tool result re-fires the tool instead of narrating the outcome, and the turn never settles. This is a **test-infra (fixture-selection) bug, not a bridge/runtime bug**: `@ag-ui/mastra` loops back correctly on real OpenAI and under strict aimock. ## Fixtures fixed **hitl-in-app** (`request_user_approval`) — re-key the 3 pill emit legs from `turnIndex:0` to `hasToolResult:false`. Matches the emit turn; excluded on the post-approval turn (where the `toolCallId` narration wins). **frontend-tools-async** (`query_notes`) — add `hasToolResult:false` to the 4 emit legs (3 pills + the `project planning` catch-all). The `toolCallId` narration legs round-trip fine (verified on the wire: emit id `call_d5_query_notes_*` matches the tool-result id on turn 2) and are unchanged. `query_notes` ids exist only in this file — no duplicate/shadow. `subagents.json` reviewed and left as-is — its `turnIndex:1/2` legs are intentional server-side step sequencing, not the client-re-POST pattern. ## Why safe - `hasToolResult` is **per-turn** in current aimock (`currentTurnHasToolResult` scans messages after the last user index), so the guard is multi-pill-safe: each pill click is a fresh user turn. (577 `hasToolResult:true` legs across 258 fixture files already depend on this and are green on `ghcr:latest`, confirming the deployed aimock is per-turn.) - No `turnIndex` dependence on the emit decision → correct under both strict and relaxed aimock. - `--validate-on-load` passes for both files. ## Validation (relaxed / default aimock — the failing mode) Live-verified in-browser against a local mastra run on aimock: - **hitl-in-app**: refund approve → narration; multi-pill (approve refund → escalate) → each pill gets its own dialog and settles. - **frontend-tools-async**: project-planning pill → single result card + narration (was: double card + `toLowerCase` error). ## NOT in this PR (separate follow-up) **open-gen-ui / open-gen-ui-advanced** also break under relaxed aimock, but the cause is different and messier: their real fixtures live in `gen-ui-open.json` / `gen-ui-open-advanced.json` (already `hasToolResult`-gated, no `turnIndex` → no PNI-100 bug). A **stale duplicate** set of `generateSandboxedUi` entries in `gen-ui-tool-based.json` (orphan `call_d5_*` ids, superseded by the real `call_d6_mastra_ogui_*` fixtures) overlaps those pills' userMessages and re-serves on turn 2, poisoning the real flow. Additionally `gen-ui-open.json` has no per-pill turn-2 narration. Fixing that cleanly = remove the stale duplicates + add narration legs to the real files; tracked separately, not bundled here. ## Follow-ups - Durable fleet fix is aimock-side: relaxed selection should prefer a more-specific match over a `turnIndex`-only fixture. - gen-ui stale-duplicate cleanup (above). Linear: PNI-100 |
||
|
Ran Shemtov
|
0f52c5260e | Merge branch 'main' into claude/youthful-williams-bf7746 | ||
|
Tyler Slaton
|
6c15645b6b | docs: organize Channels guides by provider and framework | ||
|
Sam Julien
|
417eb746d2 |
docs(react-native): expand into a production guide (#6144)
## What
Expands the React Native docs page from a "get to first chat" quickstart
into a full production guide, matching the depth of the Slack/Teams
frontend pages. The existing quickstart Steps are unchanged; the new
material is added after them.
### Production sections added
- **Headless imports** — `@copilotkit/react-native/headless` for a
custom-UI app, avoiding the chat/attachment native peer deps the default
barrel re-exports.
- **Metro configuration for release bundles** —
`unstable_enablePackageExports` + browser-first
`unstable_conditionNames` so the transitive `jose` dependency resolves
to its browser build (fails only at release-bundle time otherwise).
- **Polyfills** — documents the real auto-installed barrel + granular
subpaths, including the `crypto` polyfill (backed by `Math.random`) and
the recommendation to install a secure RNG for production.
- **Provider options** — the full `CopilotKitProvider` prop surface:
`runtimeUrl`, `headers` (auth), `credentials`, `properties`, `onError`,
`debug`, `defaultThrottleMs`, `useSingleEndpoint`.
- **Runtime and model wiring** — the string model form,
`OPENAI_BASE_URL` (and Anthropic/Google equivalents) for
OpenAI-compatible endpoints, `createCopilotNodeListener` zero-dep
serving, and `BuiltInAgent` options.
- **Connecting from a device or bench** — LAN IP, Android emulator
`10.0.2.2`, `adb reverse` for USB, and Android release cleartext HTTP
via `expo-build-properties`.
- **Frontend tools and generative UI** — `useFrontendTool` with
zod/Standard Schema, the send-a-turn recipe, `useAgent` read-only
subscribe + `threadId`, discriminated-union params, and variable-length
`ScrollView` rendering.
- **Run lifecycle and UI** — `isRunning` outliving the visible compose,
and gating overlays/reveal motion accordingly.
- **Voice and speech-to-text** — DIY STT with a graceful-fallback
warning for de-Googled/automotive hardware.
- Refreshed **What's included** and **Known limitations**, plus a **Next
steps** section.
### Dependency on runtime / react-native fixes
Three of the four fixes this guide relies on are now **merged to
`main`**, so it documents them as current behavior:
- `@copilotkit/react-native/headless` subpath (headless provider + hooks
without chat/attachment deps) — #6142 ✅ merged
- `resolveModel` honoring `OPENAI_BASE_URL` / `ANTHROPIC_BASE_URL` /
`GOOGLE_GENERATIVE_AI_BASE_URL` for the string model form — #6140 ✅
merged
- union / `anyOf` / `oneOf` tool-param schemas surviving JSON-schema→zod
conversion — #6143 ✅ merged
The fourth — `useAgent` accepting an optional `threadId` (#6141) — is
**still open**. The guide therefore does **not** document it as working;
it is listed under **Known limitations** instead, and will be promoted
once #6141 lands.
Every API, export, env var, and behavior in the page was independently
re-verified against the package source (three parallel source audits
over `packages/{react-native,react-core,runtime}`). That pass turned up
one overstatement, fixed in
|
||
|
tylerslaton
|
17564afd2b | chore: release monorepo v1.64.0 | ||
|
David McKay
|
9ebada7cd8 |
fix(runtime): emit activity snapshot before any delta in open generative UI middleware (#5392)
## Summary Fixes the silent failure where `generateSandboxedUi` (Open Generative UI) intermittently renders an empty gray box — the agent says "Done — I built the calculator…" but no sandboxed UI appears. Reported from a live demo against https://langgraph-py.examples.copilotkit.ai/ (Linear: CPK-7634). ## Root cause `ArgsParser` in `open-generative-ui-middleware.ts` only emitted the activity-creating `ACTIVITY_SNAPSHOT` when it parsed the **`initialHeight`** param. The LLM controls the key order of the streamed tool-call JSON, so whenever `initialHeight` was not the first key (or was omitted), every `css`/`html`/`jsFunctions` `ACTIVITY_DELTA` was emitted **before the activity message existed**. `@ag-ui/client` silently drops `ACTIVITY_DELTA` events whose `messageId` has no prior snapshot, so all UI content was lost; the late snapshot then created an activity containing only `{initialHeight, generating}`. Captured from production (failing run, event order on the wire): `ACTIVITY_DELTA /css → /cssComplete → /html (127 chunks) → /htmlComplete → /jsFunctions → … → ACTIVITY_SNAPSHOT {initialHeight: 760} → … → /generating: false` Result: 760px empty gray box, zero console errors, all requests 200. Whether a given click works is pure LLM key-order roulette — which is why the demo failed twice in a row and then worked. ## Fix - Emit the snapshot lazily before the **first** delta of any kind (guarded, still emitted exactly once). - When `initialHeight` parses after the snapshot has gone out, deliver it as a `/initialHeight` delta instead. - Happy path (`initialHeight` first) is byte-identical to current behavior; all 18 existing tests pass unchanged. ## Tests 3 new regression tests, including one that replays the exact production failure ordering (`css → html → jsFunctions → initialHeight → jsExpressions → placeholderMessages`) and asserts the reconstructed activity content is complete. Red before the fix, green after. Full `@copilotkit/runtime` suite: 1528 tests pass. ## Follow-ups (out of scope) - `@ag-ui/client` drops `ACTIVITY_DELTA` for unknown `messageId` silently — a `console.warn` there would have surfaced this immediately. Worth an upstream issue. - Pre-existing `check-types` failures/OOM in `packages/runtime` (398 errors in unrelated test files on main) — unrelated to this change. 🤖 Generated with [Claude Code](https://claude.com/claude-code) |
||
|
David McKay
|
2864973051 |
Banking demo: ChatGPT-style shell, gen-UI beats, and durable-memory self-learning (#6136)
Upgrades the Northwind Finance banking demo
(`examples/showcases/banking`) into a presentable, end-to-end demo.
Every beat below was driven live and verified against real app state
(API reads, not just "the agent said so").
## The demo: 8 suggestion pills, in order
1. **Show the spending trend** — chart in chat
2. **Change my card PIN** — interactive PIN component *in the chat*:
card picker + four masked auto-advancing digits. The agent never asks
for or receives the digits, so the PIN stays out of the transcript and
the model's context
3. **What's on my screen?** — answers from what the page actually
renders
4. **Show me the 10 most expensive charges** — new `/charges` page,
agent navigates pre-filtered and stack-ranked
5. **Prep the Q2 spend report** — one click stages a real PDF invoice;
gpt-5.4 reads it and folds its 5 line items ($62,800) into the filed
report's figures and charts
6. **Summarize our spend** — recalls a stored *preference* and applies
it unasked; the recalled preference drives the component's props, so
memory changes the UI's structure
7. **I don't recognize the Delta charge** — recalls a stored *procedure*
and executes it: flag → alert → note
8. **Approve the $15,000 AWS charge** — learns a *new* procedure: record
→ watch the officer demonstrate → save to durable memory. On a **fresh
thread** it then applies that procedure to a different over-limit charge
unaided
Beats 6–8 are deliberately sequenced: already-knows-a-preference →
already-knows-a-procedure → learns-a-new-one.
## Shell and UI
- **Chat docked left, ChatGPT-style**: `[ threads 200 ][ conversation
480 ][ app ][ nav rail ]`. The app's icon rail moved right via flex
`order`, so nav still precedes `<main>` in the DOM
- The chat surface runs ChatGPT's neutral palette; the banking app keeps
its violet identity
- **Tool activity** renders as ChatGPT-style expandable lines (chevron
reveals the real call); internal plumbing (AG-UI state deltas) is
filtered out
- **Never markdown tables** — tabular data goes through components; a
one-row table is blocked structurally, since a single-record table is
narration, not data
- Assistant markdown scoped and retuned for a narrow column
- Filed reports are now a dashboard (KPI tiles + 3 charts + decision
rows), not a memo
- One colour per team across every chart, keyed to the team rather than
its index
- Report uses ranked bars, not a donut: an attached invoice pushes one
team to 96% and a donut collapses to a single ring
## Notable fixes worth a reviewer's eye
- **Anything a recalled procedure can call must be registered
globally.** Four action tools were registered on the cards route, so a
saved procedure only worked from one page and failed elsewhere with "the
required action tools aren't available"
- **An unanswered approval card poisons the thread.** The procedure's
closing step was human-in-the-loop; skipping it left an unresolved tool
call and the next message died with `Tool result is missing for tool
call …`. That step now runs without a gate — approvals that move money
keep theirs
- **Two families of helpers in `actions.ts`** and they are not
interchangeable: `openPolicyException` / `finalizePolicyException` /
`changeTransactionStatus` return `{ok, data/error}`; `changePin` /
`addNoteToTransaction` resolve with the updated record. Destructuring
`ok` off the second family reports success as failure
- **A stale canvas surface hid the page.** The canvas is derived from
the last `a2ui-surface` message and replaces the page body until
dismissed; the dismiss effect keyed on `pathname` only, so a `?tab=`
switch left it covering the page
- Suggestion pills ignore clicks while a run is in flight (a
double-click orphaned the previous run's tool call)
## Verification
Full 8-beat sequence run in one unbroken session from a clean reset,
checked against the API: charges navigate correctly; the report files
with 5 invoice additions; the Delta note content changes from its seeded
value; the teach arc captures all 6 demonstrated steps and persists the
`EXC-BOARD-APPROVED` procedure (memory 3 → 4); a fresh thread then
recalls it. Typecheck and lint clean; 0 console errors on load, both
light and dark.
## Not included on purpose
The `@copilotkit/license-verifier` `pnpm patch` (local workaround for
the "Invalid license token" banner) is left uncommitted — it patches a
dependency for every install and isn't demo scope.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
|
||
|
David McKay
|
cee8fcfcbb | Merge branch 'main' into banking-demo-upgrades | ||
|
David McKay
|
66a6af5d3e |
feat(banking): ChatGPT-style shell, gen-UI beats, and durable-memory self-learning
Turns the Northwind Finance banking demo into a presentable end-to-end demo.
Every beat was driven live and verified against real app state, not just the
agent's own claims.
The demo is eight suggestion pills, in order: show a chart; change a card PIN in
an interactive in-chat component; ask what is on screen; open the 10 most
expensive charges; prep the Q2 report from an attached PDF invoice; summarize
spend using a remembered preference; handle an unrecognized charge using a
remembered procedure; and finally learn a brand-new procedure by watching the
officer clear an over-limit charge. The last three are sequenced deliberately:
already-knows-a-preference, already-knows-a-procedure, learns-a-new-one — and on
a fresh thread the newly learned procedure is recalled and applied to a
different charge unaided.
Shell and UI:
- Chat docks LEFT as two columns (thread rail + conversation) with the app's
icon rail moved right via flex `order`, so nav still precedes <main> in the
DOM. The chat surface runs ChatGPT's neutral palette while the app keeps its
violet identity.
- Tool activity renders as ChatGPT-style expandable lines; internal AG-UI
plumbing is filtered out of the transcript.
- Tabular data always renders as components, never markdown tables; a one-row
table is blocked structurally because a single-record table is narration.
- Filed reports are a dashboard (KPI tiles, three charts, decision rows) rather
than a memo, with one colour per team across every chart and ranked bars in
place of a donut that collapsed when an invoice pushed one team to 96%.
- PIN entry happens in the chat component; the agent never asks for or receives
the digits.
Fixes worth review attention:
- Anything a RECALLED procedure can call must be registered globally. Four
action tools were registered on the cards route, so a saved procedure only
worked from one page.
- An unanswered human-in-the-loop card poisons the thread: skipping it left an
unresolved tool call and the next message failed with "Tool result is missing
for tool call ...". The procedure's closing step no longer gates; approvals
that move money still do.
- actions.ts has two helper families that are not interchangeable —
openPolicyException / finalizePolicyException / changeTransactionStatus return
{ok, data/error}, while changePin / addNoteToTransaction resolve with the
updated record. Destructuring `ok` off the second family reports success as
failure.
- A stale canvas surface hid the page: it is derived from the last a2ui-surface
message and replaces the page body until dismissed, but the dismiss effect
keyed on pathname only, so a ?tab= switch left it covering the page.
- Suggestion pills ignore clicks while a run is in flight, since a double-click
orphaned the previous run's tool call.
Deliberately NOT included: the @copilotkit/license-verifier pnpm patch (local
workaround for the "Invalid license token" banner) stays uncommitted, because it
patches a dependency for every install and is not demo scope.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|
David McKay
|
6632e48a89 | Merge branch 'main' into david/fix-cpk-7634-activity-snapshot-order | ||
|
David McKay
|
d892b7975c | Merge branch 'main' into docs/react-native-production-guide | ||
|
Benjamin Taylor
|
ef21c12b6d |
fix(channels-intelligence): surface an unreachable gateway host instead of hanging the connect
A managed Channel whose wsUrl points at a wrong or unreachable host sat in connecting for the caller's full settle budget and then reported only a timeout. Phoenix retries a failed FIRST connect forever and reports transport errors as reconnect churn, and the join push's own timeout never fires in that state (Channel.onError calls joinPush.reset() while joining, detaching the reply binding the armed timeout would have triggered), so the connect await hung indefinitely with no indication that the host was the problem. Watch the initial connect separately from reconnects, keyed off whether the socket has EVER opened: a socket that never opened rejects with a new RealtimeGatewayUnreachableError naming the endpoint and the underlying transport error, while one that opened and later dropped stays with the existing reconnect/give-up state machine. NXDOMAIN fails immediately (a host that does not exist cannot start existing); every other cause is given the new connectTimeoutMs window so a still-booting gateway is not turned into a permanently errored Channel — the supervising ChannelManager does not retry activation. The error deliberately does NOT carry the SETUP_REQUIRED marker: a misconfigured host must reject ready(), not resolve as setup_required. Refs OSS-623 |
||
|
Martha Schumann
|
551d7b0e7d | feat: share ops clerk session in docs header | ||
|
Benjamin Taylor
|
3b842ccf1b |
docs(channels-intelligence): name the gateway socket path the code actually uses
ConnectRealtimeGatewayOptions.wsUrl was documented as `wss://gateway.example/socket`, while the runtime skill lists `/socket` as a mistake because it is not a real path. The skill is right, and the gateway mounts exactly `/runner` and `/client` — there is no `/socket`. The two docs were describing different layers, which is how the contradiction survived: the public wsUrl a developer configures is a bare base, and the Intelligence client appends `/runner` before it reaches connectRealtimeGateway, after which Phoenix appends `/websocket`. So this option is the fully-resolved runner URL, and the doc comment now says so instead of implying developers should write `/socket` anywhere. Test fixtures follow. Refs OSS-621 |