copilotkit 4.15.0 → 4.17.0

package/README.md

@@ -280,8 +280,14 @@ and gives up after 10 minutes.
 
 Under `--json`, the first `authentication_url` record is the URL with the code
 in it, and it also carries `user_code` and `expires_at`. A sign-in that ends without a session writes a `failed`
-record with `reason: expired` or `reason: access_denied`. If the Ops service
-has no device routes, `login --json` falls back to the loopback flow.
+record with `reason: expired` or `reason: access_denied`, and with
+`retry: ask_developer`: a person must act before a new code can work. After 2
+codes in a row expire with nobody approving them, `login --json` refuses to
+request another. It writes a `failed` record with `reason: repeated_expiry` and
+exits non-zero. Run `copilotkit login --json --force` when someone is ready to
+approve. Any sign-in that succeeds resets the count, and the count lapses after
+a day. If the Ops service has no device routes, `login --json` falls back to the
+loopback flow.
 
 Approve a code only if your own terminal or coding agent showed it to you. If
 someone sent you a code, deny the request: approving it signs their CLI in as
@@ -334,7 +340,10 @@ asks which frontend they want and offers Slack and Microsoft Teams there. If the
 copied prompt came from a Slack or Teams docs page, that page is the named
 frontend.
 Its first prompt records the coding agent with `onboard identify`, including when
-the entry command omitted `--coding-agent`. Channel setup stage events include
+the entry command omitted `--coding-agent`. The agent also passes `--model` with
+the exact model id its instructions name, and leaves it out when they name none.
+The event records a missing id as `unknown`, and the coding agent the environment
+shows as `detected_coding_agent`. Channel setup stage events include
 the existing `onboarding_run_id` when the command runs inside an onboarding run;
 standalone commands omit it. These events use the CLI's existing telemetry consent gate.
 
@@ -350,6 +359,24 @@ subagent returns, when the plan is approved, when implementation validation
 passes, and on each proof attempt and repair cycle. A run that cannot go on
 reads `feature/stop`, reports from there, and does not run `onboard complete`.
 
+### Onboarding for an existing Intelligence project
+
+Use the optional `--project` flag when the developer already chose a hosted
+Intelligence project, for example from the Threads or Analytics page of that
+project. It takes the numeric project id. The run then selects that project at
+the project-selection step instead of asking which project to use or creating
+one. The CLI still checks that the signed-in organization holds the project, so a
+link cannot point a run at another organization's project.
+
+```bash
+npx --yes copilotkit@latest onboard start \
+  --project <project-id> \
+  --run <12-character-id>
+```
+
+`--project` accepts digits only and refuses anything else before a run starts.
+A later `onboard start` that re-enters the same run keeps its project.
+
 ### Coming back after a run that broke
 
 A run whose stack this release serves, and which broke anyway, reads
@@ -432,13 +459,21 @@ copilotkit init -n my-agent -f langgraph-py \
 - `--project <slug-or-id>` selects an existing hosted Intelligence project, and
   `--create <name>` makes one. They are mutually exclusive, and they resolve the
   same way `copilotkit project select` does: a typo fails with the available
-  slugs instead of creating something you did not ask for.
+  slugs instead of creating something you did not ask for. A refused value fails
+  before `init` writes any file, so you can retry into the same directory.
 - `-y`/`--yes` installs dependencies without asking; `--no-install` answers the
   same question without installing. `--install` is a longhand for `--yes`.
 - `--no-key-prompt` skips the question about a missing model key. Use it where the
   shell is a pseudo-terminal but nobody types, such as a coding agent's shell:
   there `init` sees a terminal and would ask anyway. The next steps still name
   each missing key.
+- `--model-key-file <path>` copies the model key the starter needs from an env
+  file you name into the new app. Only that variable is copied, into the file the
+  starter reads (`agent/.env` for the Microsoft Agent Framework Python starter).
+  `init` prints the variable name and never the value. A real value already in
+  the app is kept. A missing or unreadable file stops `init` before it clones
+  anything. The .NET starter keeps its key in `dotnet user-secrets`, so this flag
+  does not fill it.
 
 A run with no terminal is refused only for what it has not answered, and every
 missing flag is named at once. Sign-in is the one answer no flag supplies:
@@ -460,7 +495,16 @@ are supported. Configure source identity and access with the
 [`MASTRA_IMPORT_*` variables](../../libs/import-mastra/README.md); destination
 Intelligence credentials use the usual import options.
 
-Local access requires Node 22.13+. Use the same source namespace when switching
+Local access requires Node 22.13+ and npm. The CLI does not ship the LibSQL
+driver, so the first local import installs `@mastra/libsql@1.14.3` and
+`@mastra/core@1.48.0` into `~/.copilotkit/cache/mastra-driver/`
+(`$XDG_CACHE_HOME/copilotkit/mastra-driver/` when that variable is an absolute
+path) and reuses them after that. The install overrides the npm settings
+`legacy-peer-deps` and `omit=optional`, which would otherwise leave out a
+required peer or the native binary. If that install fails, the error prints the
+`npm install` command to run by hand. Server mode installs nothing.
+
+Use the same source namespace when switching
 between local and remote access so repeat imports deduplicate. Import while the
 source is idle. This reads existing history and pending data; it does not execute
 models, tools or native resume operations.
@@ -990,6 +1034,24 @@ exits zero only when `/info` is valid, declares the agent named by `--agent`,
 reports no Intelligence entitlement, and `--round-trip` passes. Both `--round-trip` and
 `--agent` are required for an OSS pass.
 
+Without `--expect-runtime`, `verify` checks an app as open source on its own
+when nothing points at a hosted setup: no `.copilotkit/project.json`, no
+Intelligence key, and a runtime that answers `/info` without an Intelligence
+client. The report says so at the top, names the runtime URL it checked, and
+says when that URL was only assumed. `--json` reports
+`"expectRuntime": "oss"` with `"expectRuntimeSource": "detected"` (otherwise
+`"flag"` or `"default"`). The round trip still has to pass. It runs against the
+agent `--agent` names, with or without `--round-trip`. Without `--agent`, when
+the runtime declares exactly one agent, `verify` runs it and names it. With no
+agent or several, the run fails and names `--round-trip --agent <id>`. A runtime
+mounted `mode: "single-route"` cannot pass this way without a key, because
+`verify` reads a single-route answer from the Intelligence platform and an
+open-source runtime records nothing there. Mount it multi-route (the default)
+and point `--runtime-url` at that endpoint.
+Pass `--expect-runtime intelligence` to check the hosted setup instead. A
+recorded project, a key, or a runtime that does not answer keeps the hosted
+checks.
+
 ### Which runtime URL gets probed
 
 `verify` works the port out from the project rather than assuming one. In order:
@@ -1173,6 +1235,35 @@ started, and a starter that serves both halves from one script loses both when
 either one goes down. Restart what you started, with the command you started it
 with, and leave the rest running.
 
+### A model key has no credits or is rejected
+
+A key with no credits passes every static check. The first model call then
+fails inside the agent, and the round-trip proof reports only a timeout.
+
+Ask the vendor about one key before the build:
+
+```bash
+copilotkit onboard model-key --key OPENAI_API_KEY
+copilotkit onboard model-key --key ANTHROPIC_API_KEY --env-file agent/.env --json
+```
+
+The command reads the key from the env file (`.env` by default) and sends one
+request with a one-token answer to that vendor. The call costs a fraction of a
+cent. It knows `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, and `GOOGLE_API_KEY`.
+
+- `pass`: the vendor served a model call with the key.
+- `fail`: the vendor refused the key. The cause is `model_quota` (no credits) or
+  `model_auth` (a rejected key).
+- `missing`: the env file or the key is absent, or the value is a placeholder.
+- `unsupported` or `undetermined`: the check did not settle it. A rate limit, a
+  vendor outage, or a probe model the key may not use proves nothing about the
+  key, so none of them is a `fail`.
+
+It does not send the key when a base URL such as `OPENAI_BASE_URL` points the
+SDK at another endpoint, or when the shell exports a different value for the
+key. It never prints the key, and it never prints the vendor's error message,
+because a vendor can echo part of the key in it.
+
 ### A command, subcommand, or flag that should exist is rejected
 
 `npx` keys its cache on the spec string, so `copilotkit@latest` can keep serving
@@ -1271,7 +1362,8 @@ projects created with the CLI. See the [package license map](../../docs/licensin
 ### Add existing threads to Learning
 
 Use `learning threads` to add prior conversations to a Container. A thread can
-join one Container permanently. Already-bound threads are ineligible.
+join this Container without changing their other memberships. Threads already
+in this Container are ineligible for another addition.
 
 ```bash
 copilotkit learning threads list support --binding all --json
@@ -1289,15 +1381,31 @@ The binding filter accepts `all`, `unbound`, `this_container`, or `other_contain
 The source filter accepts `all`, `app`, `slack`, or `teams`, where `app` means the
 thread arrived straight from the Runtime and the provider values select threads a
 Channel created.
+`unbound` means no active Container membership. `other_container` means active
+membership elsewhere, without membership in this Container. Those threads remain
+eligible for addition to this Container.
 
-Read the preview before commit. `--yes` approves permanent assignment of that
-saved selection. Each operation accepts at most 10,000 threads. New matching
+Read the preview before commit. `--yes` adds or restores memberships for that
+saved selection. Existing memberships in other Containers stay active. Each operation accepts at most 10,000 threads. New matching
 threads cannot enter an existing preview, and a repeated commit cannot bind a
-second batch. Threads bound by another action after preview are skipped and
-reported. Recovery continues in the background after the CLI exits.
+second batch. Threads already added to the same Container after preview are skipped and
+reported. A retry of a committed operation does not undo a later removal. Recovery continues in the background after the CLI exits.
 
 Results distinguish threads bound, runs harvested, runs unrecoverable, other
 skipped runs, and pending runs. Pending work is not a completed harvest. The
 preview reflects retained history at its timestamp; delayed events or retention
 changes can change the final result. `--json` prints a versioned result envelope
 on stdout, including errors, and failures exit nonzero.
+
+## Download skills from several containers
+
+```bash
+copilotkit skills download support company-wide --output ./skills
+```
+
+Several container IDs produce separate directories, such as `./skills/support/refund-policy/SKILL.md`.
+A single container keeps the existing flat layout, such as `./skills/refund-policy/SKILL.md`.
+The destination must not already exist. The CLI validates every bundle before it creates the destination.
+If a download or validation fails, the CLI leaves no partial destination.
+Container IDs must be unique and belong to the selected project. Select up to 50 containers.
+Multiple containers use one product API batch request. If any container fails, the whole request fails.

package/cli-build-info.json

@@ -2,20 +2,20 @@
   "schemaVersion": 1,
   "package": {
     "name": "copilotkit",
-    "version": "4.15.0"
+    "version": "4.17.0"
   },
   "intelligence": {
-    "commit": "f6de0940e2aac5d2e323767f3d6431354715d2e6"
+    "commit": "f6f91f8357a9058dcda3f2ef07a3283e23ddb9e8"
   },
   "copilotKit": {
-    "submittedInput": "33db9a81ccfd",
-    "commit": "33db9a81ccfd2d6e820defe3c1616594909439af"
+    "submittedInput": "0c8647a7f4ec",
+    "commit": "0c8647a7f4ecf565e58405642539c9d9744f62c5"
   },
   "channel": "production",
-  "triggeringActor": "AlemTuzlak",
+  "triggeringActor": "BenTaylorDev",
   "workflow": {
-    "runId": "36016174452",
-    "runUrl": "https://github.com/CopilotKit/Intelligence/actions/runs/36016174452"
+    "runId": "36178536102",
+    "runUrl": "https://github.com/CopilotKit/Intelligence/actions/runs/36178536102"
   },
   "validationResult": "passed",
   "ag2": {
@@ -24,5 +24,5 @@
     "revision": "main",
     "pinned": false
   },
-  "builtAt": "2026-09-24T14:55:57Z"
+  "builtAt": "2026-09-25T19:17:42Z"
 }