- Updated Go version from 1.24 to 1.26.5 in Dockerfile and CI configuration.
- Upgraded various dependencies in go.mod, including AWS SDK and OpenTelemetry packages, to their latest versions for enhanced features and security.
- Refactored Docker client imports from the Docker library to the Moby library for better compatibility with the updated API.
- Adjusted Docker client usage throughout the codebase to align with the new Moby client structure.
- Replaced client.IsErrNotFound with cerrdefs.IsNotFound for consistent error handling across container operations.
- Updated probe image version to alpine:3.23.5.
- Enhanced logging for container removal failures in flow tools, ensuring better traceability of issues.
- Improved context usage in tests for better cancellation handling.
A flow stores the id of its primary container in the database. When that
container is removed outside pentagi the row keeps status 'running', so
Prepare reused a container the daemon no longer knows about and every
terminal call failed with "No such container" until the flow was recreated.
Confirm with the daemon before reusing the stored container and let the
existing remove-and-rebuild path take over when it is gone. An unreachable
daemon is still an error, so a transient failure cannot discard a healthy
container.
ContainerInspect returns a not-found error once a container is gone from
the daemon, and IsContainerRunning wrapped it as an inspection failure, so
callers could not tell a missing container apart from an unreachable
daemon. StopContainer and RemoveContainer already special-case
client.IsErrNotFound; do the same here.
- Added `RenameFlowsProvider` and `ResetFlowsProviderToDefault` methods to the `FlowController` to handle renaming of user-defined providers and resetting to built-in defaults.
- Introduced SQL queries for bulk updating flow and assistant provider names based on user actions, ensuring idempotency and safe retries.
- Enhanced error handling and logging for provider updates, ensuring that flows and assistants remain valid after provider changes.
- Added unit tests to verify the correct behavior of provider renaming and resetting functionalities.
- Introduced a new test case to verify that multiple nil FunctionCall tool calls are correctly removed from the message content, ensuring only relevant text parts are retained.
- Removed the previous test file `newbodypair_reg_test.go` as its functionality is now covered in the updated test suite.
- Renamed the test function to reflect a broader focus on CLI argument guidance rather than specific XSStrike flags.
- Enhanced test descriptions and guidance to cover common AI-agent mistakes, ensuring clarity and tool-agnostic advice.
- Updated the template to remove specific tool references, promoting a more generalized approach to command-line argument handling.
- Updated the API documentation in `docs.go`, `swagger.json`, and `swagger.yaml` to remove the maxLength constraint for password fields, simplifying the validation requirements.
- Added `github.com/docker/go-units` as a direct dependency in `go.mod` to support updated functionality.
- Increased temperature settings for `simple` and `simple_json` models from 0.7 to 1.0 for enhanced variability.
- Changed model references from `gemini-3.5-flash` to `gemini-3.5-flash-lite` for `reflector`, `searcher`, and `enricher`, optimizing for cost and performance.
- Updated `coder`, `installer`, and `pentester` models to `gemini-3.6-flash`, reflecting the latest version with improved pricing and capabilities.
- Revised test report to reflect new model configurations, including updated success rates and average latencies, ensuring accurate performance metrics.
- Enhanced documentation to clarify model descriptions and pricing adjustments for better user understanding.
- Replaced direct error logging calls with a centralized `obs.LogErrorOrCancel` function to ensure consistent logging behavior for errors, particularly in cases of context cancellation.
- Updated various controllers and providers to utilize the new logging method, enhancing maintainability and clarity in error handling.
- Introduced new methods for invalidating subtasks and tasks in the flow and subtask controllers to improve resource management and prevent stale references.
- Enhanced the handling of database errors in task and subtask status updates to treat missing records as completed, ensuring idempotent task shutdowns.
- Added new environment variables `DATABASE_EXTENSIONS_SCHEMA` and `DATABASE_SEARCH_PATH_VIA_OPTIONS` to `.env.example` and `docker-compose.yml` for better management of PostgreSQL schemas in multi-tenant deployments.
- Updated the README and configuration documentation to explain the purpose and usage of the new variables, particularly for setups using Supabase.
- Implemented schema verification and initialization logic in the backend to ensure proper handling of tenant-specific schemas during database connections.
- Enhanced the installer and server settings forms to include the new configuration options, improving user experience and clarity.
- Updated the documentation in `docker.md` to provide a detailed explanation of the explicit capability allow-list used for primary containers, emphasizing the rationale behind the selected capabilities and the deliberate omission of `MKNOD`.
- Revised comments in `client.go` and `tools.go` to reflect the decision against using `no-new-privileges`, clarifying its impact on privilege escalation testing and container security.
- Enhanced the overall clarity and completeness of the capability management section to aid understanding of security measures in the Docker-in-Docker setup.
- Changed the model version from `claude-opus-5` to `claude-opus-4-8` in the configuration file for both generator and refiner.
- Updated the test report to reflect the new model version, including adjustments to success rates and average latencies for the generator and refiner agents.
- Revised overall average latency in the test report to account for the updated model performance.
- Added new environment variables `DOCKER_INSIDE_HOST`, `DOCKER_INSIDE_TLS_VERIFY`, and `DOCKER_INSIDE_CERT_PATH` to facilitate secure Docker access for worker containers.
- Updated `.env.example` and `docker-compose.yml` to reflect these new configurations.
- Enhanced backend logic to support the new Docker settings, ensuring proper isolation and security for worker containers.
- Expanded documentation to clarify the usage and implications of the new Docker access configurations.
- Introduced `TENANT_ID` to namespace resources for multi-instance deployments, preventing collisions in shared services.
- Added new environment variables in `.env.example` and `docker-compose.yml` for Docker daemon configurations (`DOCKER_INSIDE_HOST`, `DOCKER_INSIDE_TLS_VERIFY`, `DOCKER_INSIDE_CERT_PATH`).
- Updated backend logic to handle tenant-specific configurations, ensuring proper isolation of resources across instances.
- Enhanced documentation to clarify the usage and implications of `TENANT_ID` and related Docker settings.
The e2e suite and CI gates could report green without checking anything: the
lint/codegen gate never ran on fork PRs, the codegen freshness check diffed the
wrong range, the sticky comment claimed passes it never read, and several
visual/palette/contrast/a11y gates were written so they could not fail. Closing
those gates then exposed real defects.
**E2E and CI.** New coverage for the assistant lifecycle, flow interrupt, live
panels, tab deep links, the report route and its exports, session expiry, and
uploads/downloads (59 → 125 spec cases). Gates now fail on real regressions:
absolute pixel budget, per-tab panel sweeps, scoped a11y waivers, page-error
assertions. CI runs on `pull_request`, ranges from the PR base, routes comments
by PR identity, and redacts stand secrets from the public artifact.
**Markdown editor.** ~20 round-trip and toolbar fixes: table pipe escaping
(nested lists, Go template pipelines, headerless tables), fence validity,
setext and line-leading escapes, inline code containing a backtick, block
toggles under select-all, controls disabled where the command is unavailable or
a table cell cannot hold the block, theme-aware code surface. Two perf fixes cut
1 MB document load from 69s to 4s.
**Accessibility and UI.** Focus returns to whatever opened a dialog, sheet or
menu; icon-only buttons named; `aria-sort` on table columns; syntax tokens
retuned to clear AA in both themes; a dedicated link token. Detail and settings
pages now distinguish authz denials and partial errors from missing records,
survive background refetches without blanking or discarding unsaved edits, and
stop naming exported PDFs `*.pdf.pdf`.
**Backend.** Passwords capped at the 72 bytes bcrypt can hash (over-long ones
previously 500'd after passing validation); four agent options the GraphQL round
trip silently dropped are carried through; a flow whose worker fails to start is
no longer left in the listing; the Graphiti health check retries before
permanently disabling the client.
---------
Co-authored-by: Sergey Kozyrenko <sirozha_blr@tut.by>
- Added specific error handling for `ErrFlowNotFound` in `PatchAssistant` and `DeleteAssistant` methods, returning a warning-level response when the flow is not found.
- Updated documentation in templates to clarify requirements for `center_node_uuid` in search types, ensuring users understand the necessity of copying UUIDs from prior results.
- Improved JSON schema descriptions for `GraphitiSearchAction` to emphasize the mandatory nature of the `query` field across all search types.
- Introduced new tests to validate handling of empty timeout values and ensure proper parsing of temporal window timestamps, addressing potential production issues.
- Introduced `callWithSetupRetries` function to enhance error resilience during LLM prompt calls, allowing for retries on transient errors with backoff.
- Updated `NewFlowProvider` and `NewAssistantProvider` methods to utilize `callWithSetupRetries` instead of direct calls to `prv.Call`, improving stability in flow and assistant creation.
- Added comprehensive unit tests for `callWithSetupRetries`, covering immediate success, transient error handling, and context cancellation scenarios.
- Enhanced error messages in Graphiti search tools to provide actionable feedback for missing or malformed parameters.
- Updated templates to clarify search type requirements and taxonomy references.
- Updated the `langchaingo` dependency in `go.mod` from version `v0.1.15-0.20260723091023-35da5c0f0620` to `v0.1.14-update.6`.
- Modified the model configurations in `config.yml` and `models.yml` to replace `claude-opus-4-8` with `claude-opus-5` for both the generator and refiner sections.
- Updated the model descriptions and pricing in `models.yml` to reflect the new `claude-opus-5` model and added new models `claude-sonnet-4-6` and `claude-haiku-4-5`.
- Adjusted the test report in `anthropic-report.md` to reflect the updated model names and improved average latencies across various tests.
- Added configuration options for an optional internal analytics engine in `.env.example`, `docker-compose.yml`, and related files.
- Updated documentation to include details about the new internal analytics engine, which scrapes and summarizes pages as a fallback for the web_search tool.
- Enhanced the `ftester` to support testing the new internal engine alongside existing search engines.
- Adjusted various components to integrate the new engine, including configuration forms and validation logic.
This feature allows users to enable a browser-based fallback for analytic queries, enhancing the flexibility of the web search capabilities.
- Added new configuration options in `.vscode/launch.json` for vllm and hcnsec providers.
- Updated `deepinfra.provider.yml` to reflect changes in model configurations and pricing.
- Introduced `hcnsec.provider.yml` with detailed model settings and pricing for HCNSec.
- Adjusted various test reports to reflect updated success rates and latencies for different models.
- Added `edit_file` to the file tool; diffs are parsed and applied in-memory via `github.com/sergi/go-diff`, exported as `tools.ApplyUnifiedDiff`.
- Made the hunk header lenient (position numbers optional) for models that omit them, with fuzzy content-based matching as fallback.
- Tuned `FileAction` field descriptions (layered, minimal-token) to steer models toward including context lines, based on live model testing via `ctester`.
- Added a `file_edit` multi-turn read_file → edit_file test case in `pkg/providers/tester`, using PentAGI's real tool schema, wired into the `advanced` test group.
- Fixed a bug where a single stateful test-case instance was shared across agent types, leaking conversation history and failures between independent runs.
- Extended the mock provider with sequential responses for multi-turn scenarios; added ctester integration tests.
Graphiti transport errors, an empty file path, and an omitted 'action' or
double-encoded 'questions' arg from the LLM all hard-failed the tool chain
and burned retries instead of degrading gracefully. Also: stopTaskTimeout
5s->60s (flow kept running after a false 500), and the routine "cookie
claim invalid" case now logs at Warn instead of Error.
Guards the two-way mapping added with the extra_body field: a JSON object
survives GraphQL→pconfig→GraphQL intact, and an absent one stays nil rather
than becoming an empty map.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The backend already threaded a per-agent `extra_body` map into the LLM request
(pconfig.AgentConfig, openai.WithExtraBody), but it was reachable only from YAML
provisioning — the GraphQL type, the converter, and the settings form all
dropped it. Editing a YAML-provisioned provider through the UI therefore round-
tripped its config and silently stripped extra_body.
Add `extraBody: Map` to AgentConfig / AgentConfigInput, carry it through the
converter in both directions, and give each agent an "Extra Body" JSON field in
the provider form (validated as an object, serialized on load, parsed on save).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Verified against the live /v2/search API: the response envelope only ever
populates data.web for this tool, and sources defaults to ["web"] when
omitted. The sources field carries a string-vs-object shape ambiguity across
the API/SDK/MCP layers (the Firecrawl MCP rejects string sources outright),
so dropping it removes a needless compatibility risk without changing
behaviour.
The summarizer prompt asked the model to 'directly answer the user query'
but never rendered the query — Firecrawl's /v2/search response, unlike
Tavily's, doesn't echo the query back, so it was dropped when adapting the
prompt. Every summarized result (the common path, since scrapeOptions
requests markdown) was therefore a generic page summary instead of a
query-focused one.
Thread the query through search -> parseHTTPResponse -> buildFirecrawlResult
-> getSummarizePrompt and restore the USER QUERY line, matching Tavily.
Add a test asserting the query is present in the prompt.
- Summarizer prompt now uses one-based source IDs (aligned with the numbered
links) and the metadata-fallback title/URL, and truncates each document's
markdown to the same per-result limit as the non-summarized path, so an
oversized or hostile page can't blow up the prompt.
- Reword tool description, searcher prompt and docs to say 'main-content
markdown' since the scrape uses onlyMainContent=true.
- config.md example now uses the real NewFirecrawlTool(...) constructor,
matching the searxng/sploitus entries.
Add Firecrawl as a network search provider alongside Tavily, Perplexity,
Traversaal, SearXNG and the others. Firecrawl's /v2/search endpoint combines
web search with page scraping, returning full-page markdown content for each
result, which the searcher agent summarizes like the other content-rich
engines.
- New firecrawl tool mirrors the Tavily provider layer-for-layer: registry
definition, tool-type mapping, factory wiring in both tool builders, and
ftester executor/args/mocks support.
- Configurable endpoint: FIRECRAWL_API_KEY plus an optional FIRECRAWL_API_URL
(default https://api.firecrawl.dev) so self-hosted Firecrawl instances work.
- Adds 'firecrawl' to the searchengine_type enum (goose migration + models)
and the search-log server model so searches are recorded per engine.
- Installer wizard, .env.example, docker-compose, prompts and docs updated.
The tool is only registered when FIRECRAWL_API_KEY is set, so existing
deployments are unaffected.
Add an explicit reasoning Off to the per-agent config, backed by the langchaingo
tri-state API. Off emits llms.WithReasoningDisabled() (the provider disable wire)
via BuildOptions, and UsesAdaptiveThinking is guarded so Off overrides the
adaptive-only auto-adaptive.
Per-model capability is derived at runtime from llms.ReasoningSupportFor and
surfaced through GraphQL ModelReasoningInfo, so the UI only offers Off where it
actually disables: cannotDisable reports when Off would be rejected (always-on
models) OR a silent no-op (an unclassified default-on model whose disable wire is
omitted), and capability is surfaced for any thinking-capable model (e.g. Gemini,
which declares thinking without a reasoning block). A new
ProviderType.ReasoningProvider() supplies the provider to the resolver.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- demuxExecStdout errors on a header cut short mid-frame (was a silent EOF that
dropped the tail) and surfaces a docker systemerr frame instead of discarding it.
- ftester drains telemetry on exit through the bounded observer.Drain instead of
two unbounded ForceFlush calls, so an unreachable collector can't hang it at exit.
- container-listing failures are sorted for a deterministic skipped-entries preview,
logged per-entry at Debug (the detail is already in the response and the endpoint
is hit on every navigation) with names quoted so control bytes in a hostile
filename can't inject into a log line; corrected the stat-failure comment
(a dangling symlink lstats fine, it doesn't fail).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The truncation slice and the demux stdout byte-cap had no docker-layer tests —
only the handler's Truncated wiring was exercised through the fake, so a
mis-slice or a dropped cap would have gone unnoticed. Extract find-output
parsing into a pure parseFindEntries and take the byte cap as a demuxExecStdout
parameter, then unit-test both boundaries (at cap / cap+1 / over-limit stream).
Also bound how many paths one container-files request may list
(maxContainerListPaths), so the per-path entry cap can't be multiplied by an
attacker-chosen path count into a large fan-out or response body.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The container-listing section still described the removed `ls -1` parse,
`pkg/queue`, and the old `[]container.PathStat` return. Update it to the current
`find -print0` + errgroup fan-out returning `ContainerDirListing{Files, Failures,
Truncated}`. Also remove the stale `WithBlock`/`DefaultDialTimeout` paragraph left
above the non-blocking `grpc.NewClient` test — its own next paragraph already
contradicted it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Container-listing polish on top of the partial-success work:
- A directory whose entries all fail to stat no longer 500s. The find exec
already proved the container alive, so ListContainerDir returns the readable
entries (possibly none) plus the per-entry failures, and the handler serves a
200 partial listing; only a cancelled request or a dir that can't be listed at
all still errors.
- Over the entry cap, list the first page and set a Truncated flag rather than
erroring with end-user copy from the docker layer. The flag flows through to
the Pull dialog, which now warns the user the directory was truncated instead
of silently showing a subset.
- The Pull dialog no longer flashes a skeleton on an in-place refetch (Refresh,
or after a Pull): the listing hook clears its rows only when the path actually
changes, so a same-path reload keeps the current rows under the loading guard.
Tests: an all-entries-failed listing returns 200 with the failures; the
Truncated flag surfaces in the response. Swagger regenerated for the new field.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Three defects on the shutdown and container-listing paths:
- Telemetry drain ran the langfuse and otel sinks serially under one deadline.
langfuse's ForceFlush/Shutdown ignore the caller ctx and block on their own
timeout, so a langfuse outage burned the whole budget and the healthy otel
sink's final batch was never flushed. Add observer.Drain, which flushes then
shuts down each sink in its own goroutine bounded by the deadline; main uses
it, retiring the inline flush-then-shutdown dance.
- The partial-success listing put the raw stat/list error into the 200 body's
Failures[].Message, exposing docker-layer detail (container ids, the daemon
address) that response.Error only reveals under develop mode. Send a generic
message to the client and keep the raw text dev-gated, logged server-side.
- A path read successfully by one query could also appear in Failures when
another query failed on it, order-dependent. Reconcile at assembly: drop any
failure whose path was read successfully, so no path is in both arrays.
Also bound the exec stdout buffered before parsing so a compromised sandbox
can't stream unbounded output into memory.
Tests: Drain delivers a healthy otel sink while a langfuse sink blocks and
returns within its deadline; the listing failure message is dev-gated; a path
never lands in both Files and Failures. Live: unreachable collector -> shutdown
stays bounded (~5s) and exits cleanly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The graceful-shutdown branch only logged "cleaning up resources" and exited
without flushing telemetry, so the last buffered batch was dropped on every
SIGTERM. Drain it, with three corrections:
- main: flush then shut down the observer on shutdown, bounded by a 5s
deadline in a goroutine so an unreachable collector can't stall exit.
Flush must precede Shutdown because the langfuse observer's Shutdown
cancels its context without flushing; its final batch drains only via
ForceFlush while the context is still live.
- observer Flush/Shutdown: drain both the langfuse and otel sinks and join
their errors instead of returning after the first, which skipped the
second sink entirely when both were configured.
- telemetryClient Flush/Shutdown: attempt all three providers and always
close the grpc connection, joining errors, so a stalled provider flush
no longer skips the rest or leaks the connection.
Tests: the langfuse observer test proves Shutdown drops the buffered batch
while ForceFlush drains it to the sink; observer-level tests prove both
sinks drain and errors aggregate. Live: with an unreachable collector,
shutdown stays bounded (~5s) and exits cleanly instead of stalling ~10s.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The startup dial used grpc.WithBlock with a 10s timeout, so a set-but-
unreachable collector stalled main() for up to 10s, and once that dial failed
the client was nil forever — a collector that came up later never connected
without a restart. Switch to grpc.NewClient (non-blocking): startup never
stalls and gRPC re-establishes the connection in the background on its own.
Also build all three exporters before any provider, so the exporter-error
cleanup (closing the connection) happens before any batch/reader goroutine
starts and can't leak one. Drops the deprecated WithBlock/WithReturnConnectionError.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ContainerFiles gained a Failures list when the container listing switched to
partial-success; regenerate the Swagger docs (swag v1.8.7, the pinned version)
so generated clients see the new field.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Dmitry Ng