feat: add OAuth support for OpenAI and Anthropic subscriptions by Shriiii01 · Pull Request #72 · ekailabs/contexto

Shriiii01 · 2026-02-10T18:55:31Z

Adds OAuth support so users can use their existing OpenAI and Anthropic (Claude) subscriptions instead of API keys.

New routes: GET /oauth/:provider/authorize, GET /oauth/:provider/callback, GET /oauth/status, DELETE /oauth/:provider
PKCE-based flow; tokens stored under .ekai/ and refreshed when expired
Chat completions, messages, and responses passthroughs use OAuth tokens when available (fallback to API keys)
Config: OPENAI_OAUTH_CLIENT_ID for OpenAI; Anthropic currently uses placeholder config
.env.example and .gitignore updated

Addresses the OAuth/subscription support you mentioned in the Ollama PR.

- Add OllamaProvider class with OpenAI-compatible API support - Register Ollama in ProviderRegistry with model selection rules - Add Ollama configuration to AppConfig (baseUrl, apiKey, enabled) - Add Ollama to chat_completions_providers_v1.json catalog with 16 popular models - Add ollama.yaml pricing file (free/local models) - Update ProviderName type to include 'ollama' - Add OLLAMA_BASE_URL and OLLAMA_API_KEY to .env.example Ollama runs models locally and exposes an OpenAI-compatible API at http://localhost:11434/v1 by default. Users can configure a custom base URL via OLLAMA_BASE_URL environment variable.

- Added Ollama to responses_providers_v1.json catalog - Created OllamaResponsesPassthrough class implementing Responses API - Registered Ollama in responses-passthrough-registry.ts Ollama supports the OpenResponses API specification at /v1/responses endpoint, providing future-proof support as /chat/completions may be deprecated.

…ider feat: Add Ollama provider support

Shriiii01 · 2026-02-11T12:38:43Z

1)OpenAI OAuth Support:
This is fully implemented according to public documentation (https://platform.openai.com/docs/guides/oauth).
The endpoints (auth.openai.com), scopes (openai.public), and PKCE flow are standard.
It is ready to use immediately by setting the OPENAI_OAUTH_CLIENT_ID environment variable.
2)Anthropic OAuth Support:
The underlying infrastructure (token exchange logic, PKCE security, refresh token handling) is fully implemented and shared with the OpenAI flow, as both follow the OAuth 2.0 standard.
However, since public documentation for Anthropic's OAuth endpoints is limited/beta, the specific URLs (e.g., https://claude.ai/oauth/authorize) and the client_id used in gateway/src/infrastructure/auth/oauth-service.ts are placeholders based on common conventions.
Action Required: You will likely need to update the ANTHROPIC_AUTH_URL, ANTHROPIC_TOKEN_URL, and ANTHROPIC_CLIENT_ID constants with the correct values from your specific Anthropic integration.
Summary: The feature is complete and working for OpenAI. For Anthropic, the heavy lifting (logic/security) is done, but the specific configuration details may need adjustment based on your credentials.

# Conflicts: # gateway/src/infrastructure/config/app-config.ts

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…ntegration Add OpenRouter integration with unified launcher and Docker fixes

Changed 'wait -n' to 'wait' to keep the container running indefinitely instead of exiting when the first service exits. This allows all services (gateway, dashboard, memory, openrouter) to continue running. Fixes issue where container would restart repeatedly with exit code 0.

- Document all 4 services and their ports (gateway, dashboard, memory, openrouter) - Add Docker service control via ENABLE_* environment variables - Clarify OpenRouter integration service runs on port 4010 (not 4006) - Add Docker Compose section with service management instructions - Document Docker restart behavior and service lifecycle

Pass userId to getRecent() in graph visualization overview branch so the knowledge graph respects user selection. Tighten user_scope filters to match exactly (no null fallthrough). Remove unnecessary back arrow from memory page header since memory is the main page.

Add user scope filtering for semantic memories on dashboard

No caller ever passed deduplicate=true, making the opt-in flag dead code. Ingestion was disabled in the OpenRouter proxy due to runaway memory growth from lack of dedup. Now dedup runs unconditionally for all sectors.

With dedup always-on, strengthenFact() is never called. strength is always 1.0, so strengthScore = log(1.0) = 0 — contributing nothing to scoring. Remove from types, scoring, store, and DDL.

Agents can now set a relevancePrompt that gates ingest — an LLM checks if incoming content matches the agent's scope before extraction/embedding. Irrelevant content is rejected early with a reason. Adds GET/PUT single agent endpoints and updates README with new API docs and flow diagram.

Replace silent INSERT OR IGNORE with a strict existence check that throws agent_not_found. Only the default agent is auto-created at init via a private upsertDefaultAgent(). Add routeError helper to router so all catch blocks return 404 on agent_not_found instead of 500.

- New /agents page: agent cards with soul/relevance prompts, per-agent stats (users, episodic, semantic, procedural), edit/create/delete modals - api.ts: add soulMd + relevancePrompt to getAgents() type; add createAgent() and updateAgent() calls - layout.tsx: add global top nav with Memory Vault and Agents links - memory/page.tsx: offset sticky header to top-11 to clear global nav

Dedup, relevance gate, and agents dashboard

Generate standalone package-lock.json files for memory and integrations/openrouter, and switch all runtime stages from npm install --omit=dev to npm ci --omit=dev. This eliminates npm registry calls during Docker builds, fixing intermittent 403 rate-limit failures in CI.

Add sqlite-vec extension to @ekai/memory, replacing the 200-row linear scan + JS cosine similarity with proper ANN indexing via vec0 virtual tables with cosine distance metric. - Add sqlite-vec dependency, load extension on construction - Create vec0 virtual tables (memory_vec, procedural_vec, semantic_vec, reflective_vec) lazily on first embedding - Insert into vec tables alongside main tables on write path - Replace getCandidatesForSector 200-row scan with two-step KNN: ANN query on vec table, then filter via main table - Replace findDuplicate linear scans with vec KNN queries - Update scoreRowPBWM to accept precomputed similarity - Make embedding optional on record types (query results no longer carry full embedding arrays) - Stop selecting embedding in semantic graph traversal queries - Clean up vec tables on delete operations

Embedding is always present on write and never read on query path (similarity is precomputed by sqlite-vec). Graph traversal methods now return Omit<SemanticMemoryRecord, 'embedding'> since they are structural queries that don't select the embedding column.

Add sqlite-vec ANN vector search to @ekai/memory

The standalone memory/package-lock.json was stale after sqlite-vec was added to package.json, causing npm ci to fail in the Docker build.

Regenerate memory lockfile to include sqlite-vec dependency

Lifecycle event logger that registers all 13 OpenClaw hooks via api.registerHook() and appends JSONL entries with safe serialization. Published to npm as @ekai/contexto.

Extract event storage from openclaw plugin into @ekai/store workspace with EventWriter (normalization, safe serialization, per-session JSONL files) and EventReader (session listing, reconstruction with tool call pairing and userId attribution). Includes path-traversal protection, chronological event ordering, and 48 tests.

- Fix durationMs: 0 being overwritten by computed value (falsy check → else-if) - Sync runtime configSchema with manifest (declare dataDir property) - Reorder root build: install first for clean-env safety, store before dependents - Remove redundant double-resolve in reconstructSession - Fix misleading test name for raw ID storage behavior

- Simplify rawAgentId/rawSessionId storage: remove dead !== check since sanitizeId always appends a hash suffix, just check if input is present - Add _error optional field to StoreEvent and AppendInput interfaces to reflect the serialization-failure fallback that appears in JSONL output

Add OpenClaw plugin and JSONL event store

- Resolve .env.example: keep OAuth vars and add upstream service toggles - Keep gateway/ and OAuth implementation (upstream removed gateway)

link to new work https://github.com/ekailabs/contexto

- Resolve README.md: keep archived notice and project description

- Resolve README.md: archived notice and project description - Resolve .env.example: keep ports and OAuth vars, add PORT - Resolve app-config: keep OAuth validation - Accept upstream model_catalog and shared/types

Made-with: Cursor

Shriiii01 and others added 5 commits February 7, 2026 16:54

refactor: Remove comments from Ollama provider files

b22d91d

Merge pull request ekailabs#71 from Shriiii01/feature/add-ollama-prov…

6b37790

…ider feat: Add Ollama provider support

feat: add OAuth support for OpenAI and Anthropic subscriptions

563e727

This was referenced Feb 10, 2026

feat: Add Ollama provider support #71

Merged

Support OAuth authentication in gateway #33

Open

Shriiii01 force-pushed the feature/oauth-support branch from cc9eadf to fd106b9 Compare February 11, 2026 12:24

sm86 and others added 21 commits February 12, 2026 18:47

fix the broken link

ac9c092

Merge branch 'agent-memory'

8d92668

# Conflicts: # gateway/src/infrastructure/config/app-config.ts

open router integration simple version

6e82165

save realtime memory

39e0b3f

npm start only services you need

32ac480

updated build/run scripts

3558a8a

updated env file

886b3ed

fixed config

65bdcdc

add scripts/launcher.js (was untracked due to *.js gitignore)

c325ccf

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

open router allow user keys

caafe2d

fixed docker file and build issues

9592d76

fixed docker image setup

9ab6080

agent centric memory

557d43f

clean up and openrouter integration

ab9434f

added more memory tests - single user mode

d06ebc0

updated rofl links

dc207b8

updated rofl links

2029d86

Merge pull request ekailabs#75 from ekailabs/feat/simple-openrouter-i…

c6073d8

…ntegration Add OpenRouter integration with unified launcher and Docker fixes

updated docker scripts

26b8b3a

sm86 and others added 26 commits February 25, 2026 15:48

Merge pull request ekailabs#91 from ekailabs/user-specific-memory

9c6428d

Add user scope filtering for semantic memories on dashboard

Make deduplication always-on, remove unused deduplicate flag

e29d477

No caller ever passed deduplicate=true, making the opt-in flag dead code. Ingestion was disabled in the OpenRouter proxy due to runaway memory growth from lack of dedup. Now dedup runs unconditionally for all sectors.

Remove dead strength field and strengthenFact()

0a4b5df

With dedup always-on, strengthenFact() is never called. strength is always 1.0, so strengthScore = log(1.0) = 0 — contributing nothing to scoring. Remove from types, scoring, store, and DDL.

Order memory logs: episodic, procedural, then semantic

0ba52f2

Merge pull request ekailabs#92 from ekailabs/dedup-and-filters

5f314b2

Dedup, relevance gate, and agents dashboard

Update README retrieval pipeline and data model for sqlite-vec

853fbf1

Merge pull request ekailabs#93 from ekailabs/vector-database-integration

b6e2741

Add sqlite-vec ANN vector search to @ekai/memory

Regenerate memory lockfile to include sqlite-vec dependency

c489df4

The standalone memory/package-lock.json was stale after sqlite-vec was added to package.json, causing npm ci to fail in the Docker build.

Merge pull request ekailabs#94 from ekailabs/vector-database-integration

f8f5cec

Regenerate memory lockfile to include sqlite-vec dependency

Add @ekai/contexto OpenClaw plugin (v0.1.0)

05d007d

Lifecycle event logger that registers all 13 OpenClaw hooks via api.registerHook() and appends JSONL entries with safe serialization. Published to npm as @ekai/contexto.

Remove _error from AppendInput (writer-internal only)

fc0fa0a

Merge pull request ekailabs#95 from ekailabs/open-claw-plugin

069f436

Add OpenClaw plugin and JSONL event store

Merge upstream/main into feature/oauth-support

bb03f1e

- Resolve .env.example: keep OAuth vars and add upstream service toggles - Keep gateway/ and OAuth implementation (upstream removed gateway)

Update README.md

7b2d69b

link to new work https://github.com/ekailabs/contexto

Merge upstream/main into feature/oauth-support

8806f46

- Resolve README.md: keep archived notice and project description

Merge upstream/main into feature/oauth-support

cb7ed17

- Resolve README.md: archived notice and project description - Resolve .env.example: keep ports and OAuth vars, add PORT - Resolve app-config: keep OAuth validation - Accept upstream model_catalog and shared/types

Shriiii01 force-pushed the feature/oauth-support branch 2 times, most recently from 634c425 to cb7ed17 Compare March 7, 2026 20:46

Shriiii01 added 2 commits March 8, 2026 02:55

Merge origin/main into feature/oauth-support, resolve conflicts

1e061fb

Made-with: Cursor

Fix README to match base branch (resolve merge conflict)

d82ea4f

Made-with: Cursor

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: add OAuth support for OpenAI and Anthropic subscriptions#72

feat: add OAuth support for OpenAI and Anthropic subscriptions#72
Shriiii01 wants to merge 106 commits intoekailabs:mainfrom
Shriiii01:feature/oauth-support

Shriiii01 commented Feb 10, 2026 •

edited

Loading

Uh oh!

Shriiii01 commented Feb 11, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

Shriiii01 commented Feb 10, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Shriiii01 commented Feb 11, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Shriiii01 commented Feb 10, 2026 •

edited

Loading