Add custom LLM provider configuration

[konard]

Summary

• Adds a shared agent provider configuration schema for local, cloud, and approved custom endpoint LLM providers.
• Validates provider ids, model ids, endpoint protocols, secure credential references, and cloud-provider opt-in through agent settings.
• Exposes provider configuration state/actions in the shared agent settings view and documents privacy behavior.

Issue

Fixes #47

Tests

• npm test
• npm run validate:foundation
• npm run validate:release
• npm run decompose:dry-run
• Manual checks, if relevant: Not applicable; foundation model and documentation change only.

Risk

• Low. This extends foundation settings validation and defaults; no production provider calls or credential resolution are implemented here.

Screenshots or recordings

Not applicable.

Security and privacy

• This PR does not include secrets, production credentials, access tokens, Telegram API hashes, private keys, or private message content.
• Any logs, screenshots, or fixtures are redacted.

[konard]

Solution summary

Implemented and pushed the fix to issue-47-3f55f4d11bb2.

PR 96 is ready for review: #96

What changed:

• Added agent-provider-config foundation schema and validation for local, cloud, and custom-endpoint LLM providers.
• Enforced secure credential references for provider API keys/tokens and explicit cloud opt-in for cloud-capable providers.
• Wired provider config into agent settings and agent settings view state.
• Added tests for provider validation, settings validation, and privacy documentation coverage.
• Updated PRIVACY.md and docs/architecture.md.
• Removed the placeholder .gitkeep.

Verification:

• npm test passed.
• npm run validate:foundation passed.
• npm run validate:release passed.
• npm run decompose:dry-run passed.
• GitHub PR checks are passing.
• Working tree is clean.

---

This summary was automatically extracted from the AI working session output.

[konard]

🤖 Solution Draft Log

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost estimation:

• Model: GPT-5.5
• Provider: OpenAI
• Public pricing estimate: $2.665928

📊 Context and tokens usage:

• 1.5M / 1.1M (146%) input tokens, 11.1K / 130K (9%) output tokens

Total: (70.6K + 1.5M cached) input tokens, 11.1K output tokens, $2.665928 cost

🤖 Models used:

• Tool: OpenAI Codex
• Requested: gpt-5.5
• Model: GPT-5.5 (gpt-5.5)

📎 Log file uploaded as Gist (18326KB)

• View complete solution draft log

---

Now working session is ended, feel free to review and add any feedback on the solution draft.

[konard]

🔄 Auto-restart triggered (iteration 1)

Reason: Merge conflicts detected

Starting new session to address the issues.

---

Auto-restart-until-mergeable mode is active. This run will stop after 5 restart iterations.

[konard]

🔄 Auto-restart-until-mergeable Log (iteration 1)

This log file contains the complete execution trace of the AI solution draft process.

💰 Cost estimation:

• Model: GPT-5.5
• Provider: OpenAI
• Public pricing estimate: $1.630644
• Token usage: 73,220 input, 4,412 output, 699,904 cache read

🤖 Models used:

• Tool: OpenAI Codex
• Requested: gpt-5.5
• Model: GPT-5.5 (gpt-5.5)

📎 Log file uploaded as Gist (24645KB)

• View complete solution draft log

---

Now working session is ended, feel free to review and add any feedback on the solution draft.