Issue #310 asks how to provide a Google Vertex AI API key in .env for
Anthropic Claude. PentAGI currently has no dedicated Vertex AI provider
path in code: backend/pkg/config and backend/cmd/installer do not read
VERTEX_API_KEY, GOOGLE_APPLICATION_CREDENTIALS, or any vertex_ai
variable. The supported routes for Claude today are direct Anthropic
(ANTHROPIC_API_KEY / ANTHROPIC_SERVER_URL) and AWS Bedrock (BEDROCK_*).
Document this explicitly so users do not assume a hidden Vertex AI
configuration path exists:
- README.md: add a NOTE callout inside the Anthropic Provider
Configuration section listing the supported routes and pointing
users who need Vertex AI today at the OpenAI-compatible custom LLM
provider path (LLM_SERVER_URL / LLM_SERVER_KEY / LLM_SERVER_MODEL)
fronted by a translating gateway, with a caveat that reliability
depends on the gateway.
- backend/docs/config.md: add a matching Note paragraph under the
Anthropic section that points at the AWS Bedrock and custom LLM
provider sections, and states that no VERTEX_API_KEY or
GOOGLE_APPLICATION_CREDENTIALS variable is wired into provider
initialization today.
Docs-only change. No runtime Go code, no installer behavior, no
generated files, no new environment variables. All env var names cited
in the new text already exist in the current PentAGI .env.example,
backend/pkg/config, and backend/cmd/installer.
- Update model descriptions to reflect V4 1M context window (up to 384K output)
instead of legacy 128K wording in models.yml and README.
- Split Flash and Pro pricing per official DeepSeek API docs:
- deepseek-v4-flash: input 0.14 / output 0.28 / cache_hit 0.0028 per 1M tokens
- deepseek-v4-pro: input 0.435 / output 0.87 / cache_hit 0.003625 per 1M tokens
- Apply per-role price split across all 13 role configs in both the embedded
config.yml and the user-facing examples/configs/deepseek.provider.yml.
- Replace stale "cache pricing is 10% of input cost" claim in the README,
which no longer holds for either V4 model.
- No change to LiteLLM prefix behavior, role-to-model mapping, lifecycle,
queues, GraphQL schema, migrations, frontend, or installer flow.
- README: align supported-models intro with the local convention used
by every other provider section ("Models marked with `*` are used
in default configuration"), so the asterisk on each model ID has a
near-by explanation.
- Installer help (`LLMFormDeepSeekHelp`): swap the legacy
"DeepSeek-Chat" / "DeepSeek-Reasoner" bullets in "Default PentAGI
Models" for the current `deepseek-v4-flash` / `deepseek-v4-pro`
defaults so the wizard guidance matches the bundled config.
No code, schema, or LiteLLM prefix behavior changes.
The DeepSeek provider config still defaulted to the legacy
`deepseek-chat` and `deepseek-reasoner` model names, which the
upstream DeepSeek API has announced for deprecation on 2026-07-24.
A first-run install therefore breaks once the legacy names are
removed.
Swap the defaults to the current DeepSeek V4 family:
- non-thinking roles use `deepseek-v4-flash`
- reasoning-heavy roles use `deepseek-v4-pro`
The change is limited to the embedded `config.yml` / `models.yml`
inside `backend/pkg/providers/deepseek`, the matching example at
`examples/configs/deepseek.provider.yml`, the `DeepSeekAgentModel`
fallback constant in `deepseek.go`, and three doc references
(README.md, backend/docs/config.md, backend/docs/llms_how_to.md)
plus one installer help string in
`backend/cmd/installer/wizard/locale/locale.go`. LiteLLM prefix
behavior is untouched.
- Introduced `EMBEDDING_MAX_TEXT_BYTES` to limit the maximum byte size of text sent to the embedding model.
- Renamed database connection pool settings: `DATABASE_MAX_OPEN_CONNS`, `DATABASE_MAX_IDLE_CONNS`, and `DATABASE_VECTOR_MAX_CONNS` for improved PostgreSQL connection management.
- Updated relevant documentation to reflect these new configuration options and their usage.
- Adjusted various components to utilize the new settings for enhanced performance and resource management.
- Introduced shared connection pooling for PostgreSQL using `*sql.DB` for sqlc and GORM, optimizing resource usage.
- Added new environment variables: `DB_MAX_OPEN_CONNS`, `DB_MAX_IDLE_CONNS`, and `DB_VECTOR_MAX_CONNS` for configurable connection limits.
- Updated documentation to reflect new connection pooling strategy and provide operational commands for monitoring.
- Implemented shared `pgxpool` for pgvector stores to reduce connection overhead and improve performance.
- Adjusted various components to utilize the new connection pooling setup, ensuring efficient database interactions.
Address Copilot review feedback on PR #305: the 'Current Limitations' bullet for the Graphiti integration mixed PentAGI's user-facing .env variables with the container env vars defined in docker-compose-graphiti.yml.
Reword both README.md and backend/docs/config.md to lead with the user-facing OPEN_AI_KEY and OPEN_AI_SERVER_URL .env variables and explicitly note that docker-compose-graphiti.yml maps them into the bundled vxcontrol/graphiti container as OPENAI_API_KEY and OPENAI_BASE_URL. Operators set the .env variables; the container variables are an implementation detail.
Signed-off-by: mason5052 <ehehwnwjs5052@gmail.com>
Address Copilot review feedback on PR #304:
- Clarify the UserFiles template variable produces a <task_files> XML block with <uploads>/<resources> nested sections (matches flowfiles.FileListingForPrompt output).
- Distinguish that uploads/resources mirror to /work/uploads/ and /work/resources/, while container snapshots can originate from arbitrary container paths and are cached only under container/ on the flow side.
- Note that the 255 filename limit is enforced by len(name) <= 255, i.e. byte-length, so it is roughly 255 ASCII characters.
Signed-off-by: mason5052 <ehehwnwjs5052@gmail.com>
The Graphiti container shipped with docker-compose-graphiti.yml only
takes OPENAI_API_KEY and OPEN_AI_SERVER_URL for entity extraction.
PentAGI configures many other LLM providers (Anthropic, Google AI,
AWS Bedrock, DeepSeek, GLM, Kimi, Qwen) for the main flow, but those
credentials are not consumed by Graphiti today. Until that changes,
operators need to plan around an OpenAI-compatible endpoint just for
the knowledge graph.
This commit makes the limitation visible in two surfaces without
changing runtime behavior:
- README.md: Adds a beta callout at the top of the Knowledge Graph
Integration section and a new 'Current Limitations' subsection
covering provider scope, fixed model, independent billing, and the
lack of an in-app graph explorer.
- backend/docs/config.md: Mirrors the beta callout under Graphiti
Knowledge Graph Settings and adds a 'Current Limitations (Beta)'
subsection with the same constraints, so config-focused readers
see the same message.
Both notes explicitly point at the simple fallback: leave
GRAPHITI_ENABLED=false if the deployment cannot reach an
OpenAI-compatible endpoint.
Refs #187
Signed-off-by: mason5052 <ehehwnwjs5052@gmail.com>
Add a How-to subsection that describes the Files tab on a flow page
without restating implementation details. The new section covers:
- The three file sources surfaced in the UI (uploads, resources,
container snapshots) with their exact action labels.
- The on-host layout under {dataDir}/flow-{id}-data/ and the
corresponding container paths /work/uploads and /work/resources.
- Per-file actions (Download, Copy path, Save as resource, Delete)
and the Pull action's disabled state when the container is not
running.
- Automatic injection of uploaded files and attached resources into
agent system prompts via the <UserFiles> block, so users understand
how the assistant sees their files.
- Current limits (300 MB / 1000 files / 2 GB / 255-char names) and
current limitations, including that flow deletion does not yet
archive or remove the flow data directory on disk.
This is a documentation-only change and does not introduce or change
runtime behavior.
Refs #193
Signed-off-by: mason5052 <ehehwnwjs5052@gmail.com>
- Changed default terminal tool timeout from 600 to 1200 seconds.
- Updated related documentation across .env.example, README.md, and config files to reflect the new timeout settings and their constraints.
- Enhanced descriptions in code comments and documentation to clarify timeout behavior, including clamping rules for values outside the accepted range.
- Introduce CONTRIBUTING.md for license compliance guidelines for developers.
- Update Dockerfile to generate license reports for frontend and backend dependencies.
- Add scripts for generating license reports and include them in the Docker build process.
- Create README.md and .gitignore files in the licenses directory for better organization.
- Update go.mod and go.sum to use the latest versions of vxcontrol dependencies.
This enhances the project's compliance with licensing requirements and improves dependency management.
Dmitry Ng