feat: add Keenable as a configurable internet search backend

[ilya-bogin-keenable]

Summary

Adds Keenable as a new internet search backend alongside the existing Bocha / Tavily / Google / Bing / Xinyu retrievers, following the Tavily backend pattern (#1357). Additive and opt-in via INTERNET_SEARCH_BACKEND=keenable; existing backends are untouched.

Keenable is a web search API built for AI agents. Unlike the key-required backends it is keyless by default: with no key it calls the public endpoint (rate-limited), and an optional KEENABLE_API_KEY only lifts the cap.

Files changed

• src/memos/memories/textual/tree_text_memory/retrieve/keenablesearch.py (new): InternetKeenableRetriever. No SDK dependency, a thin requests call. Keyless requests hit /v1/search/public; a configured key switches to /v1/search with an X-API-Key header. Attribution via X-Keenable-Title. Results map into TextualMemoryItem the same way the Tavily retriever does.
• src/memos/configs/internet_retriever.py: KeenableSearchConfig (API key optional) + registration in InternetRetrieverConfigFactory.
• src/memos/memories/textual/tree_text_memory/retrieve/internet_retriever_factory.py: register keenable + constructor branch.
• src/memos/api/config.py: INTERNET_SEARCH_BACKEND=keenable branch (KEENABLE_API_KEY optional).

Testing

• python -m py_compile on all changed files: passes.
• ruff check on all changed files: passes.

[ilya-bogin-keenable]

Hey @bittergreen could you please take a look? Thanks!

[Memtensor-AI]

🤖 Open Code Review

Target: PR #2072
Task: 504091e23c505b41
Base: main
Head: feat/keenable-web-search

✅ OpenCodeReview: No comments generated. Looks good to me.

Generated by cloud-assistant via Open Code Review.

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-33586be3c2b3f89c-20260801031509: 107/107 passed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search

[ilya-bogin-keenable]

Аixed 4 of the 5: jieba is now gated behind require_python_package like the bocha retriever (an English-only install used to fail at construction), empty content is no longer embedded, and GDP/AI are lowercased so they can actually match.

Will not fix for #2. Forwarding the local mode to the API would break the default path: the search endpoint returns 400 for mode: "fast", and fast is the default the caller passes. The API's mode and this method's mode are different things, so I added a comment saying so instead.

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-b3c50e54d556e024-20260804132254: 86/87 passed, 1 failed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-5a6fc0c17e654329-20260805220539: 95/98 passed, 3 failed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-a94f4452ecff66c8-20260807133658: 96/96 passed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search

[ilya-bogin-keenable]

@syzsunshine219 could you merge this one when you have a moment? You seem to be the one landing PRs here, and this has been sitting ready since the 1st.

State: APPROVED by @WeiminLee (2026-08-04, after the last base merge), MERGEABLE against current main, autotest PASSED (5/5, plus 96/96 auto-generated) and open-code-review passed with 4 non-blocking findings. mergeable_state is blocked with no required checks reported, so as far as I can tell nothing is left but the merge itself.

For context, it is 4 files / +342: a keenable internet-search backend mirroring the merged Tavily one, keyless by default (the public endpoint needs no key; KEENABLE_API_KEY only lifts rate limits). Formatting is verified against the repo's pinned ruff==0.11.8 from .pre-commit-config.yaml, not the latest ruff, since the two disagree.

Happy to merge main in again if it drifts.

[ilya-bogin-keenable]

@WeiminLee thanks for the two approvals. This has been review-complete since 2026-08-01 and I want to make sure it is not just waiting on me:

• approved twice by you, reviewDecision: APPROVED still standing across four base merges
• autotest PASSED (5/5, plus the auto-generated suite)
• open-code-review clean, its findings answered and non-blocking
• MERGEABLE against current main, 4 files / +342/-1, additive only

mergeable_state reports blocked with no required checks listed, so as far as I can tell the only thing left is someone with write access clicking merge. Is there a specific person I should ask, or does this wait for a release cycle? (I pinged @syzsunshine219 a couple of days ago on the guess that they are the one landing PRs here.)

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-b90c9e651259700e-20260813203716: 140/140 passed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search

[Memtensor-AI]

✅ Automated Test Results: PASSED

All tests passed (5/5 executed). memos_python_core/changed-python-source: 5/5. Duration: 4s [advisory, non-gating] AI-generated tests on branch test/auto-gen-504091e23c505b41-20260814164055: 173/174 passed, 1 failed — these do NOT affect the PR verdict; review the branch manually.

Branch: feat/keenable-web-search