Commit graph

40 commits

Author SHA1 Message Date
Marshall Bowers
7be1f2418d
Replace zed_llm_client with cloud_llm_client (#35309)
This PR replaces the usage of the `zed_llm_client` with the
`cloud_llm_client`.

It was ported into this repo in #35307.

Release Notes:

- N/A
2025-07-30 00:09:14 +00:00
Antonio Scandurra
de16f2bbe6
Bypass account age check when feature flag is set (#32393)
Release Notes:

- N/A
2025-06-09 18:44:48 +02:00
Ben Brandt
ca72efe701
Add overdue invoices check (#31290)
- Rename current_user_account_too_young to account_too_young for
consistency
- Add has_overdue_invoices field to track billing status
- Block edit predictions when user has overdue invoices
- Add overdue invoice warning to inline completion menu

Release Notes:

- N/A

---------

Co-authored-by: Marshall Bowers <git@maxdeviant.com>
2025-05-23 20:02:02 +00:00
Kirill Bulatov
16366cf9f2
Use anyhow more idiomatically (#31052)
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.

The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.

The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.

* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`

Release Notes:

- N/A
2025-05-20 23:06:07 +00:00
Marshall Bowers
f7a0834f54
collab: Create Zed Free subscription when issuing an LLM token (#30975)
This PR makes it so we create a Zed Free subscription when issuing an
LLM token, if one does not already exist.

Release Notes:

- N/A

---------

Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
2025-05-19 18:45:22 -04:00
Marshall Bowers
f29c6e5661
Update zed_llm_client to v0.8.1 (#30433)
This PR updates the `zed_llm_client` crate to v0.8.1.

The name of `Plan::Free` changed to `Plan::ZedFree` in this version.

Release Notes:

- N/A
2025-05-09 21:08:03 +00:00
Marshall Bowers
cf8f003916
collab: Improve error message when requesting an LLM token without a subscription (#30405)
This PR improves the error message when trying to obtain an LLM token
without a subscription:

<img width="411" alt="Screenshot 2025-05-09 at 12 30 41 PM"
src="https://github.com/user-attachments/assets/c53326ba-4a99-4d9c-88ba-674e520f941f"
/>

Release Notes:

- N/A
2025-05-09 16:51:41 +00:00
Marshall Bowers
d270f6b953
collab: Require subscription_period in LLM token claims (#30392)
This PR makes the `subscription_period` field in the LLM token claims
required.

Release Notes:

- N/A
2025-05-09 15:20:14 +00:00
Marshall Bowers
6827bf114a
collab: Remove legacy claims from LLM token (#30294)
This PR removes some legacy claims related to the old billing from the
LLM token.

We already stopped reading this in the LLM Worker.

Also removed an outdated feature flag check that restricted access to
obtaining an LLM token.

Release Notes:

- N/A
2025-05-08 14:32:54 -04:00
Marshall Bowers
181cd6294f
collab: Pass down staff usage in UpdatePlan message (#29939)
This PR fixes an issue where we weren't correctly passing down usage
information in the `UpdatePlan` message for Zed staff.

Release Notes:

- N/A
2025-05-05 18:02:54 +00:00
Marshall Bowers
161f6dfcb6
collab: Set billing-related fields for Zed staff (#29887)
This PR sets the billing-related fields in the LLM token claims for Zed
staff.

Staff members are automatically in the Zed Pro plan with a subscription
periods that spans the entirety of each month.

Release Notes:

- N/A
2025-05-04 21:00:34 +00:00
Marshall Bowers
cceb13b7cd
collab: Add use_llm_request_queue to LlmTokenClaims (#29877)
This PR adds a `use_llm_request_queue` field to the LLM token claims,
based on the `llm-request-queue` feature flag.

Release Notes:

- N/A
2025-05-04 12:08:43 -04:00
Marshall Bowers
5bf1b4f0a8
collab: Add use_new_billing to LlmTokenClaims (#29739)
This PR adds a `use_new_billing` field to the LLM token claims, based on
the `new-billing` feature flag.

Release Notes:

- N/A
2025-05-01 15:43:53 +00:00
Marshall Bowers
24e47de02a
collab: Add has_extended_trial to LlmTokenClaims (#29622)
This PR adds the `has_extended_trial` field to the LLM token claims.

Release Notes:

- N/A
2025-04-29 20:22:51 +00:00
Marshall Bowers
9a325a23e5
collab: Set overage preferences in LLM token claims (#29457)
This PR sets the user's overage preferences in the LLM token claims.

Release Notes:

- N/A
2025-04-26 02:27:47 +00:00
Marshall Bowers
266c41ed9a
collab: Add can_use_web_search_tool to LLM token claims (#29278)
This PR adds a `can_use_web_search_tool` field to the LLM token claims.

Currently anyone in the `assistant2` feature flag will have access to
the web search tool.

Co-authored-by: Bennet <bennet@zed.dev>

Release Notes:

- N/A
2025-04-23 14:22:18 +00:00
Marshall Bowers
9bbc2e0fb2
collab: Set plan in LLM token based on subscription (#29231)
This PR updates the `plan` field in the LLM token to be based on the
subscription.

We weren't using this field anywhere outside of the new billing code, so
it is safe to change its meaning.

Release Notes:

- N/A
2025-04-22 19:44:16 +00:00
Marshall Bowers
3fef3cc392
Use more types/constants from zed_llm_client (#28909)
This PR makes it so we use more types and constants from the
`zed_llm_client` crate to avoid duplicating information.

Also updates the current usage endpoint to use limits derived from the
`Plan`.

Release Notes:

- N/A
2025-04-16 20:58:00 +00:00
Marshall Bowers
bb0b2a5b7b
collab: Remove has_predict_edits_feature_flag from LlmTokenClaims (#28879)
This PR removes the `has_predict_edits_feature_flag` field from the
`LlmTokenClaims`.

We are no longer reading this anywhere.

Release Notes:

- N/A
2025-04-16 17:11:18 +00:00
Marshall Bowers
b486e32f05
collab: Add GET /billing/usage endpoint (#28832)
This PR adds a `GET /billing/usage` endpoint for retrieving billing
usage to show on the `zed.dev/account` page.

Release Notes:

- N/A
2025-04-16 03:28:09 +00:00
Marshall Bowers
68ec1d724c
collab: Include subscription_period in LLM token claims (#28819)
This PR updates the LLM token claims to include the user's active
subscription period.

Release Notes:

- N/A
2025-04-15 23:25:41 +00:00
Piotr Osiewicz
dc64ec9cc8
chore: Bump Rust edition to 2024 (#27800)
Follow-up to https://github.com/zed-industries/zed/pull/27791

Release Notes:

- N/A
2025-03-31 20:55:27 +02:00
Marshall Bowers
cd5d7e82d0
collab: Make account age-related fields required in LlmTokenClaims (#26959)
This PR makes the account age-related fields required in
`LlmTokenClaims`.

We've also removed the account age check from the LLM token issuance
endpoint, instead having it solely be enforced in the `POST /completion`
endpoint.

This change will be safe to deploy at ~8:01PM EDT.

Release Notes:

- N/A
2025-03-17 19:54:44 -04:00
Marshall Bowers
0851842d2c
collab: Defer account age check to POST /completion endpoint (#26956)
This PR defers the account age check to the `POST /completion` endpoint
instead of doing it when an LLM token is generated.

This will allow us to lift the account age restriction for using Edit
Prediction.

Note: We're still temporarily performing the account age check when
issuing the LLM token until this change is deployed and the LLM tokens
have had a chance to cycle.

Release Notes:

- N/A
2025-03-17 22:42:29 +00:00
Marshall Bowers
1397e01735
collab: Clean up LLM token creation (#26955)
This PR cleans up the LLM token creation a bit.

We now pass in the entire list of feature flags to the
`LlmTokenClaims::create` method to prevent having a bunch of confusable
`bool` parameters.

Release Notes:

- N/A
2025-03-17 22:25:43 +00:00
Conrad Irwin
63091459d8
Allow too many arguments (#26375)
This is nearly half of our #allows, and seems like something we happily
break whenever we need

Release Notes:

- N/A
2025-03-10 13:38:30 -06:00
Cole Miller
c0c48d30db
Revert "file_finder: Remove common segments of long paths in search results (#25049)" (#25163)
This reverts commit 9ef0501853 due to a
panic.

```
{
  "thread": "main",
  "payload": "9 is not a valid char boundary in path \"crates/…/LiveKitBridge/\"",
  "location_data": {
    "file": "crates/file_finder/src/file_finder.rs",
    "line": 646
  }
}
```

Release Notes:

- N/A
2025-02-19 15:32:29 +00:00
Cole Miller
9ef0501853
file_finder: Remove common segments of long paths in search results (#25049)
This PR makes progress on #7711 by identifying any common prefix of the
paths in the file finder's search results, and replacing the "interior"
of that prefix---every path segment but the first and last---with `...`,
when a heuristic indicates that the longest path would otherwise
overflow the modal.

The elision is not applied to any segment that contains a match for the
search query.

There may be more work to do on #7711 in the case of long result paths
that do not share a significant common prefix.

Release Notes:

- Improved display of long paths in the file finder modal

Co-authored-by: Max <max@zed.dev>
2025-02-18 10:09:15 -05:00
Agus Zubiaga
4a7630204a
Check for predict-edits feature flag, remove is_staff check (#23165)
Release Notes:

- N/A

---------

Co-authored-by: Thorsten Ball <mrnugget@gmail.com>
2025-01-15 13:52:10 +00:00
Marshall Bowers
8a85d6ef96
collab: Make metrics_id required in LlmTokenClaims (#21771)
This PR makes the `metrics_id` field on the `LlmTokenClaims` required,
as we always have one in practice.

Release Notes:

- N/A
2024-12-09 17:58:14 -05:00
Conrad Irwin
984bb192ba
Send llm events to snowflake too (#21091)
Closes #ISSUE

Release Notes:

- N/A
2024-11-22 20:40:39 -07:00
Marshall Bowers
1a4b253ee5
collab: Add support for a custom monthly allowance for LLM usage (#19525)
This PR adds support for setting a monthly LLM usage allowance for
certain users.

Release Notes:

- N/A
2024-10-21 17:12:33 -04:00
Marshall Bowers
69711660ab
collab: Make LLM billing fields required in LlmTokenClaims (#18959)
This PR makes the `has_llm_subscription` and
`max_monthly_spend_in_cents` fields in the `LlmTokenClaims` required.

This change will be safe to deploy in ~45 minutes.

Release Notes:

- N/A
2024-10-09 18:42:22 -04:00
Marshall Bowers
3db789ed90
collab: Include max monthly spend preference in LLM token (#18955)
This PR updates the LLM token claims to include the maximum monthly
spend.

Release Notes:

- N/A
2024-10-09 17:39:34 -04:00
Marshall Bowers
801210cd50
collab: Make github_user_login required in LlmTokenClaims (#18882)
This PR makes the `github_user_login` field required in the
`LlmTokenClaims`.

We previously added this in
https://github.com/zed-industries/zed/pull/16316 and made it optional
for backwards-compatibility.

It's been more than long enough for all of the previous LLM tokens to
have expired, so we can now make the field required.

Release Notes:

- N/A
2024-10-08 20:03:33 -04:00
Marshall Bowers
f861479890
collab: Update billing code for LLM usage billing (#18879)
This PR reworks our existing billing code in preparation for charging
based on LLM usage.

We aren't yet exercising the new billing-related code outside of
development.

There are some noteworthy changes for our existing LLM usage tracking:

- A new `monthly_usages` table has been added for tracking usage
per-user, per-model, per-month
- The per-month usage measures have been removed, in favor of the
`monthly_usages` table
- All of the per-month metrics in the Clickhouse rows have been changed
from a rolling 30-day window to a calendar month

Release Notes:

- N/A

---------

Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max <max@zed.dev>
2024-10-08 18:29:38 -04:00
Max Brunsfeld
b5bd8a5c5d
Add logic for closed beta LLM models (#16482)
Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>
2024-08-19 11:09:52 -07:00
Marshall Bowers
9233418cb8
collab: Attach GitHub login to LLM spans (#16316)
This PR updates the LLM service to include the GitHub login on its
spans.

We need to pass this information through on the LLM token, so it will
temporarily be `None` until this change is deployed and new tokens have
been issued.

Release Notes:

- N/A
2024-08-15 17:06:20 -04:00
Bennet Bo Fenner
3a52d6cc52
assistant: Limit model access for Zed AI users to Claude-3.5-sonnet (#15904)
This prevents users from accessing other models, such as OpenAI's GPT-4
or Google's Gemini-Pro.
Staff members can still access all models.

Co-authored-by: Thorsten <thorsten@zed.dev>

Release Notes:

- N/A

---------

Co-authored-by: Thorsten <thorsten@zed.dev>
2024-08-07 16:26:56 +02:00
Max Brunsfeld
8e9c2b1125
Introduce a separate backend service for LLM calls (#15831)
This PR introduces a separate backend service for making LLM calls.

It exposes an HTTP interface that can be called by Zed clients. To call
these endpoints, the client must provide a `Bearer` token. These tokens
are issued/refreshed by the collab service over RPC.

We're adding this in a backwards-compatible way. Right now the access
tokens can only be minted for Zed staff, and calling this separate LLM
service is behind the `llm-service` feature flag (which is not
automatically enabled for Zed staff).

Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
2024-08-05 20:26:21 -04:00