feat(selfhost): support per-repo model overrides for ollama/openai/anthropic providers

[JSONbored]

Summary

• The per-repo reviewer model override (review.ai_model in .gittensory.yml) was wired end-to-end only for the two CLI-subscription providers (claude-code/codex). createOpenAiCompatibleAi (ollama/openai/openai-compatible) and createAnthropicAi bound their model ONCE at buildProvider() construction time from a global env var, with no per-call override parameter at all.
• Concretely: an operator running Ollama (or a BYOK OpenAI-compatible/Anthropic HTTP provider) across multiple repos had no way to set a stronger/cheaper model per repo the way claude-code/codex operators already could — a review.ai_model.ollama_model (etc.) config entry was silently ignored, with no warning, whenever the active provider wasn't claude-code/codex.
• Extended SelfHostAiModelConfig (packages/gittensory-engine/src/focus-manifest.ts — this type was extracted into the shared engine package; the miner package doesn't consume it, so this is gittensory-review-only) and AiRunOptions (src/selfhost/ai.ts) with ollamaModel/openaiModel/openaiCompatibleModel/anthropicModel, threaded through the full chain: focus-manifest parser → processors.ts → GittensoryAiReviewInput → AiRunCorrelation → runWorkersOpinion's ai.run() call → read per-call inside createOpenAiCompatibleAi/createAnthropicAi's own .run() — mirroring exactly how claudeModel/codexModel already work, at the same repo-override > global-env-var > hardcoded-default priority.
• Also extended the AI-review cache fingerprint (src/review/ai-review-cache-input.ts, version bumped v3→v4 following the file's own established precedent for adding a hashed field) so changing one of these new per-repo overrides correctly invalidates a previously-cached review instead of replaying a decision made under a different model.
• Scoped effort out: the CLI providers' claudeEffort/codexEffort have no equivalent for these HTTP-API providers (no existing effort-shaping mechanism to override — inventing one is a separate, larger feature).
• Left config/examples/gittensory.full.yml's commented ai_model: example block un-updated: that file sits at 65,478/65,536 bytes against MAX_FOCUS_MANIFEST_BYTES, ~58 bytes of margin — nowhere near enough room for 4 new documented keys without trimming unrelated comment text elsewhere in a 65KB shared file. Noting this explicitly rather than silently leaving the example incomplete (a known, pre-existing byte-budget fragility, also flagged in feat(regate-sweep): add opt-in oldest-first ordering mode to selectRegateCandidates #3867 earlier).

Found via a fresh performance/scalability/accuracy hardening audit of the self-host ORB stack. Tracked under #1667.

Scope

• packages/gittensory-engine/src/focus-manifest.ts — type, empty-config, parser, presence-check, serialization
• src/selfhost/ai.ts — AiRunOptions, createOpenAiCompatibleAi (+ new providerName field), createAnthropicAi, buildProvider
• src/services/ai-review.ts — GittensoryAiReviewInput, AiRunCorrelation, construction + spread sites
• src/queue/processors.ts — forward the 4 new fields from the resolved manifest
• src/review/ai-review-cache-input.ts — fingerprint fields + version bump v3→v4
• Tests: focus-manifest.test.ts (parser, all 8 knobs + each new one individually with round-trip), selfhost-ai.test.ts (per-provider override priority + buildProvider end-to-end wiring), ai-review-cache-input.test.ts (fingerprint changes per new field); fixed 2 pre-existing test files whose fixtures/assertions needed updating for the stricter type / bumped cache version

Validation

• npm run typecheck
• npm run test:coverage (full unsharded) — 561 files / 11120 tests passed; changed lines in every touched src/** file fully covered per lcov.info (cross-checked against diff hunks — zero overlap with pre-existing uncovered lines)
• git diff --check clean

Safety

• Absent/null override fields (the default — no .gittensory.yml ai_model.* set) are byte-identical to today: same global-env-var-then-hardcoded-default resolution as before this existed. No secrets; no new credential paths (only the model NAME can be redirected, never the API key/base URL, matching the existing claude/codex override's own scope).

Closes #3902

[superagent-security]

Superagent didn't find any vulnerabilities or security issues in this PR.

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Preview URL	Updated (UTC)
✅ Deployment successful! View logs	gittensory-ui	1e2f0b8	Commit Preview URL Branch Preview URL	Jul 07 2026, 08:02 AM

[loopover-orb]

Warning

🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨🟨

⏸️ Gittensory review result - manual review recommended

_{Review updated: 2026-07-07 08:06:06 UTC}

10 files · 1 AI reviewer · no blockers · readiness 100/100 · CI pending · blocked

⏸️ Suggested Action - Manual Review

• Touches a guarded path — held for manual review: This PR changes guardrail-protected path(s): src/selfhost/ai.ts (matched src/selfhost/**).

Review summary
This PR extends the existing per-repo `review.ai_model` override mechanism (already working for claude-code/codex) to the HTTP-API self-host providers (ollama/openai/openai-compatible/anthropic), threading the four new fields through focus-manifest parsing, `GittensoryAiReviewInput`/`AiRunCorrelation`, `runWorkersOpinion`, and into `createOpenAiCompatibleAi`/`createAnthropicAi`'s per-call model resolution, with a matching v3→v4 cache-fingerprint bump so a changed override invalidates stale cached reviews. The `resolveOpenAiCompatibleRepoOverride` dispatch correctly maps `providerName` to its own override key with no cross-variant leakage (verified by the added test), and the priority order (repo override > construction-time/env model > hardcoded default) mirrors the established claude/codex pattern exactly. Test coverage is thorough across all four new fields at the unit, buildProvider-wiring, cache-fingerprint, and focus-manifest-parse levels.

Nits — 7 non-blocking

• src/selfhost/ai.ts: `resolveOpenAiCompatibleRepoOverride`'s final `else return options.openaiCompatibleModel` implicitly treats any non-ollama/non-openai providerName as openai-compatible — currently safe because the `providerName` param type is a closed union, but worth a comment noting the assumption if that union ever grows.
• src/services/ai-review.ts:286 and similar: the `feat(selfhost): support per-repo model overrides for ollama/openai/anthropic providers #3902` issue-number references in comments are fine as historical breadcrumbs but add no runtime value — not an issue, just flagging per the external brief's magic-number note as a non-concern.
• Effort-shaping (`claudeEffort`/`codexEffort` equivalent) is explicitly scoped out for the HTTP-API providers with a documented rationale — reasonable, but worth confirming operators are told (e.g. in README/config docs) that effort override isn't available for ollama/openai/anthropic to avoid a support question.
• Consider a small lookup object (`{ollama: 'ollamaModel', openai: 'openaiModel', 'openai-compatible': 'openaiCompatibleModel'}`) in `resolveOpenAiCompatibleRepoOverride` instead of the if/else chain for readability parity with similar maps elsewhere in ai.ts.
• The `.gittensory.yml` example/docs (if any exist alongside `review.ai_model.claude_model` etc.) should be updated to list the four new `ollama_model`/`openai_model`/`openai_compatible_model`/`anthropic_model` keys so operators discover them.
• PR author also opened the linked issue — Link an issue that was opened by a different contributor, or provide a rationale for why this self-authored issue represents genuine discovery work.
• Touches a guarded path — held for manual review — A maintainer must review and merge this change.

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewer
Linked issue	✅ Linked	#3902
Related work	✅ No active overlap found	No same-issue or scoped active PR overlap found.
Change scope	✅ 20/20	Low review scope from cached public metadata (1 linked issue).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 51 registered-repo PR(s), 43 merged, 343 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	JSONbored; Gittensor profile; 51 PR(s), 343 issue(s).
Gate result	⚠️ Not blocking	Advisory; not blocking this PR.

Review context

• Author: JSONbored
• Role context: owner (maintainer lane)
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: Python, TypeScript, JavaScript, Ruby, Go, Kotlin, MDX, Shell
• Official Gittensor activity: 51 PR(s), 343 issue(s).
• PR-specific overlap: none found.

Contributor next steps

• Treat this as maintainer-lane context rather than normal contributor-lane activity.

Signal definitions

• Related work = same linked issue, overlapping active PRs, or title/path similarity.
• Change scope = cached public metadata such as size labels, draft state, and review-burden hints.
• Validation posture = whether the PR provides enough public validation/test evidence for maintainer review.
• Contributor workload = public contributor activity and cleanup pressure, not a repo-wide quality failure.
• Contributor context = public GitHub/Gittensor identity context; non-Gittensor status is not a blocker.

_{🟩 Safe / merged · 🟦 Advisory · 🟨 Held for review · 🟥 Blocked / closed}

---

💰 Earn for open-source contributions like this. Gittensor lets GitHub contributors earn for the work they already do — register to start earning →.

Checked by Gittensory, a quiet PR intelligence layer for OSS maintainers.

• Re-run Gittensory review

[codecov]

Codecov Report

❌ Patch coverage is 85.18519% with 4 lines in your changes missing coverage. Please review.
✅ Project coverage is 93.67%. Comparing base (b8a1186) to head (1e2f0b8).
⚠️ Report is 16 commits behind head on main.
✅ All tests successful. No failed tests found.

Files with missing lines	Patch %	Lines
src/services/ai-review.ts	50.00%	0 Missing and 4 partials ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #3965      +/-   ##
==========================================
- Coverage   93.68%   93.67%   -0.01%     
==========================================
  Files         373      373              
  Lines       34895    34919      +24     
  Branches    12768    12791      +23     
==========================================
+ Hits        32692    32712      +20     
  Misses       1584     1584              
- Partials      619      623       +4     

Files with missing lines	Coverage Δ
packages/gittensory-engine/src/focus-manifest.ts	100.00% <100.00%> (ø)
src/queue/processors.ts	94.55% <100.00%> (+<0.01%)	⬆️
src/review/ai-review-cache-input.ts	100.00% <100.00%> (ø)
src/selfhost/ai.ts	98.61% <100.00%> (+0.01%)	⬆️
src/services/ai-review.ts	96.42% <50.00%> (-0.65%)	⬇️

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.