# Description of Changes
Two layers — the `DocumentClassifier` utility plus the full data model
for the new billing engine. Nothing wires the entities into application
behaviour yet; services and controllers land in follow-up PRs.
**Companion PR:**
[Stirling-PDF-SaaS#296](https://github.com/Stirling-Tools/Stirling-PDF-SaaS/pull/296)
— Supabase migration for the v3 dev branch, schema-equivalent to the
Flyway migration in this PR.
## 1. DocumentClassifier (under `payg.docs`)
`DocumentClassifier` computes the doc-unit cost of an uploaded file (or
multi-file input) under a `PricingPolicy`. PDFs read page count via
`stirling.software.jpdfium.PdfDocument`; non-PDFs are bytes-only.
Formula: `max(ceil(pages / docPagesPerUnit), ceil(bytes /
docBytesPerUnit))` clamped to `[1, fileUnitCap]`. Multi-file is the sum
of raw per-file units capped at `fileUnitCap × file_count`.
Two floors, by design: the classifier returns `docUnits` with an
absolute `1` floor for non-empty input; the policy-level
`minChargeUnits` is intentionally applied later, at process-open time in
`JobChargeService`, per design § 3.4 (`unitsForProcess =
max(policy.min_charge_units, docUnits)`). Documented in the interface +
impl javadoc.
Upload bytes are materialised through
`TempFileManager.createManagedTempFile` so jpdfium gets a `Path`; the
temp file auto-deletes on close.
Twelve tests, all in-memory fixtures generated with PDFBox at test time
— no committed binary blobs.
## 2. PAYG data model (under `payg.*`)
JPA entities, repositories, and a Flyway migration covering the full
schema in §6 of the design.
**Enums** (`payg.model`):
`JobSource`, `ProcessType`, `JobStatus`, `JobStepStatus`,
`ArtifactKind`, `LedgerEntryType`, `LedgerBucket`, `ReferenceType`,
`EntitlementState`, `FeatureSet`, `FeatureGate`, `WalletEngine`,
`CapPeriod`, `AutoGroupStrategy`.
**Entities + repositories:**
| Entity | Table | Notes |
|---|---|---|
| `PricingPolicy` | `pricing_policy` | Promoted from a record.
`stepLimits` is `Map<JobSource, Integer>` persisted via normalised child
table `pricing_policy_step_limit`. `stripePriceIds` is `Set<String>`
persisted via `pricing_policy_stripe_price` — currency comes from
`stripe.prices` via Sync Engine, not stored locally. |
| `ProcessingJob` | `processing_job` | UUID PK. Tracks lineage window
via `step_count` and `last_step_at`. |
| `ProcessingJobStep` | `processing_job_step` | Per-tool-call audit. |
| `JobArtifactHash` | `job_artifact_hash` | Composite key `(job_id,
content_hash, kind)`. `content_hash VARCHAR(128)` so multiple signature
schemes coexist as `"type:value"` storage keys. Lineage detector queries
this. |
| `WalletLedgerEntry` | `wallet_ledger` | Append-only, signed
`amount_units`. Two unique indexes kill double-posting. |
| `WalletPolicy` | `wallet_policy` | Per-team engine + cap + degradation
rules + lineage strategy. No `@Version` — admin-only writes (documented
in javadoc). |
| `WalletEntitlementSnapshot` | `wallet_entitlement_snapshot` |
Composite key `(team_id, user_id)`; `user_id = 0` is the team-wide
sentinel. No `@Version` — full-row recompute via
`EntitlementService.recompute` (documented in javadoc). |
| `PaygShadowCharge` | `payg_shadow_charge` | Per-job diff while in
`PAYG_SHADOW` engine mode. |
| `PaygTeamExtensions` | `payg_team_extensions` | Sidecar 1:1 with
`teams` carrying `pricing_policy_id` (per-team override) +
`stripe_customer_id`. Sidecar pattern (mirrors `saas_team_extensions`)
so OSS Hibernate ddl-auto never sees PAYG columns on `teams`. |
**Column adds:**
- `team_memberships.cap_units` (optional per-member sub-cap)
**Width split (intentional, documented in V11):** per-row deltas
(`wallet_ledger.amount_units`, `processing_job.charged_units`) are
`INTEGER` because no single charge realistically approaches 2B units.
Cap and period-rollup columns (`team_memberships.cap_units`,
`wallet_policy.cap_units`,
`wallet_entitlement_snapshot.period_spend_units / period_cap_units`) are
`BIGINT` because they accumulate across a billing period and admins may
legitimately set headroom-cap values into the millions.
**JPA wiring:** `SaasJpaConfig` was updated to include
`stirling.software.saas.payg.repository` in
`@EnableJpaRepositories.basePackages` and `stirling.software.saas.payg`
in `@EntityScan` (covers `payg.policy` / `payg.job` / `payg.wallet` /
`payg.entitlement` / `payg.shadow` recursively). New
`SaasJpaConfigScanTest` reads the annotations reflectively and asserts
every expected package is wired — catches the next time someone adds a
new sub-package without updating the scan paths.
**Migration:** `V11__saas_payg_model.sql` (purely additive).
Schema-equivalent to the Supabase migration in the companion PR —
including the `VARCHAR(128) content_hash` width that's needed for the
multi-signature-scheme storage encoding the lineage layer uses.
## 3. Smoke tests
`PaygEntitiesSmokeTest` exercises each entity via the no-arg ctor JPA
requires, plus getter/setter round-trips and composite-key equality —
catches Lombok/annotation regressions without needing a database.
Real-DB integration coverage lands alongside the services that consume
each entity.
## Why this is safe to land now
- All schema changes are additive — no existing rows modified, no
columns dropped.
- The entities are not yet referenced from any production code path;
they exist for the next PRs to build on.
- The v3 Supabase dev branch picks up the schema via the companion PR;
the main repo's Flyway migration applies the same shape when an instance
boots against a freshly-migrated v3 database.
## Open decisions made
- **Step-limits keyed by `JobSource`** rather than by `ProcessType`.
Captures the "self-hosted gets a different knob" framing in earlier
feedback. Trivially overridable per pricing policy version.
- **Step limits + Stripe price IDs normalised into child tables** rather
than JSONB on `pricing_policy` (per Connor's review on #296). Typed
columns, queryable directly, no JSON parsing.
- **Currency dropped from `pricing_policy_stripe_price`** — it lives on
`stripe.prices.currency` and is resolved via Sync Engine. App is
currency-blind.
## Rollback
Straight `git revert` on this PR. The Supabase migration in #296 is
additive and can be left in place safely — the running app ignores
tables it doesn't reference.
---
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [x] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md)
- [x] I have performed a self-review of my own code
- [x] My changes generate no new warnings
- [x] I have run `task check` (via `./gradlew :saas:test` with
`ENABLE_SAAS=true`) — passes
# Description of Changes
Set CI backend & engine comments to auto-delete once the CI has passed.
Also redesign the engine CI to call `task engine:check` like it should
have been, and make it post a comment when the tool models need to be
updated.
Also makes the comment wording more consistent between the three
languages.
# Description of Changes
Two narrowly-scoped hardening changes to the credits engine.
## 1. CreditService — move Stripe meter call to `afterCommit`
The Stripe metered-usage call sits inside the surrounding
`@Transactional`, holding the `user_credits` row lock for the duration
of an HTTP round-trip to Supabase. Under load this starves concurrent
debits; a transient Stripe blip rolls back a (correct) free-credit
consumption and forces the caller to retry.
The Stripe call now runs in a `TransactionSynchronization.afterCommit`
hook — DB commits first, Stripe fires immediately after. If Stripe fails
after commit, we log + increment a new `credits.stripe_report.failures`
counter; the idempotency key is stable, so a manual replay recovers
without double-charging.
Applied to both `consumeCreditBySupabaseId` and
`consumeCreditWithWaterfall`.
**Dead-code removed:**
- Unreachable UUID fallback for MDC `requestId` — `CorrelationIdFilter`
already guarantees the key on every request.
- The `"Unable to report usage to Stripe"` `RuntimeException` and its
catch block — the afterCommit refactor eliminates the throw path.
- `StripeRollbackOnFailureTest` — pinned the rollback-on-Stripe-fail
behaviour this refactor replaces.
## 2. `@AutoJobPostMapping` — build-time lint for `resourceWeight`
`UnifiedCreditInterceptor` multiplies `resourceWeight` into the per-call
charge. An endpoint that falls through to the annotation default
produces a charge derived from a value nobody chose.
- Annotation default flipped from `1` to `Integer.MIN_VALUE` (sentinel).
Both runtime readers (`UnifiedCreditInterceptor`, `AutoJobAspect`)
already clamp into `[1, 100]` so behaviour is unchanged.
- New `AutoJobPostMappingWeightTest` scans the classpath and fails the
build if any method leaves the sentinel.
- Initial run caught 11 endpoints relying on the default. Explicit
weights now declared, chosen by comparing to peer endpoints:
- `EditTextController` — LARGE
- `EmailController#sendEmailWithAttachment` — SMALL
- `ConvertPDFToMarkdown` — MEDIUM
- `AttachmentController` (extract/list/rename/delete) — SMALL × 4
- `ConvertImgPDFController` (cbr/cbz ↔ pdf) — MEDIUM × 2, LARGE × 2
## Tests
- `StripeUsageIdempotencyKeyTest` — pins the `(supabaseId, overage,
requestId)` idempotency key shape so Stripe always dedupes a retry.
- `StripeAfterCommitOrderingTest` — pins that `afterCommit` fires after
commit and NOT on rollback.
- `AutoJobPostMappingWeightTest` — the lint itself, plus a self-check
that the classpath scan finds at least 10 `@AutoJobPostMapping` methods
(guards against the lint passing vacuously).
Build verified: `ENABLE_SAAS=true ./gradlew :stirling-pdf:test
:saas:test`.
---
## Checklist
### General
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [x] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable) — no translation changes
- [x] I have performed a self-review of my own code
- [x] My changes generate no new warnings
### Documentation
- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
— internal-billing change, no public docs impact
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags)
— N/A
### Translations (if applicable)
- [ ] Not applicable
### UI Changes (if applicable)
- [ ] Not applicable
### Testing (if applicable)
- [x] I have run `task check` (via `./gradlew :stirling-pdf:test
:saas:test` with `ENABLE_SAAS=true`) — passes
- [x] I have tested my changes locally
## Summary
Regression from #6404 (Restructure/frontend editor). Two CI workflows
copy the built installers to the wrong directory, so installer artifacts
(MSI / DMG / DEB / RPM / AppImage) silently vanish:
- **`tauri-build.yml`** (PR/desktop smoke builds) - uploads zero
installer artifacts.
- **`multiOSReleases.yml`** (production releases) - the empty artifacts
are downloaded by `create-release` and fed to `action-gh-release`, so a
release would publish **only the JARs, no desktop installers**.
## Root cause
#6404 moved the Tauri project from `frontend/` to `frontend/editor/` and
updated every **absolute** path (`projectPath`, `cd`, `Get-ChildItem`)
to add the `editor/` segment - but left the **relative** copy targets
`../../../dist`. Those resolve against the (now one level deeper)
working dir after `cd ./frontend/editor/src-tauri/target`:
| | resolves to |
|---|---|
| before #6404 (`frontend/src-tauri/target`) | repo-root `dist/` ✅ |
| after #6404 (`frontend/editor/src-tauri/target`) | `frontend/dist/` ❌
(missing) |
The `cp` fails, repo-root `dist/` (from `mkdir -p ./dist`) stays empty,
and the upload finds nothing. `find -exec cp` failing is non-fatal, so
jobs still report success - that's why it went unnoticed. No release has
shipped broken yet: the last release (v2.11.0, 2026-05-19) predates
#6404 (2026-05-22).
## Fix
Copy to an absolute `$GITHUB_WORKSPACE/dist` in both workflows so the
`cd` can't drift the destination again. This matches where the upload /
signature-verify steps already read from.
## Evidence (run 26574078559, all 3 OS legs)
```
cp: cannot create regular file '../../../dist/Stirling-PDF-windows-x86_64.msi': No such file or directory
##[warning]No files were found with the provided path: ./dist/*. No artifacts will be uploaded.
```
The Tauri builds themselves succeeded - only the copy/upload was broken.
## Test plan
- [ ] `tauri-build` on this PR uploads non-empty `Stirling-PDF-<name>`
artifacts on Windows/macOS/Linux.
- [ ] Next release (or a `workflow_dispatch` of multiOSReleases)
attaches MSI/DMG/DEB/RPM/AppImage to the release.
# Description of Changes
#6402 introduced a Rust test `refresh_token_fallback.rs`, but it wasn't
moved properly after the restructure of the `frontend/` folder in #6404.
This PR moves the file to the right place, and also hooks up Task and CI
rules for `cargo test` since nothing was actually running the test in
the first place.
# Description of Changes
Various fixes and improvements I made while testing the SaaS code:
- Changes the new `.env.saas` file to live in `app/` and match the
semantics of the other `.env` files
- Adds top-level `task dev:saas` command to spawn SaaS frontend &
backend
- Deletes dead SaaS code and improves some overriding logic
- Fixes refreshing issue when coming back to the tab
- Fix the Compare tool's selection logic
- Make Compare handle error cases properly
- Fixes the location of the "Dismiss All Errors" button (was rendering
on top of the top-bar with a transparent background previously so it
looked rubbish)
- Fixes file selection in PDF Editor
# Description of Changes
Adds a cancel button to the AI chat to allow the user to abort
long-running AI tasks. Just disconnects the SSE stream (all the backend
code already interrupts when it notices the stream is dead).
# Description of Changes
## What & why
Customers using ADFS (or any generic OIDC provider that doesn't emit
`email`) hit `Attribute value for 'email' cannot be null` during OAuth2
login with no visibility into what claims the provider actually sent.
The only available remedy was guessing at
`security.oauth2.useAsUsername` until something worked.
This PR adds a new opt-in `security.oauth2.debugLogging` flag (default
`false`). When enabled, `CustomOAuth2UserService` logs:
- All ID token claims (sorted, with values)
- All UserInfo endpoint claims (if any)
- The merged attribute key set Spring exposes to `getAttribute()`
- The value the configured `useAsUsername` actually resolved to
- A **`Hint:`** line listing the claim keys present in the token that
map to a valid `UsernameAttribute` enum value — i.e. exactly what the
operator could put in `useAsUsername` to make login work
Logged at `INFO` on the success path and `ERROR` on failure (inside the
existing `catch (IllegalArgumentException)` block that throws
`OAuth2AuthenticationException`). The block is wrapped with a `[OAUTH2
DEBUG] ... [/OAUTH2 DEBUG]` banner and ends with a PII warning so
operators don't leave it on in production.
Default off → zero observable change for anyone not actively
troubleshooting.
## Files changed
| File | Why |
|---|---|
| `app/common/.../ApplicationProperties.java` | New `debugLogging` field
on the `OAUTH2` config class with javadoc warning about PII |
| `app/core/src/main/resources/settings.yml.template` | Documents
`oauth2.debugLogging` so it appears on next startup |
| `app/proprietary/.../security/service/CustomOAuth2UserService.java` |
Emits the claim dump + suggestion hint when the flag is on |
|
`app/proprietary/.../security/service/CustomOAuth2UserServiceDebugLoggingTest.java`
(new) | Unit test: mocks the OIDC delegate, asserts off-path is silent
and on-path emits the dump with the right Hint contents |
## End-to-end verification
Ran the bundled `testing/compose/docker-compose-keycloak-oauth.yml`
Keycloak realm, configured `security.oauth2.useAsUsername: mail`
(Keycloak emits `email`, not `mail`) and `provider: demarest` (matches
the original customer bug report). Triggered the OAuth flow at
`http://localhost:8080/oauth2/authorization/demarest` and confirmed:
- The ERROR-level dump fires with the full 19-claim ID token decoded
- `-- Value at 'mail' : <NULL — this is why login fails>` correctly
identifies the missing claim
- `-- Hint:` correctly suggests `[email, family_name, given_name,
preferred_username]` (the four keys present that map to valid
`UsernameAttribute` values)
- Auth still fails with the original `OAuth2AuthenticationException` —
no change to control flow, just added diagnostic logging
Unit test (`CustomOAuth2UserServiceDebugLoggingTest`) covers both
branches.
## Reviewer notes
- **No new public APIs.** The flag is config-only; no servlet endpoints
exposed.
- **PII is logged when the flag is on.** This is the whole point —
operators need to see the claims to fix their config — but it's gated,
defaults off, and the dump self-documents with a `WARNING: ... Set
security.oauth2.debugLogging=false once troubleshooting is complete.`
footer.
- **Why log everything, not just sub/email?** Because the operator
doesn't know in advance which claim they actually want. ADFS uses `upn`
in some configs and `preferred_username` in others; Azure AD uses `oid`;
the customer here had neither. Dumping the full set is the only way to
make the diagnostic self-service.
- **Out of scope for this PR (follow-ups):**
- The `UsernameAttribute` enum doesn't include `upn` / `unique_name`
(common ADFS claims). If the customer's token only has `upn`, the Hint
will be empty even though the operator can see `upn` in the dump. Worth
a separate PR to extend the enum.
- The known-provider validator in `Provider.java` (rejects e.g.
`useAsUsername: mail` for `provider: keycloak` at startup) bypasses our
diagnostic for those provider names. ADFS customers using `provider:
<name>` fall into the `default` branch so are not affected — but it's a
sharp edge worth documenting.
---
## Checklist
### General
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [x] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable) — N/A, backend-only change
- [x] I have performed a self-review of my own code
- [x] My changes generate no new warnings
### Documentation
- [ ] Doc-repo update (if functionality has heavily changed) —
diagnostic flag is self-documenting via the `settings.yml.template`
comment and the in-log warning; happy to add a doc-repo entry if
reviewers want one
- [ ] Translation tags — N/A
### UI Changes (if applicable)
- [ ] N/A — backend-only
### Testing (if applicable)
- [x] Unit test added (`CustomOAuth2UserServiceDebugLoggingTest`)
covering on/off paths and Hint correctness
- [x] End-to-end verified locally against bundled Keycloak compose with
intentionally misconfigured `useAsUsername`
- [x] Full `:proprietary:test` suite passes
Bumps the pip group with 1 update in the /testing/cucumber directory:
[idna](https://github.com/kjd/idna).
Updates `idna` from 3.12 to 3.15
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/kjd/idna/blob/master/HISTORY.md">idna's
changelog</a>.</em></p>
<blockquote>
<h2>3.15 (2026-05-12)</h2>
<ul>
<li>Enforce DNS-length cap on individual labels early in
<code>check_label</code>,
short-circuiting contextual-rule processing for oversized input
while staying compatible with UTS 46 usage.</li>
<li>Tidy core helpers: hoist bidi category sets to module-level
frozensets (avoiding per-codepoint list construction), simplify
length checks, and reuse the shared <code>_unicode_dots_re</code> from
<code>idna.core</code> in the codec module.</li>
<li>Use <code>raise ... from err</code> for proper exception chaining
and
switch internal string formatting to f-strings.</li>
<li>Allow <code>flit_core</code> 4.x in the build backend.</li>
<li>Expand the ruff lint set (flake8-bugbear, flake8-simplify,
pyupgrade, perflint) and apply the surfaced fixes; pin lint CI
to Python 3.14.</li>
<li>Add Dependabot configuration for GitHub Actions.</li>
<li>Convert README and HISTORY from reStructuredText to Markdown.</li>
<li>Reference CVE-2026-45409 for the 3.14 advisory in place of the
initial GHSA identifier.</li>
</ul>
<p>Thanks to Felix Yan, Stan Ulbrych, and metsw24-max for
contributions to this release.</p>
<h2>3.14 (2026-05-10)</h2>
<ul>
<li>Removed opportunity to process long inputs into quadratic
time by rejecting oversize inputs up-front. Closes a bypass
of the CVE-2024-3651 mitigation. [CVE-2026-45409]</li>
</ul>
<p>Thanks to Stan Ulbrych for reporting the issue.</p>
<h2>3.13 (2026-04-22)</h2>
<ul>
<li>Correct classification error for codepoint U+A7F1</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="https://github.com/kjd/idna/commit/af30a092e158181d0b35ac66dfa813788126bdd8"><code>af30a09</code></a>
Release 3.15</li>
<li><a
href="https://github.com/kjd/idna/commit/30314d4628744ca14cf2b5820564e5127a9f86f2"><code>30314d4</code></a>
Pre-release 3.15rc0</li>
<li><a
href="https://github.com/kjd/idna/commit/05d4b219aa9eddc47371fcbd2000f0301016f3e9"><code>05d4b21</code></a>
Merge pull request <a
href="https://redirect.github.com/kjd/idna/issues/237">#237</a> from
kjd/convert-docs-to-markdown</li>
<li><a
href="https://github.com/kjd/idna/commit/2987fdba1962bbb2358399e0084ba062b98a0bee"><code>2987fdb</code></a>
Convert README and HISTORY from reStructuredText to Markdown</li>
<li><a
href="https://github.com/kjd/idna/commit/59fa8002d514bf4a5ce7b58f67b9ec587d53fa9c"><code>59fa800</code></a>
Merge pull request <a
href="https://redirect.github.com/kjd/idna/issues/236">#236</a> from
kjd/dependabot/github_actions/actions-f3e34333ea</li>
<li><a
href="https://github.com/kjd/idna/commit/def69834ced5d4b3c50439d8b99c4c856ec19ca2"><code>def6983</code></a>
Merge branch 'master' into
dependabot/github_actions/actions-f3e34333ea</li>
<li><a
href="https://github.com/kjd/idna/commit/bbd8004a797185d8c56bb555cd5c88fde05e0631"><code>bbd8004</code></a>
Merge pull request <a
href="https://redirect.github.com/kjd/idna/issues/234">#234</a> from
StanFromIreland/patch-1</li>
<li><a
href="https://github.com/kjd/idna/commit/edd07c05024344a6ccb517414ccb36683aee99fc"><code>edd07c0</code></a>
Bump github/codeql-action from 3.35.2 to 4.35.2 in the actions
group</li>
<li><a
href="https://github.com/kjd/idna/commit/5557db030c11bdec50d62aa5f631d705d33ba123"><code>5557db0</code></a>
Merge branch 'master' into patch-1</li>
<li><a
href="https://github.com/kjd/idna/commit/f11746cf4981d25123ef7830d3ee60f07de8ae3d"><code>f11746c</code></a>
Merge pull request <a
href="https://redirect.github.com/kjd/idna/issues/235">#235</a> from
StanFromIreland/patch-2</li>
<li>Additional commits viewable in <a
href="https://github.com/kjd/idna/compare/v3.12...v3.15">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore <dependency name> major version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's major version (unless you unignore this specific
dependency's major version or upgrade to it yourself)
- `@dependabot ignore <dependency name> minor version` will close this
group update PR and stop Dependabot creating any more for the specific
dependency's minor version (unless you unignore this specific
dependency's minor version or upgrade to it yourself)
- `@dependabot ignore <dependency name>` will close this group update PR
and stop Dependabot creating any more for the specific dependency
(unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore <dependency name>` will remove all of the ignore
conditions of the specified dependency
- `@dependabot unignore <dependency name> <ignore condition>` will
remove the ignore condition of the specified dependency and ignore
conditions
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/Stirling-Tools/Stirling-PDF/network/alerts).
</details>
Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Anthony Stirling <[email protected]>
## Summary
Adds a new AI specialist that finds **textual contradictions** across
one or more PDFs — conflicting claims, recommendations, points of view,
contested facts — built entirely in Python on top of the new
`DocumentService` + `ChunkedReasoner` stack from #6314. Replaces the
closed#6304, which was started before #6314 landed and therefore
over-engineered (Java orchestrator, two-round handshake, resume
artifact, discriminated-union lift).
Two commits:
1. **`refactor(engine): extract ChunkedMapper[T] from ChunkedReasoner`**
— pure refactor, public API of ChunkedReasoner unchanged. New
`ChunkedMapper[T: BaseModel]` is a generic parallel-chunk primitive
(slicing, semaphore, time-bounded extraction, cancellation drain,
progress events) that's now a peer to ChunkedReasoner rather than locked
inside it. The compression loop stays on ChunkedReasoner where it
belongs.
2. **`feat(ai): add Contradiction Agent on ChunkedMapper`** — the agent
itself, plus integrations into `PdfReviewAgent` and `PdfQuestionAgent`.
## Architecture
- **Python-only.** No Java code. No `AgentToolId.CONTRADICTION_AGENT`.
No dedicated HTTP endpoint. No resume artifact, no discriminated-union
lift in `contracts/common.py`. Detector runs inside the Python engine
and the Python engine alone.
- **Review path** (`PdfReviewAgent`): a new
`ContradictionIntentClassifier` fires on contradiction-flavoured
prompts; agent runs detection synchronously and emits a single
`EditPlanResponse(steps=[ADD_COMMENTS])`. Single-turn flow — no resume.
- **Question path** (`PdfQuestionAgent`): a new
`ContradictionCapability` joins `RagCapability` and
`WholeDocReaderCapability` in the smart-model toolset, exposing
`find_contradictions(query)`. The smart model picks it from the toolset
alongside `search_knowledge` and `read_full_document`.
## Inside `ContradictionDetector.detect()`
1. `DocumentService.read_pages(file_id)` → ordered `list[Page]`.
2. `ChunkedMapper[_ExtractedClaims].map_pages(...)` — char-budgeted
multi-page slicing; each slice runs the claim-extractor LLM in parallel
under a semaphore.
3. Page-traceability: the extractor returns `_ExtractedClaim.page`
(which `[Page N]` marker the claim came from). The wrapper validates
`page ∈ chunk.pages`; if not, mechanical fallback searches the chunk's
page text for the verbatim quote and reassigns. If still no match, drop
the claim.
4. `Claim.anchor_quality: Literal[\"verbatim\", \"paraphrased\"]` is set
by a substring check against the declared page's text. Verbatim quotes
feed `anchor_text` for snap-to-quote add-comments placement; paraphrased
ones fall back to margin geometry.
5. Subject canonicalisation: ONE fast-model LLM call collapses synonyms
across the document. Fails open to lexical bucketing.
6. Pre-filters: drop identical-quote pairs; drop same-page same-polarity
paraphrases.
7. Per-bucket pair detection in parallel (separate semaphore, cap 5).
Buckets > 12 claims chunk into windows of 12 with overlap 2; pairs
deduped across overlapping windows by frozen `(i, j)` index pair.
8. Summary fast-model call with fallback string on error.
## Prompt-injection hardening
Every prompt that interpolates user-supplied or PDF-extracted text wraps
content in `<user_message>` / `<verdict>` / `<content>` tags with an
explicit SECURITY preamble instructing the model to treat tagged content
as data only.
## Limitations
- **Combined math + contradiction intent**: when both intent classifiers
fire on the same prompt, contradiction takes precedence and the math
intent is silently dropped. Documented in the Review module docstring
and pinned by
`test_review_integration.py::test_contradiction_precedence_over_math`.
- **Cross-window contradiction reach**: within a subject bucket, pairs
more than ~10 claim indices apart in the same chunked window may be
missed by the overlap-2 strategy. Documented in `test_detector.py`.
Acceptable for v1.
## Settings (engine/src/stirling/config/settings.py)
```python
contradiction_detect_concurrency = 5 # per-bucket detector semaphore
contradiction_bucket_chunk_size = 12 # max claims per detector call
contradiction_bucket_chunk_overlap = 2 # overlap for >threshold buckets
```
`chars_per_slice` and extraction concurrency are reused from the
existing `chunked_reasoner_*` settings.
## Test plan
- [x] `uv run pytest tests/ -v` — **245/245 pass** (210 pre-existing +
35 new)
- [x] `uv run ruff check src/ tests/` — clean
- [x] `uv run pyright src/stirling/agents/contradiction/
src/stirling/contracts/contradiction.py` — 0 errors
- [x] `./gradlew :proprietary:test` — green; no Java was touched, but
verified untouched
- [x] Page-traceability tests cover: valid page kept, hallucinated page
dropped, mechanical-reassign on misattribution, anchor-quality verbatim
vs paraphrased
- [x] Review integration: ADD_COMMENTS plan with two paired CommentSpecs
per contradiction; NeedIngestResponse precheck; precedence vs math
intent pinned
- [x] Question integration: all three capabilities wired into
smart-model toolset; `find_contradictions` returns formatted report text
- [x] ChunkedMapper standalone: slicing, multi-chunk ordering, worker
failures, timeouts, cancellation drain, semaphore saturation
- [x] ChunkedReasoner regression: all pre-existing tests pass unchanged
after the internal split
## Relationship to closed#6304#6304 was closed in favour of this PR. The closed PR predated #6314 and
modelled the agent as a Java-orchestrated two-round examine/deliberate
flow with its own HTTP endpoint and a discriminated-union resume
artifact. With #6314 making full ordered page text available to the
engine via `DocumentService.read_pages`, none of that is needed. Net
effect: drop ~600 lines of Java, drop the two-round handshake, drop the
`ToolReportArtifact` lift, while ending up with a more scalable agent
(chunk-based instead of page-based extraction; tested to
ChunkedReasoner-equivalent scale).
ConnorYohandGitHub
James BruntonandGitHub
EthanHealy01andGitHub
Anthony StirlingandGitHub
Saul IfshinandGitHub
LudyandGitHub
Reece BrowneandGitHub
