The source headers, LICENSE files, and license metadata had drifted
apart. Align the entire project to MIT:
- Convert every source-file header to the MIT text across all comment
styles (Go, TS, TSX, JS, MJS, SQL, CSS, GraphQL, shell), including
SPDX-License-Identifier tags
- Set the root and cookie-banner LICENSE files to the MIT text with a
"MIT License" title line
- Switch the package.json license fields, Docker image label, and
cookie-banner README to MIT
- Update docs and the genmodels header generator accordingly
- Normalize copyright lines to a single format
(Copyright (c) <year(s)> Probo Inc <hello@probo.com>.): unify the
hello@getprobo.com and hello@probo.inc emails to hello@probo.com and
the comma-separated years to a hyphenated range
Genuine third-party references are intentionally left untouched: the
Lucide icon attributions (Lucide is ISC) and the trivy dependency
license allowlist.
Signed-off-by: Sacha Al Himdani <sacha@probo.com>
Address PR review feedback: rename the shared string-helper package
from strutil to stringsx to avoid the discouraged util suffix and the
collision with the standard strings package, updating all import paths
and call sites.
Replace the manual wg.Add/wg.Done bookkeeping in the enrichment worker
with wg.Go, which is less error-prone.
Signed-off-by: Émile Ré <emile@probo.com>
The alphanumeric-normalisation helper was duplicated verbatim in the
common-third-party owned-domains resolver and the cookiebanner tracker
mapping worker. Hoist it into a new dependency-free strutil package so
both call sites share one implementation and one test.
Signed-off-by: Émile Ré <emile@probo.com>
The common-third-party enrichment pipeline ran Agent B (compliance
docs), Agent C (owned domains), and the deterministic logo step
sequentially even though, once Agent A resolves the website, the
three depend only on that website and not on each other. Fan them
out across goroutines under a WaitGroup so wall time is the slowest
of the three rather than their sum. Each step builds its own per-run
browser and writes only into its own locals; the shared LLM, HTTP,
and FileManager clients are safe for concurrent use and the database
is untouched until persist. Results merge in a fixed order so
runErrors and log output stay deterministic.
Also replace the single-sentence confidence guidance in the three
agent prompts with an explicit, calibrated rubric tied to evidence
strength, and remind the model that a downstream threshold gates
persistence so it should neither inflate nor deflate its estimates.
Signed-off-by: Émile Ré <emile@probo.com>
Reject oversized logo responses instead of silently truncating them,
which could persist corrupt image bytes as a valid logo.
Tighten ownership substring matching with a length-ratio guard so a
short label root no longer attributes unrelated domains to a vendor.
Render the worker confidence threshold when set to zero by testing
against nil, so an explicit "accept all" value is not dropped by Helm's
falsy-numeric truthiness.
Sanitize and bound per-agent error text before persisting it to the
enrichment metadata column to avoid leaking unbounded internal detail.
Signed-off-by: Émile Ré <emile@probo.com>
Add `proboctl common-third-party reenrich` to re-arm the async
enrichment worker for selected catalog rows, and `stats` to summarize
the catalog by enrichment state and last run status. Rows are selected
verbatim via --id/--slug or across the catalog via
--category/--keyword/--state/--status, gated by --dry-run and --yes.
Extend `list` with --state/--status filters and STATE/STATUS columns,
and `show` with enrichment state, attempts, last run status, error,
per-field provenance, and discovered domains.
Back these with CommonThirdPartyFilter state/status/IDs filters plus
CommonThirdParties.LoadAllIDs and RequestEnrichmentByIDs. The latter
stamps enrichment_requested_at and resets the attempt counter while
preserving the existing payload, so the worker merge keeps curated and
human-edited provenance.
Also simplify exactLabelMatch to use slices.Contains.
Signed-off-by: Émile Ré <emile@probo.com>
When the common-third-party enrichment worker discovers owned domains
for a vendor, tracker patterns that were detected and left unmatched
before those domains were known had nothing to re-trigger them.
Add RequestMappingForUnmappedByInitiatorDomains, a global re-arm that
stamps mapping_requested_at on still-unmapped patterns whose detected
trackers share one of the new domains, and call it from the enrichment
worker's persist step for newly-inserted domains only. The mapping
worker then re-resolves them through its existing domain-overlap path.
Targeting is limited to patterns with no resolved vendor (no org third
party and an absent or unlinked catalog row), so a pattern already
attributed to this or any other vendor is never disturbed.
Signed-off-by: Émile Ré <emile@probo.com>
Add a domain-discovery step to the enrichment pipeline so the catalog's
domain set, previously written only by the curated seed, grows
automatically. A focused agent enumerates the registrable domains a
vendor owns and operates - marketing, product and sub-brand, app, API,
and CDN/asset domains - from links seen while browsing and from web
search, anchored on the website resolved earlier in the run.
A deterministic ownership gate reduces the candidates to eTLD+1 and
keeps only those that clear a strict confidence floor and match the
vendor by domain label. Shared tracker-delivery and CDN infrastructure
is dropped unless the vendor itself is that provider, in which case its
own brand-matching domain passes a stricter exact-label check. The
survivors are upserted into common_third_party_domains in the run's
final transaction and recorded in the enrichment payload, feeding the
tracker-mapping domain step and disambiguation.
Signed-off-by: Émile Ré <emile@probo.com>
Give the company-profile agent (Agent A) the read-only browser toolset
and build it per-run, so it can read footer, imprint, about, and legal
pages and follow a product domain to the corporate one to resolve the
legal name and headquarters address rather than failing cold.
Make the website the hard precondition: when Agent A cannot resolve a
canonical website, skip the compliance-docs agent and logo step instead
of running them blind, which previously produced inconsistent
cross-domain document URLs. Fall back to the catalog display name for
the legal name when nothing better is found, recorded with a distinct
provenance status so a later real find overwrites it.
Rewrite both enrichment prompts in the project's role/task/instructions
XML style, add a domain-consistency rule for document URLs and a
tool-budget directive, and document the prompt style as a rule and guide.
Fix the find_links_matching browser tool, which double-encoded its
pattern and made JSON.parse fail on every keyword, starving any agent
that used it until it hit the turn cap. Salvage output when an agent
exhausts its turn budget while still exploring with a pending structured
output by forcing one final synthesis turn instead of failing outright.
Signed-off-by: Émile Ré <emile@probo.com>
Introduce a poll-based worker that fills the global common_third_parties
catalog (URLs, headquarter address, legal name, certifications, logo)
so each tenant no longer starts from sparse, name-only rows. Enrichment
is requested at row creation by ResolveOrCreateCommonThirdParty; curated
seed rows are not enqueued, to avoid a re-seed storm.
The pipeline uses two specialized agents plus a deterministic logo step.
Agent A (company profile) resolves legal name, headquarter address, and
the canonical website over web search; its website and legal name feed
Agent B and the logo step. Agent B (compliance docs) resolves the legal
document URLs, trust/security/status pages, and certifications using the
browser read-only toolset (gated on ChromeDPAddr) plus web search. The
logo step restores pkg/webinspect as a pure deterministic package and
stores the discovered icon in S3, linked via logo_file_id.
Each agent returns per-field value/confidence/source_url. The worker
writes a column only when confidence clears a configurable threshold and
the field is not externally owned (seed or human), and always records
full per-field provenance in a new enrichment JSONB column so re-runs
fill only gaps and human edits are never clobbered. New bookkeeping
columns (enrichment_requested_at, enrichment, enrichment_attempts) back
the claim queue and stale recovery; agents run outside transactions and
results persist in one final transaction.
The worker is opt-in: it no-ops unless its agent provider is configured.
Signed-off-by: Émile Ré <emile@probo.com>
Trust GraphQL and MCP still exposed presigned URL strings for
trust-center logos while console and connect already serve stable
File.downloadUrl paths. Phase 1 migrates the seven public logo
fields on trust GraphQL and the trust-center file references on MCP
to the shared File type; trust GraphQL NDA stays on fileUrl for a
follow-up.
Trust resolvers load public files through filemanager and map them
with types.NewFile. The trust app Relay queries and components now
read logo.downloadUrl. MCP specification, resolvers, and helpers
are updated in sync, including NDA on MCP where callers already
have file access.
filemanager is split into focused files and its URL surface is
narrowed to GenerateFileURL(file) for stable app URLs and
GeneratePresignedURL for S3 redirects. GetPublicFile remains the
DB entry point when only a file ID is known.
Add trust and MCP e2e coverage for public logo download URLs.
Signed-off-by: Ludovic Vielle <ludovic@probo.com>
The tracker-mapping worker had been reduced to catalog resolution only,
which removed not just the auto-creation of an org ThirdParty but also
the auto-linking of an existing one. Only the creation needed to go: it
raced the load-then-create check and produced duplicate vendors.
Restore the full org ThirdParty resolution (exact common-id link,
sibling direct-link, high-confidence heuristic, and the disambiguation
agent) and remove only the CreateFromCommon branch and its
categorisation gate. When nothing matches, the worker now leaves
third_party_id unset rather than creating a vendor; creation happens
exclusively through the explicit ImportFromCommon action. Drop the
now-dead CreateFromCommon helper and rename match.go to common_match.go.
Fix a latent test bug surfaced by actually running the DB-backed suite
(skipped in CI without Postgres): the heuristic-match candidate lacked
Level 1, so the level-filtered candidate loader excluded it and the old
fallback create masked the miss.
Signed-off-by: Émile Ré <emile@probo.com>
The tracker-mapping worker no longer auto-creates or auto-links org
third parties, so the heuristic ranker, the disambiguation agent, and
the catalog-to-org seeding helpers are dead code.
Delete pkg/thirdparty/match.go (RankCandidates, ScoredCandidate,
LinkToCommon, CreateFromCommon, suffix stripping, score thresholds) and
disambiguation_agent.go, along with their tests. Drop the
ThirdPartyDisambiguation agent slot and the worker's
DisambiguationAgentTimeout from probodconfig, the builder env wiring, and
the builder tests.
Remove the matching helm surface too: the thirdPartyDisambiguation agent
values, the disambiguationAgentTimeout worker tuning, and the
AGENT_THIRD_PARTY_DISAMBIGUATION_* / TRACKER_MAPPING_DISAMBIGUATION_AGENT
_TIMEOUT environment mappings, with a chart changelog note. The probod
config is built from env lookups with defaults, so a lingering value in
an older deployment is simply ignored.
Signed-off-by: Émile Ré <emile@probo.com>
Replace the many-to-many junction table with a direct
parent_third_party_id foreign key on third_parties. Each
sub-third-party now belongs to exactly one parent, making
duplicates across parents independent entities.
Replace the firstLevel boolean with an integer level field
(1 = direct, 2+ = parent level + 1) to support arbitrary
nesting depth.
Remove the createThirdPartyThirdPartyMapping and
deleteThirdPartyThirdPartyMapping mutations, the CLI
link/unlink commands, and the corresponding MCP tools.
Creating a child third party now just requires passing
parentThirdPartyId on the existing createThirdParty mutation.
The frontend walks the parentThirdParty chain to build
display names like "Name (Ancestor1/Ancestor2)" and shows
clickable ancestor links on the detail page.
Signed-off-by: Sacha Al Himdani <sacha@getprobo.com>
The tracker-mapping, common-pattern enrichment, and third-party
disambiguation agents were all built from one shared
TrackerAgentsConfig fed by a single tracker-mapping config slot. That
forced a single AgentTimeout to be reused and patched per worker, and
two unrelated max-turns fields to share one struct.
Split the in-code config into TrackerMappingAgentConfig,
TrackerEnrichmentAgentConfig, and DisambiguationAgentConfig, each with
its own timeout and max-turns, and add dedicated tracker-enrichment and
third-party-disambiguation provider slots (the latter resolving next to
third-party-vetter). Enrichment and disambiguation fall back to the
tracker-mapping slot when their own provider is unset, preserving
single-config deployments.
Drop the shared pkg/agentsbuild package and duplicate its small wiring
into probod and proboctl so the two executables stay decoupled. Wire
the new env vars, builder test coverage, and Helm values.
Signed-off-by: Émile Ré <emile@probo.com>
Each package that exercises the database against a real Postgres
carried its own copy of the connection bootstrap and schema setup.
Those copies had already drifted: some keyed off PROBO_TEST_PG_ADDR
with hardcoded defaults, others off PROBO_TEST_PG_URL, and the
agentrun/coredata suites hand-applied individual agent_runs
migrations to ensure the table existed.
Introduce a single test.PGClient helper that parses PROBO_TEST_PG_URL
(falling back to the local compose database), runs the full coredata
migration set once per process, and skips when no database is
reachable so make test stays a pure unit-test run. Migrate the
agentrun, coredata, cookiebanner, iam, and thirdparty suites onto it
and delete the duplicated helpers so the bootstrap can no longer
diverge.
Signed-off-by: Bryan Frimin <bryan@probo.com>
CommonThirdParty.logoUrl and TrustCenterReference.logoUrl were
returning expiring S3 presigned URLs, which break if cached or
shared past their TTL.
Replace with stable /api/files/v1/{id} application URLs.
file.Service now generates these via baseurl; a new filesign
package owns presigning for the files/v1 HTTP handler that
does the internal redirect.
Signed-off-by: Ludovic Vielle <ludovic@probo.com>
Queue vetting on third_parties with PENDING, PROCESSING,
COMPLETED, and FAILED states. Expose enqueue and status through
GraphQL, MCP, CLI, and n8n, validate vet requests, tune the
worker via config, and poll the detail page while vetting runs.
Signed-off-by: Sacha Al Himdani <sacha@getprobo.com>
Address review feedback on the agent-driven tracker catalog path:
- Return initiator-domain load failures instead of swallowing them,
so the worker retries rather than running the agent on partial
context.
- In the resolver, treat only ErrResourceNotFound as a catalog miss
and propagate genuine name/slug lookup errors.
- Insert the new vendor inside a savepoint and, on the slug
unique-violation race, reload and return the winning row instead of
aborting the caller's transaction.
- Stop seeding common_third_party_domains from observed initiator
domains. They are a co-occurrence signal, not verified ownership,
and writing them into the global cross-tenant catalog pollutes the
domain-based matcher. The curated seed owns that data.
- Warn the mapping agent that observed domains may belong to shared
CDNs, tag managers, or hosting infrastructure rather than the
vendor, so it does not attribute on that basis alone.
- Extract a shared tracker-identification prompt helper and move the
common-pattern identification prompt next to the enrichment agent.
Signed-off-by: Émile Ré <emile@probo.com>
resolveOrCreateCommonThirdParty lived as a package-level helper in the
tracker mapping worker, but the common pattern enrichment worker now
reuses it. Homing shared catalog logic in a mapping-named file made the
enrichment worker quietly depend on the mapping worker's file, and it is
not a mapping concern.
Move it to pkg/thirdparty as exported ResolveOrCreateCommonThirdParty,
decoupled from cookiebanner's TrackerMappingAgentResult (it now takes a
name and category) to avoid an import cycle. It stays a transaction-
scoped free function so both workers compose it into their own tx for
atomicity rather than receiving a service that owns its own connection.
Relocate the catalog dedup DB test alongside it.
Signed-off-by: Émile Ré <emile@probo.com>
The tracker mapping, common-pattern enrichment, and third-party
disambiguation agents default to a small max-tokens budget on the
premise that their final output is tiny structured JSON. On
reasoning models such as the GPT-5 family, reasoning tokens count
against max_tokens, so a small budget is consumed by reasoning and
the JSON is truncated, surfacing as "unexpected end of JSON input".
Raise the defaults to 4096 (1024 -> 4096 for tracker mapping, 512
-> 4096 for disambiguation) to leave headroom for the reasoning
phase. Update the bootstrap builder default, its test, and the
production values example to match.
Signed-off-by: Émile Ré <emile@probo.com>
The tracker-mapping and common-pattern-enrichment workers ran with the
kit/worker defaults (interval 10s, max-concurrency 5 each) and dropped
the resolved per-agent max-tokens/temperature, so up to ten LLM
pipelines could run unbounded on one OpenAI client. The mapping worker
also held a FOR UPDATE transaction across the LLM and Firecrawl calls
while its DB search tools acquired a second pooled connection, risking
pool exhaustion under concurrency.
Plumb max-tokens, temperature, agent timeout, and per-worker max-turns
through TrackerAgentsConfig and DisambiguationConfig into all three
agent builders, replacing the hard-coded constants with config-fed
fields and package fallbacks. Expose worker interval, concurrency,
stale-after, agent timeout, and max-turns as config (env, Helm values,
deployment template) mirroring the evidence-describer pattern, and
apply them at registration.
Refactor Process into deterministic-read, agent (no transaction), and
persist phases so neither the mapping agent nor disambiguation runs
inside an open transaction, removing the row locks held across network
latency and the nested-connection pressure.
Signed-off-by: Émile Ré <emile@probo.com>
When an org third party already has a common_third_party_id set,
LinkToCommon now skips the write instead of overwriting it with a
different catalog ID. This prevents heuristic or agent false
positives from corrupting a previous, more accurate association.
Signed-off-by: Émile Ré <emile@probo.com>
Third parties created by the tracker mapping worker are confirmed
active on the organization's cookie banner, making them first-level
by definition. Also remove unused ptr test helpers.
Signed-off-by: Émile Ré <emile@probo.com>
Manual moves of a non-extension TrackerPattern lacking a ThirdPartyID
now request mapping, which the tracker-mapping worker resolves with a
four-stage pipeline: exact common_third_party_id link, heuristic
ranking, agent disambiguation, and finally CreateFromCommon. Existing
fuzzy-matched org rows are tagged with common_third_party_id so the
next promotion takes the O(1) exact-link path.
The matching primitives live in pkg/thirdparty (RankCandidates,
LinkToCommon, CreateFromCommon, ScoredCandidate, threshold constants)
so the disambiguation agent and the heuristic share one candidate
type. Cookiebanner orchestrates them; cookie-banner-specific concerns
(pattern -> common-pattern -> common-party navigation, the EXTENSION
gate, and structured logs) stay in the worker.
Signed-off-by: Émile Ré <emile@probo.com>
Surface the third-party links carried by tracker patterns (org-scoped
ThirdParty via third_party_id, or global CommonThirdParty via
common_tracker_pattern_id) requires three new batch loaders and two
filter dimensions, all kept inside their owning entity tables to honour
the no-cross-entity-JOIN rule.
* CommonTrackerPatterns gains LoadByIDs and the ID-only
LoadIDsByCommonThirdPartyID helper, which lets callers translate a
common third party into a set of common_tracker_pattern_id values
without ever JOINing against tracker_patterns.
* CommonThirdParties gains LoadByIDs.
* TrackerPatterns gains LoadDistinctThirdPartyIDsByCookieBannerID and
LoadDistinctCommonTrackerPatternIDsByCookieBannerID, used by the
upcoming CookieBanner.linkedThirdParties resolver to enumerate the
third parties referenced in a banner.
* TrackerPatternFilter gains thirdPartyID and commonTrackerPatternIDs
filter dimensions; the GraphQL layer will dispatch a single
thirdPartyId argument to the right one based on the GID entity-type
prefix.
Service-layer wrappers (cookiebanner.GetCommonTrackerPatternsByIDs,
cookiebanner.LoadCommonTrackerPatternIDsByCommonThirdPartyID,
cookiebanner.LoadDistinctThirdPartyIDsByCookieBannerID,
cookiebanner.LoadDistinctCommonTrackerPatternIDsByCookieBannerID, and
thirdparty.GetCommonThirdPartiesByIDs) expose the new loaders to the
console resolvers and dataloaders that follow.
Signed-off-by: Émile Ré <emile@probo.com>
Fetch favicons at import time instead of calling Google's favicon
service per page load. Logos are stored as public files in S3 and
served through the existing /api/files/v1/{id} endpoint.
Signed-off-by: Émile Ré <emile@getprobo.com>
The CreateVendorDialog previously loaded the entire @probo/vendors
JSON bundle client-side and used MiniSearch for fuzzy search. This
replaces it with a GraphQL query against the common_third_parties
database table, searched server-side via ILIKE filtering.
Backend: adds CommonThirdParty GraphQL type, a pkg/thirdparty
service, and a commonThirdParties(name) root query. Frontend:
splits into CommonThirdPartyCombobox (display) and an @inline
fragment read on selection via readInlineData.
Signed-off-by: Émile Ré <emile@getprobo.com>
