This PR hardens artifact URL signing by encoding signature inputs in an
unambiguous binary payload before computing the HMAC.
What it changes:
- replace direct concatenation-style signing inputs with explicit
payload builders
- encode string fields with a length prefix before appending their bytes
- encode integer fields as fixed-width binary values instead of decimal
text
- apply the same hardening to both:
- Actions Artifact V4 signing in `routers/api/actions/artifactsv4.go`
- artifact download signing in `routers/api/v1/repo/action.go`
- add regression tests that verify distinct field combinations produce
distinct payloads and signatures
Why:
The previous signing logic built HMAC inputs by appending multiple
fields without a strongly structured representation. That kind of
construction can create ambiguity at field boundaries, where different
parameter combinations may serialize into the same byte stream for
signing.
This change removes that ambiguity by constructing a deterministic
payload format with explicit boundaries between fields.
Backport #37707
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
backport #37118
This PR closes remaining `public-only` token gaps in the API by making
the restriction apply consistently across repository, organization,
activity, notification, and authenticated `/api/v1/user/...` routes.
Previously, `public-only` tokens were still able to:
- receive private results from some list/search/self endpoints,
- access repository data through ID-based lookups,
- and reach several authenticated self routes that should remain
unavailable for public-only access.
This change treats `public-only` as a cross-cutting visibility boundary:
- list/search endpoints now filter private resources consistently,
- repository lookups enforce the same restriction even when addressed
indirectly,
- and self routes that inherently expose or mutate private account state
now reject `public-only` tokens.
---
Generated by a coding agent with Codex 5.2
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
Co-authored-by: Nicolas <bircni@icloud.com>
Backport #37465
Make DEFAULT_TITLE_SOURCE default to "auto" like GitHub
---------
Co-authored-by: 0xGREG <28388707+0xGREG@users.noreply.github.com>
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Nicolas <bircni@icloud.com>
Backport #37657 by @bircni
Fixes an issue where users could not commit changes on a file which is
unprotected.
Fixes#37655
Co-authored-by: Nicolas <bircni@icloud.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Backport #37704
This PR hardens OAuth token exchange validation by binding exchanged
credentials to the client and redirect URI that originally obtained
them.
What it changes:
- reject refresh token exchanges when the refresh token belongs to a
different OAuth application
- reject authorization code exchanges when the `redirect_uri` in the
token request differs from the `redirect_uri` stored with the
authorization code
- add integration coverage for:
- authorization code exchange with a mismatched redirect URI
- refresh token reuse across two different dynamically created OAuth
applications
Why:
OAuth authorization codes and refresh tokens must remain bound to the
client context that originally received them. Without those checks:
- a valid authorization code can be redeemed against a different
registered redirect URI of the same client
- a refresh token can be replayed by a different OAuth client
---------
Co-authored-by: Nicolas <bircni@icloud.com>
Backport #37706
This PR tightens several OAuth validation paths related to PKCE
handling, redirect URI normalization, and refresh-token replay safety.
What it changes:
- switch redirect URI comparison to ASCII-only normalization for
exact-match checks, avoiding Unicode case-folding surprises
- harden PKCE verification by:
- allowing PKCE omission only when no challenge data was stored
- rejecting exchanges with a missing verifier when PKCE was used
- rejecting malformed challenge state where a challenge exists without a
valid method
- comparing derived challenges with constant-time string matching
- make refresh-token invalidation counter updates conditional on the
previously observed counter value, so stale refresh state cannot be
accepted after the grant changes
Why:
These checks close gaps where:
- redirect URI comparisons could rely on broader Unicode normalization
than intended
- malformed or incomplete PKCE state could be treated too permissively
- concurrent or stale refresh-token use could advance the same grant
more than once
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
Co-authored-by: Nicolas <bircni@icloud.com>
Backport #37588 by @pandareen
## Summary
Fixes
[go-gitea/gitea#37564](https://github.com/go-gitea/gitea/issues/37564):
when an OIDC provider returns a `picture` claim, Gitea is supposed to
download that image as the user's avatar (if `[oauth2_client]
UPDATE_AVATAR = true`). Two latent bugs prevented this from working
consistently:
1. **Default Go User-Agent rejected by some image hosts.**
`oauth2UpdateAvatarIfNeed` used `http.Get`, which sends `User-Agent:
Go-http-client/1.1`. Hosts like `upload.wikimedia.org` reject that UA
with `403`, and every error path silently returned, so the user was left
with an identicon and **no log line** to diagnose the issue.
2. **Link-account *register* path skipped avatar sync.** First-time OIDC
sign-ins where auto-registration is disabled (or required a
username/password retype) go through `LinkAccountPostRegister`, which
created the user but never called `oauth2SignInSync`. So the avatar /
full name / SSH keys from the IdP were dropped on the floor for those
users, even though the existing-account-link path (`oauth2LinkAccount`)
and the auto-register path (`handleOAuth2SignIn`) both already did the
sync.
## Changes
- `routers/web/auth/oauth.go` — `oauth2UpdateAvatarIfNeed` now uses
`http.NewRequest` + `http.DefaultClient.Do`, sets `User-Agent: Gitea
<version>`, and logs every failure path at `Warn` (invalid URL, fetch
error, non-200, body read error, oversize body, upload error). No silent
failures.
- `routers/web/auth/linkaccount.go` — `LinkAccountPostRegister` now
calls `oauth2SignInSync` after a successful user creation, mirroring the
auto-register and link-existing-account flows.
- `tests/integration/oauth_avatar_test.go` — new
`TestOAuth2AvatarFromPicture` integration test with five sub-cases:
- `AutoRegister_FetchesAvatarFromPictureWithGiteaUA` — happy path,
asserts `use_custom_avatar=true`, an avatar hash is set, exactly one
HTTP request was made, and the request carried a `Gitea ` UA. The mock
server enforces the UA prefix to mirror real-world hosts that reject
Go's default UA.
- `AutoRegister_NonOK_DoesNotUpdateAvatar` — server returns 403; user's
avatar must remain unset.
- `AutoRegister_EmptyPicture_NoFetch` — empty `picture` claim must not
trigger any HTTP request.
- `AutoRegister_UpdateAvatarFalse_NoFetch` — `UPDATE_AVATAR=false` must
not trigger any HTTP request.
- `LinkAccountRegister_FetchesAvatarFromPicture` — guards the
`linkaccount.go` fix; without the new `oauth2SignInSync` call this
assertion fails.
## Test plan
- [x] `go test -tags 'sqlite sqlite_unlock_notify' -run
'^TestOAuth2AvatarFromPicture$' ./tests/integration/ -v` — 5/5 sub-tests
pass.
- [x] Manual: log in as a Keycloak user with `picture` claim pointing at
`https://avatars.githubusercontent.com/u/9919?v=4` — Gitea avatar is
replaced with the GitHub picture.
- [x] Manual: same flow with `https://upload.wikimedia.org/...` —
request now succeeds (or returns a clearly logged `Warn` line if
rate-limited with `429`); previously it silently 403'd.
- [x] Manual: `UPDATE_AVATAR=false` — user keeps the identicon, no
outbound request in container logs.
- [ ] Reviewer: please double-check that no other call sites of
`oauth2UpdateAvatarIfNeed` rely on the old `http.Get` behaviour.
## Related
- Upstream issue: go-gitea/gitea#37564
--------------------------------------------
AI Editor was used in this PR
---------
Signed-off-by: silverwind <me@silverwind.io>
Co-authored-by: pandareen <7270563+pandareen@users.noreply.github.com>
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Nicolas <bircni@icloud.com>
Backport #37695 by @lunny
This PR fixes two permission-checking gaps in Git and LFS request
handling.
## What it changes
- keep wiki Git HTTP pushes on the normal write-permission path, even
when proc-receive support is enabled
- revalidate LFS bearer token requests against the current user state
and current repository permissions before allowing access
- add regression coverage for unauthorized wiki HTTP pushes
- add LFS tests for blocked users, revoked repository access, read-only
upload attempts, and valid write access
## Why
- wiki repositories should not inherit the relaxed refs/for handling
used for normal code repositories
- LFS authorization tokens should not remain usable after a user is
disabled or loses repository access
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #37679 by @Exgene
## Description
As mentioned in #37654 `AWSAccessKeyID` and `AWSSecretAccessKey` are not
encrypted and stored as is.
## Update
Follow the existing `AuthToken` flow of setting the `Encrypted` fields,
`Decrypting` them later and `Clearing` them at the end.
Closes#37654
Signed-off-by: Kausthubh J Rao <105716675+Exgene@users.noreply.github.com>
Co-authored-by: Kausthubh J Rao <105716675+Exgene@users.noreply.github.com>
Co-authored-by: Lauris B <lauris@nix.lv>
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
Backport #37631 by @silverwind
`UpdateLog` short-circuits on `len(Rows)==0` before honoring `NoMore`,
so a final empty `UpdateLog{NoMore:true}` never runs `TransferLogs`. The
task's `dbfs_data` rows are then never moved to log storage and never
deleted.
The bug has been latent since the original Actions implementation,
`act_runner` versions after
[runner#819](https://gitea.com/gitea/runner/pulls/819) trip it
deterministically.
Fix: let `NoMore=true` with no new rows fall through to `TransferLogs`.
Bail when the runner has outrun the server (`Index > ack`) even with
`NoMore`, since archiving a log with a gap is worse than retrying.
Always call `WriteLogs` so `offset==0` bootstraps an empty DBFS file in
the no-output case (otherwise `TransferLogs` would fail at `dbfs.Open`).
Fixes: https://github.com/go-gitea/gitea/issues/37623
Ref: [runner#952](https://gitea.com/gitea/runner/pulls/952)
Ref: [runner#950](https://gitea.com/gitea/runner/pulls/950)
---
This PR was written with the help of Claude Opus 4.7
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
Backport of #37662.
---
This PR was written with the help of Claude Opus 4.7
---------
Co-authored-by: Giteabot <teabot@gitea.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
## Summary
When comparing branches with **no common merge base** (e.g. unrelated
histories or orphan branches), `PageIsComparePull` is false and
`CommitCount` is zero. The compare template still showed
`repo.commits.nothing_to_compare`, which in German reads like the
branches are identical—even though the flash already explains there is
no merge base.
## Changes
- **`templates/repo/diff/compare.tmpl`**: Only render the grey “nothing
to compare” segment when `CompareInfo.CompareBase` is set.
<img width="1962" height="564"
src="https://github.com/user-attachments/assets/adc3b4a0-6f03-45da-b297-e15e5ad0aa79"
/>
---
Backport of https://github.com/go-gitea/gitea/pull/37651
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
## Summary
- handle compare requests where base and head refs have no common merge
base without returning 500
- keep the compare branch selectors usable and show a clear warning
message
- add regression coverage for unrelated-history compare selection and
merge-base error detection
Fixes#37469
Manuel Backport of: https://github.com/go-gitea/gitea/pull/37470
---------
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #37583 by @lunny
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: Nicolas <bircni@icloud.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: silverwind <me@silverwind.io>
Backport #37592 by @bircni
When a workflow job failed, the API response reported all steps as
failed — even steps that had completed successfully before the failing
step. `ToActionWorkflowJob` was calling `ToActionsStatus(job.Status)`
for every step instead of `ToActionsStatus(step.Status)`, so the job's
overall conclusion was propagated to each step.
Each `ActionTaskStep` has its own `Status` field that tracks the actual
outcome of that step independently of the job result.
Co-authored-by: Nicolas <bircni@icloud.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #37553
fixes adding collaborative owners in Actions settings when the user or
organization name contains capital letters.
Fixes#37548
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Nicolas <bircni@icloud.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #37572 by @Exgene
## Issue
Closes#37217
The error string was getting lost while returning due to `ctx.JSON()`
which cannot serialize the `error` object.
## Fix
Use `ctx.APIError()` to return proper error messages back to the client.
Co-authored-by: Kausthubh J Rao <105716675+Exgene@users.noreply.github.com>
Backport #37570 by @Exgene
## The issue
Closes#37568. Basically due to empty fields being present in the
actions file, the jobs would be produced as `nil` inside `jobparser.go`
. Because of this when we call `Parse` on the `jobparser` module.
```go
Needs: job.Needs(),
```
would propagate the `nil` job down the chain.
## The fix
For now i decide to fix it by guarding with an `if job == nil` check.
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Kausthubh J Rao <105716675+Exgene@users.noreply.github.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #37546 by @KalashThakare
This PR fixes issue #37523:
1. Prevents a 500 error on the Actions page when disabling workflows
with an empty workflow parameter
2. Uses a single **ctx.JSONError** in the handler to return 400 Bad
Request with the message “workflow is required” for empty input
Co-authored-by: Kalash Thakare ☯︎ <kalashthakare898@gmail.com>
Backport #37461 by @silverwind
Fixes#37446.
The job-status resolver in `checkJobsOfCurrentRunAttempt` only
considered `needs` and job-level concurrency when transitioning jobs out
of `Blocked`. When something drove the resolver against a run blocked
solely by workflow-level concurrency — for example, a sibling run in the
same group entering the queue and triggering `EmitJobsIfReadyByRun` —
the run's job silently became `Waiting` while another run still held the
concurrency group, and the runner could pick it up, defeating the
concurrency guarantee.
The fix bails out of the resolver when the run's latest attempt is still
blocked by run-level concurrency. `checkRunConcurrency` re-evaluates
when the holding run finishes.
Covered by a unit test
(`Test_checkJobsOfCurrentRunAttempt_RunLevelConcurrencyKeepsJobsBlocked`
in `services/actions/job_emitter_test.go`) that sets up a Running holder
attempt and a Blocked sibling attempt in the same concurrency group
directly in the DB, calls `checkJobsOfCurrentRunAttempt`, and asserts
the blocked job stays `Blocked`. Fails on master, passes with the fix.
---
This PR was written with the help of Claude Opus 4.7
---------
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Claude (Opus 4.7) <noreply@anthropic.com>
