Borehole · Risk register · free tier

chatchat-space/langchain-chatchat

Free reading: not for reliance

49165d6 · 2,471 commits · 523 files
Issued 2026-10-23

Nothing significant. Questions worth asking about Security & Reliability Posture, Observability & Operations.

98 checks ran across 6 assessable dimensions. 1 finding is worth checking first. 17 findings, each with evidence. One dimension cannot be assessed without an acquirer.

What the repository says about itself

1 submodule(s) this survey does not read: chatchat/chatchat/data/knowledge_base/samples/content/wiki .gitmodules:1

Worth checking first

Borehole's proprietary scoring is calibrated across hundreds of repositories. Each finding here reads significant, but its check has not yet held up often enough in that calibration to rate significant on its own. If one holds when someone checks it, it is significant.

05.45 2 workload settings give a container the host

Published under today's rules. The verification code attests to this reading as it was stored. This page differs from it as follows.

Words about people are today's: bands rather than exact shares, dates or day counts, and what the history measured rather than why.
5 findings from checks Borehole's calibration found wrong more often than right are no longer published.
3 findings about one contributor are withheld: one author wrote nearly all of this repository's commits; a buyer of this report reads them.

	Dimension	Rating
01	Architecture & Codebase — including AI provenance	strong
02	Engineering Process & SDLC Maturity	strong
03	Organization & Key-Person Risk	not assessable
04	Product & Engineering Maturity	adequate
05	Security & Reliability Posture	adequate
06	Observability & Operations	adequate
07	Fit with the Acquirer	not assessable

strong adequate significant findings not assessable from a repository

Provenance disclosure does not affect any rating

0% of the code standing today was written in AI-declared commits

0% of lines still in the tree 0 of 2,759,665 0% of lines ever added these differ when early hand-written code has since been replaced

0/2,086 commits declaring an agent

confidence: moderate

5% of non-merge commits carry any trailer at all
low trailer coverage: the convention may not be in consistent use
no widespread author/committer date divergence
deep scan blamed 515 of 523 counted files

58,188 lines excluded as lockfiles, vendored or generated.

This is a lower bound. It counts what the repository declares. Undeclared AI authorship is invisible here, and a single rebase removes the trailers this rests on. Absence of a declaration is absence of disclosure, not absence of AI authorship.

Architecture & Codebase — including AI provenance

01 · strong · ratings ↑

A note that does not affect this rating

01.3

Commit messages are templated rather than written

adequate

41% of commit subjects are exact repeats of another subject, and subject length varies by only 39.1 characters. A log written by someone explaining their reasoning to a future reader does not look like this. The log is therefore weak evidence of intent, whatever the code is like.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

commit-subjects	164× 'Update README.md'
commit-subjects	135× 'Add files via upload'
commit-subjects	80× 'update README.md'

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

An owner's response is removed only when it is unlawful, impersonates someone, publishes personal data or a credential, or is not about the finding. Disagreeing with the report is never a reason. To report a response, or to reach us about one, write to takedown@borehole.dev.

Engineering Process & SDLC Maturity

02 · strong · ratings ↑

A note that does not affect this rating

02.6

Almost no process scaffolding exists in the repository

adequate

Of five ordinary markers — CI workflows, CODEOWNERS, a pull-request template, pre-commit hooks, contribution guidance — 1 is present: CI workflows. Branch protection itself is a GitHub setting rather than a file, so this is a reading of proxies and not of the rules themselves. What it does establish is that the process is not written down anywhere a new engineer would find it.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

process-scaffolding

1 of 5 markers present across 523 tracked files

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Organization & Key-Person Risk

03 · not assessable · ratings ↑

Not rated: one author wrote nearly all of this repository's commits, so a finding about one contributor would be about someone its history all but names; the public report does not carry those, and does not rate this dimension without them. The findings below are what it could still read.

03.27

Regular contributors fell from 15 to 2 in a year

adequate

12 people who committed regularly the year before made no commits in the last year, and 0 new regular contributors arrived. Ask whether the work they did is still covered.

Evidence

regular contributors by year

15 then 2; 12 stopped committing, 0 began

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Product & Engineering Maturity

04 · adequate · ratings ↑

04.19

10% of bug fixes add or change a test

adequate

Of 83 fixes in the last 24 months, 8 touched a test. A fix without the test that would have caught the bug can quietly come back, and the suite never learns from what went wrong.

Evidence

fix commits touching tests

8 of 83

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Security & Reliability Posture

05 · adequate · ratings ↑

05.2

None of the standard security guard rails are configured

adequate

There is no disclosure policy, no automated dependency updates, no named code owners and no pre-commit configuration. None of these is load-bearing on its own. Their collective absence says that security posture here is whatever the current team happens to remember to do, which is not a posture that survives the team changing.

Evidence

guardrail-scan

checked 5 kinds of guard rail across 523 tracked files; 0 present

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.6

1 Dockerfile runs the application as root

adequate

No USER instruction switches away from root, so the process runs with full privileges inside the container. It is a one-line fix and an ordinary expectation, which is why its absence is worth asking about: it usually says more about whether anyone has reviewed the deployment than about this container specifically.

Evidence

no-USER-instruction docker/Dockerfile — runs as root

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.45

2 workload settings give a container the host

adequate worth checking first

2 places in the deployment configuration run a container privileged or in the host's network, process or IPC namespace. A compromise of that container is a compromise of the machine, and most acquirers' security reviews block it. Node agents (network, storage, monitoring) are excluded.

The check that found this reads significant, but it has not yet held up often enough in Borehole's calibration to rate a finding significant on its own. Opening docker/docker-compose.yaml:9 settles it. If it holds when someone checks it, this finding is significant.

Evidence

docker/docker-compose.yaml	`docker/docker-compose.yaml:9` — privileged or host namespace
docker/docker-compose.yaml	`docker/docker-compose.yaml:34` — privileged or host namespace

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.8

Manifest says MIT, licence file says Apache-2.0

adequate

pyproject.toml declares MIT. LICENSE contains the text of Apache-2.0. Package managers and downstream users read the first; auditors and acquirers read the second. One of them is wrong, and until it is settled the terms this code is offered under are genuinely ambiguous.

Evidence

pyproject.toml	`pyproject.toml:6` — declares MIT
LICENSE	`LICENSE` — text of Apache-2.0

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.65

8 advisories against this project in the last 24 months, 1 high or critical

adequate

The newest was published on 2026-10-01. A project that publishes advisories is telling its users about its fixes, and the count and pace say how much security work it carries.

Evidence

CVE-2026-51884	2026-10-01: CVE-2026-51884 (critical): The /knowledge_base/upload_temp_docs temporary document upload endpoint in Langchain Chatchat 0.3.1 is vulnerable to path traversal. By crafting malicious filen
GHSA-jv4p-mhmp-69vw	2026-05-05: GHSA-jv4p-mhmp-69vw (low): Langchain-Chatchat Uses Insufficiently Random Values
GHSA-wmvv-fhm6-w34x	2026-05-05: GHSA-wmvv-fhm6-w34x (low): Langchain-Chatchat Uses a Broken or Risky Cryptographic Algorithm
GHSA-x229-w2j4-h748	2026-05-05: GHSA-x229-w2j4-h748 (low): Langchain-Chatchat has a Race Condition in its OpenAI-Compatible File Upload API
CVE-2026-7844	2026-05-05: CVE-2026-7844 (low): A vulnerability was detected in chatchat-space Langchain-Chatchat up to 0.3.1.3. This vulnerability affects the function files/list_files/retrieve_file/retrieve

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Notes that do not affect this rating

05.25

1 environment file is committed

adequate

libs/chatchat-server/.env is tracked in git. Environment files are where credentials usually live, and committing one usually means nobody decided how secrets reach the running application. Whatever is in it is in the history for good. Check 05.1 says whether it holds anything credential-shaped.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

libs/chatchat-server/.env libs/chatchat-server/.env — committed environment file

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.27

The build runs third-party code it does not pin

adequate

8 third-party CI actions are referenced by a tag or branch rather than a commit, so they run whatever that tag points to on the day. Tags have been moved to malicious commits in real supply-chain attacks, and a piped script is whatever the server returns that minute. Pinning to a commit is the fix, and it is small.

A note that does not affect this rating: notes like it are common in well-run projects.

Evidence

.github/workflows/_release.yml	`.github/workflows/_release.yml:202` — action pinned by tag
.github/workflows/_release.yml	`.github/workflows/_release.yml:249` — action pinned by tag

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.13

5 outbound calls can wait forever

adequate

5 HTTP calls use a client with no timeout (Python `requests` without `timeout=`, or Go's default client). When a dependency slows down, each one holds a worker until the connection gives up, and enough of them take the service down with the dependency.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

libs/chatchat-server/chatchat/server/agent/tools_factory/amap_poi_search.py	`libs/chatchat-server/chatchat/server/agent/tools_factory/amap_poi_search.py:19` — outbound call without a timeout
libs/chatchat-server/chatchat/server/agent/tools_factory/amap_weather.py	`libs/chatchat-server/chatchat/server/agent/tools_factory/amap_weather.py:22` — outbound call without a timeout
libs/chatchat-server/chatchat/server/agent/tools_factory/amap_weather.py	`libs/chatchat-server/chatchat/server/agent/tools_factory/amap_weather.py:37` — outbound call without a timeout

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.20

3 SQL statements built from strings

adequate

3 places in product code build SQL by formatting or joining strings rather than passing parameters. In each, what the code shows going in is a table or column name, a constant, or something the line does not show, not a request's value. Ask whether any value reaches these strings, rather than a parameter.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

libs/chatchat-server/chatchat/server/knowledge_base/kb_service/relyt_kb_service.py	`libs/chatchat-server/chatchat/server/knowledge_base/kb_service/relyt_kb_service.py:33` — SQL built from a string
libs/chatchat-server/chatchat/server/knowledge_base/kb_service/relyt_kb_service.py	`libs/chatchat-server/chatchat/server/knowledge_base/kb_service/relyt_kb_service.py:45` — SQL built from a string
libs/chatchat-server/chatchat/server/knowledge_base/migrate.py	`libs/chatchat-server/chatchat/server/knowledge_base/migrate.py:82` — SQL built from a string

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

05.21

9 shell commands built from strings

adequate

9 places run a command through a shell (`shell=True`, `os.system`, `exec` with a template) rather than passing arguments. Where any part comes from outside, it is command injection. Ask where each one's input comes from.

A note that does not affect this rating: in Borehole's calibration, this check's notes were usually true but overstated.

Evidence

libs/chatchat-server/chatchat/server/llm_api_shutdown.py	`libs/chatchat-server/chatchat/server/llm_api_shutdown.py:31` — command run through a shell
libs/chatchat-server/chatchat/server/llm_api_stale.py	`libs/chatchat-server/chatchat/server/llm_api_stale.py:244` — command run through a shell
libs/chatchat-server/chatchat/server/llm_api_stale.py	`libs/chatchat-server/chatchat/server/llm_api_stale.py:245` — command run through a shell

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Observability & Operations

06 · adequate · ratings ↑

06.1

No telemetry or error reporting is wired in anywhere

adequate

None of 421 readable files references an instrumentation, metrics or error-reporting library. If this system is in production, nobody learns that it broke from the system itself — they learn it from a customer. That is a reliability finding before it is an observability one.

Evidence

telemetry-scan

searched 421 tracked text files for 16 known instrumentation libraries; manifests for metrics, tracing and error-reporting families; locked dependencies for the packages that emit; 0 matched

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

06.2

No structured logging library is in use

adequate

Nothing references a structured logging library. Logs that are written to be read by a person are not searchable by a machine, which means incident response here is proportional to how well someone remembers the codebase rather than to what the tooling can find.

Evidence

logging-scan

searched 421 files for 10 structured logging libraries; 0 matched

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

A note that does not affect this rating

06.9

No error reporter is wired in

adequate

Nothing in the service initialises an error reporter (Sentry, Rollbar, Bugsnag, Honeybadger or an APM agent). An exception in production reaches a person only if someone is reading the logs, which usually means a customer reports it first.

A note that does not affect this rating: notes like it are common in well-run projects.

Evidence

error reporting

no error reporter initialised

Respond to this finding

Your response is published beside the finding, not instead of it. A finding you can argue with is the point — and a wrong one is calibration data we want.

Fit with the Acquirer

07 · not assessable · ratings ↑

Not rated: structurally not assessable from a repository. What a person adds here.

Check it on the running system

13 checks against the running system follow from the findings above: what a buyer's engineer will try, how to run it first, and what to have ready. A paid survey of this repository includes them. See the tiers.

A paid survey of a public repository is also reviewed: a language model reads each finding against the code and withdraws only findings it judges the code contradicts, each listed with its reason. The review is a language model's reading of the findings against the code, and it can be wrong. It never adds a finding, never raises a band, and never removes a finding from a proven check or an advisory that affects the surveyed version.

What a person adds

The survey reads what the repository can show. The code cannot settle these questions, and on them this report states nothing. Each says where its answer lives: your own engineer, the company, or an assessor you choose can settle it. Questions marked measured open with something this repository shows.

Architecture & Codebase — including AI provenance

01 · full coverage

measured No architecture or design document is in the tree, across 383 product files. Where does the design live, and who holds it? Answer lives in: The team01.38
measured The repository pulls code in through git submodules (.gitmodules). A buyer receives pointers, not that code. Can every submodule be fetched without the team's credentials, and who owns each one? Answer lives in: The team and the submodule owners01.35
Is the architecture right for the next three years of the product? Answer lives in: Your architects, with the product roadmap01.39
Were the home-grown components reasonable choices when they were made, and are they now? Answer lives in: The team's reasoning at the time01.40

Engineering Process & SDLC Maturity

02 · high coverage

Is review real or a rubber stamp? Comment depth and time to approve need the pull request history. Answer lives in: The code host's pull request data02.32
Is delivery planned and measured, or heroic? Answer lives in: The issue tracker: backlog, sprint history, estimate accuracy02.38
How are incidents run, reviewed and learned from? Answer lives in: Tickets, chat and postmortems02.37

Organization & Key-Person Risk

03 · partial coverage

Which of the people who wrote this are part of the transaction, and for how long after it? Answer lives in: The deal terms03.29
Is that code finished, or abandoned, and who still knows how it works? Answer lives in: The team03.22
Who mentors whom, and would that survive a departure? Answer lives in: The team; review history only suggests candidates03.28
Can the team grow, and who stands behind the top three contributors? Answer lives in: Recruiting data and the org chart03.30
Is the seniority mix sound, and will pay survive your salary bands? Answer lives in: HR data03.31
Is the pace sustainable? Commit times cannot say: git keeps no reliable local time. Answer lives in: Interviews and on-call history03.14
Does the team want to stay after close? Answer lives in: Interviews03.32
How are decisions made and disagreements resolved? Answer lives in: Time with the team03.33

Product & Engineering Maturity

04 · minimal coverage

measured 59 commits landed in the last year, against 736 the year before (-92%). Is that maintenance mode, a pivot, or fewer people working on it? The count looks the same for all three. Answer lives in: The team04.11
Can this team deliver the stated roadmap on the stated timeline? Answer lives in: The data room and the team's record of estimates04.32
Does leadership know about the debt, and is time budgeted to repay it? Answer lives in: Budget and roadmap decisions04.31
Is the engineering shape consistent with the commercial story? Answer lives in: Revenue, customer and churn data04.33

Security & Reliability Posture

05 · partial coverage

measured No threat model is in the tree of what looks like a running service. Does one exist elsewhere, and who owns it? Answer lives in: The security owner05.43
What has actually broken, how often, and how badly? Answer lives in: Ticketing and chat05.41
What did external testing find, and was it fixed? Answer lives in: Reports in the data room05.42
What is the SOC 2, ISO 27001 or GDPR status, and where is the evidence? Answer lives in: Audit reports; policy files in the tree are not evidence05.44

Observability & Operations

06 · partial coverage

measured Nothing in the tree backs up or restores data. How is data backed up, and has a restore ever been rehearsed? Answer lives in: The operations team06.19
measured No alert rule is defined in the repository. Where are alerts defined, who receives them, and when did one last fire? Answer lives in: The alerting tool and the on-call rota06.10
Are the dashboards opened, the alerts acknowledged and the pages answered? Answer lives in: Pager history and dashboard logs06.29
Are the service-level objectives actually met? Answer lives in: Production metrics06.30
Who carries the pager, and how often does it go off? Answer lives in: Pager exports and interviews06.31
What does it cost to run, and how much headroom is there? Answer lives in: Cloud billing and capacity plans06.32

Fit with the Acquirer

07 · none coverage

Not rated: structurally not assessable from a repository.

This is primarily a Python codebase. Does your engineering organisation already run Python in production, or would this be the first? 07.1
The bulk of this system sits in libs/, markdown_docs/, docker/. Which of your existing systems would each of those have to absorb or replace? 07.10
The repository carries deployment configuration (docker/Dockerfile and 1 more). Does that match your deployment and on-call model, or does it need rehosting first? 07.2
What is your tolerance for the findings above remaining unaddressed for the first two quarters after close, given everything else that will compete for this team's time?
Which of these systems duplicate yours, and which get retired? Answer lives in: Your architecture07.11
What will integration cost, and in what order? Answer lives in: The engagement07.12
Where does the team land in your organisation, and who reports to whom? Answer lives in: Your org design07.13
Are there earn-outs, retention packages or contractor IP to assign? Answer lives in: Deal terms07.14
Do customer contracts limit hosting, regions or vendors? Answer lives in: Customer contracts07.15

Request a human assessment Download JSON Badge PDF

A human assessment is Borehole's own paid service, €12,000+ (total price is determined per engagement; travel billed at cost). It is not independent of this report: the same business produced both. It is a separate contract, with its own scope, terms and reliance.

Embed the badge

Tied to this commit and this date, and it fades after 90 days — an honest badge is one that expires. A repository with significant findings gets a neutral "read" badge rather than a red one: the library is where the range is visible, not someone else's README.

[![Borehole](/badge/chatchat-space/langchain-chatchat.svg "Borehole free reading: not for reliance. See the full report.")](/r/chatchat-space/langchain-chatchat/49165d6)

If you embed it: link it to the report, remove it if the report is delisted, and do not present it as a certification or an endorsement.

Rejection log — 81 signals that ran and did not fire

Appendix: rejection log — 81 signals that ran and did not fire

Published on purpose. A signal that looked and decided not to fire has told you something, and this is the calibration data behind every threshold above.

Looked, and found nothing — 57

Signal	What it found
04.hotspot_concentration	change is spread across the codebase rather than pooling in a few filesfiles 6,836 · top5 share 0.058
04.debt_markers	debt markers are sparsemarkers 34 · per kloc 0.71 · lines read 47,995
04.dependency_sprawl	direct dependency counts are unremarkable
04.churn_trend	rework is not rising against new worklate delete per insert 0.352 · early delete per insert 0.625
04.eol_runtime	every pinned runtime is still supportedeol as of 2026-09-24
04.compat_layers	little code is kept for the old wayshare 0.0 · code files 236 · compat files 0
06.print_logging	raw prints are few, or outnumbered by logger callsprints 110 · logger calls 170
06.correlation_ids	a request can be followed through the logstracing False · request id sites 1
06.usage_reporting_default	the product's code names no reporting hostsettings on 0 · settings off 0
06.deployed_image_floats	every deployed image names a versionimages 2 · floating 0
06.environment_branching	environment differences live in configurationsites 0
06.migrate_on_start	migrations do not run at container start
03.contributor_concentration	withheld: this check's result would describe one person
03.drive_by_contributors	withheld: this check's result would describe one person
03.critical_path_ownership	withheld: this check's result would describe one person
02.merge_discipline	a meaningful share of recent change carries evidence of reviewmerges 144 · window last 24 months · with tracked 2
02.ci_presence	CI configuration is present in the working treecount 7
02.test_presence	tests are present in a normal proportion to sourcetests 31 · source 267 · test ratio 0.116
02.release_cadence	tags are presenttags 31
02.conventional_commits	commit subjects generally carry contentsampled 2,086 · low content share 0.113
02.ci_runs_tests	CI invokes a test runnerconfigs 7 · with tests 3
02.skipped_tests	few tests are switched offfocused 0 · skipped 0 · test files 47
02.ci_test_gating	no test run in CI is written so that it cannot failconfigs 7
02.revert_share	change is rarely undoneshare 0.001 · reverts 1 · recent commits 799
02.flaky_test_markers	tests are not retried until they passtest retries 0 · suite retries 0
02.lint_in_build	a linter or formatter runs in the buildwired 3 · ci configs 7 · product files 236
02.long_lived_branches	the typical branch reaches the trunk quicklyshare 0.079 · merges 63 · long lived 5
02.commit_size	changes arrive in reviewable sizesshare 0.032 · commits 776 · over 2000 lines 25
01.burst_import	no commit run met both the rate and the net-addition thresholdgap seconds 180 · min add ratio 3.0 · min net added 2,000
01.initial_dump	first commit is not a disproportionate share of the codebaseinsertions 221 · share of insertions 0.0
01.oversized_modules	no module is an outlier against this codebase's own normlargest 998 · threshold 1,000 · median lines 33
01.duplicated_blocks	little shipping code is repeated verbatim across filesshare 0.0224 · product files 234 · distinct blocks 17,492
01.swallowed_errors	errors are rarely thrown awayloc 48,380 · files 3 · per kloc 0.06
01.build_reproducibility	every base image names a versionfloating 0 · from lines 1
01.unfinished_migration	no language migration is stalled halfway
01.weights_in_git	no model weights are committedfiles 0
05.committed_secrets	no credential-shaped strings outside test and fixture paths; the only other matches are expired or licence tokens or placeholders, which grant nothingnote the working tree only; the history is 05.5 · patterns 8 · files read 421
05.license_present	a licence file is presentfound True
05.unsafe_deserialization	no code-executing deserialiser in product codesites 0
05.tls_verification_off	no TLS verification is switched off in product codefiles 0 · sites 0 · pinned instead 0
05.credentials_in_deploy_config	deployment configuration references secrets, never holds themfiles 0 · sites 0
05.signing_material	no signing keystore or profile is committedfiles 0
05.license_vendored_unlicensed	no vendored third-party code is committedcomponents 0
05.license_grant_unclear	the licence is recognisable as Apache-2.0class permissive · license Apache-2.0
05.committed_native_libraries	no widely used compiled library is committed to the productlibraries 0
04.api_versions_coexisting	one API version is served, or none
04.deprecations_lingering	few deprecations have outlived two yearsolder than two years 0 · files with deprecations 8
04.dependency_churn	few dependencies were added and dropped within 60 daysdependencies seen 272 · added in two years 195 · removed within 60 days 15
04.ci_platforms_dropped	no platform was dropped from CI in the last two years
04.repository_status	the README's first screen states no end, move or freezestatements 0
02.development_elsewhere	nothing says development happens elsewhereno pr statements 0 · mirror statements 0 · replayed commit share 0.0
05.licence_changes	the root licence has not changed in the history readlicence versions 1 · unreleased changes 0
05.paid_edition	no directory carries a separate paid-edition licencedirectories 0
04.releases_stopped	releases keep pace with developmentmedian gap days 19.5 · days since last tag 833 · commits last 90 days 0
04.release_branch	the newest release was cut from the branch surveyedelsewhere 0 · on branch 31 · tags in window 31
03.single_maintainer	withheld: this check's result would describe one person
05.project_exploited	no affecting advisory is on CISA's Known Exploited listexploited 0

Could not conclude, or did not apply — 24

Not a clean result. Each says why it could not answer here.

Signal	Why
04.fix_share_trend	fewer than six busy quarters to compare
04.schema_churn	no schema migrations to read
04.dependency_redundancy	no JavaScript manifest to read
06.telemetry_depth	none at all is 06.1
06.alert_rules	no alert rules in the repository; they may live in a console
06.probes_identical	no Kubernetes probes
06.single_replica	no Kubernetes deployments
06.release_markers	fewer than 100 commits in the last year
06.feature_flags	no feature-flag service; flags may live elsewhere
03.knowledge_silos	withheld: this check's result would describe one person
03.second_contributor_attrition	withheld: this check's result would describe one person
02.dependency_update_cadence	no lockfile to date
01.notebook_outputs	not a data or machine-learning repository
05.dependency_pinning	no manifest whose pinning can be read without a lockfile
05.migration_reversibility	too few migrations to judge
05.resource_limits	no Kubernetes workload manifests
05.known_vulnerabilities	no lockfile this survey can read, or a collector older than 0.4.0
05.public_env_secret	not a frontend
05.unsafe_html	not a frontend
05.source_maps_shipped	not a frontend
05.cleartext_traffic	not a mobile app
05.dataset_provenance	not a data or machine-learning repository
05.license_copyleft_inherited	no third-party code is committed to this repository, so the licences it depends on are resolved at build time and are not readable here
04.flags_accumulating	few or no feature flags in the history

Anyone can check this report against the authoritative record — click the stamp, or enter K98K-0EDK-M4DP at borehole.dev/verify.

The code commits to the 106 checks this run performed, the bands they produced, and the commit they were read at. It does not cover checks written since.

Put the mark in your README

The image is wrapped in a link to the verification page, so a reader can check it rather than take it on trust. If you embed it: link it to the report, remove it if the report is delisted, and do not present it as a certification or an endorsement.

[![Borehole reading, not a certification](https://borehole.dev/badge/chatchat-space/langchain-chatchat/49165d6.svg "Borehole free reading: not for reliance. See the full report.")](https://borehole.dev/verify/K98K0EDKM4DP?via=badge)

Where this scan ran

This scan ran on ordinary cloud infrastructure (cloud-run), not in a hardware-isolated confidential VM. Nothing about it is attested by Google.

What an attested survey proves, and what it does not.

What this scan did with the repository — 7 steps

Written by the steps themselves as they ran, not described afterwards. A hand-written account of a data flow drifts the first time somebody changes the flow and not the account.

At	Step	Detail
0.0s	read repository metadata from the GitHub API	size mb: 141.1authenticated: False
5.7s	cloned the repository to a temporary directory	depth: full
11.8s	read the git history	commits: 2471tracked files: 523
70.7s	ran the deterministic checks	blame pass: Trueread working tree: False
70.7s	recorded where this scan ran	attested: Falseenvironment: cloud-run
108.9s	kept the facts, never the source, for re-reading under new checks
108.9s	deleting the working copy

Total 108.9s ·source content sent off this machine: none · calls to a language model: 0 · the clone was deleted when the survey ended

An automated reading of a repository's code and its history up to one commit, with public advisory records. It may be wrong, it is not legal, financial, investment or security advice, and it does not replace diligence by a qualified person. It is provided for information: nobody may rely on it (Borehole's terms, section 3).

BOREHOLE 0.7.15 DETERMINISTIC LAYER · NO MODEL CALLSREAD ON BOREHOLE'S SERVER · CLONE DELETED TAKEDOWNCONTRIBUTED TO THIS REPOSITORY? YOUR RIGHTS