[email protected]andClaude Opus 4.6 11646d20e6 fix: cost pricing, fire_manual workspace, heartbeat concurrency cap ...

Round 3 review fixes:

- Cost tracking passes None for cost_per_token when model override is
  active, letting CostGuard look up pricing by model name instead of
  using the default provider's rates (serrrfirat).

- fire_manual() now uses per-user workspace, matching spawn_fire()
  pattern (serrrfirat).

- Removed MULTI_TENANT env var — multi-tenant mode is auto-detected
  solely from GATEWAY_USER_TOKENS presence (serrrfirat + Copilot).

- Multi-user heartbeat capped at 8 concurrent tasks to avoid flooding
  the LLM provider (serrrfirat + Copilot).

- Fixed inject_model_override doc comment accuracy (Copilot).

- Added comment explaining multi-tenant notification routing priority
  (Copilot).

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

2026-03-24 12:25:25 -07:00

..

transcription

refactor(llm): move transcription module into src/llm/ (#1559)

2026-03-22 00:25:54 -07:00

anthropic_oauth.rs

fix: staging CI triage — consolidate retry parsing, fix flaky tests, add docs (#1427)

2026-03-19 18:33:15 -07:00

bedrock.rs

fix(llm): add stop_sequences parity for tool completions (#1170)

2026-03-14 13:06:48 -07:00

circuit_breaker.rs

fix: add debug_assert invariant guards to critical code paths (#1312)

2026-03-18 11:34:11 -07:00

CLAUDE.md

feat(llm): add GitHub Copilot as LLM provider (#1512)

2026-03-21 00:02:00 -07:00

codex_auth.rs

feat: Reuse Codex CLI OAuth tokens for ChatGPT backend LLM calls (#693)

2026-03-16 07:43:45 +00:00

codex_chatgpt.rs

feat: Reuse Codex CLI OAuth tokens for ChatGPT backend LLM calls (#693)

2026-03-16 07:43:45 +00:00

codex_test_helpers.rs

fix(safety): escape tool output XML content and remove misleading sanitized attr (#1067)

2026-03-21 20:51:03 -07:00

config.rs

feat(gemini_oauth): full Gemini CLI OAuth integration with Cloud Code API (#1356)

2026-03-21 22:41:44 -07:00

costs.rs

fix(llm): report zero cost for OpenRouter free-tier models (#463) (#613)

2026-03-07 07:10:33 +00:00

error.rs

refactor: make src/llm/ self-contained for crate extraction (#767)

2026-03-09 22:31:17 +00:00

failover.rs

refactor: make src/llm/ self-contained for crate extraction (#767)

2026-03-09 22:31:17 +00:00

gemini_oauth.rs

feat(gemini_oauth): full Gemini CLI OAuth integration with Cloud Code API (#1356)

2026-03-21 22:41:44 -07:00

github_copilot_auth.rs

feat(llm): add GitHub Copilot as LLM provider (#1512)

2026-03-21 00:02:00 -07:00

github_copilot.rs

fix: post-merge review sweep — 8 fixes across security, perf, and correctness (#1550)

2026-03-23 14:50:15 -07:00

image_models.rs

feat: full image support across all channels (#725)

2026-03-09 03:41:27 +00:00

mod.rs

fix: generate Mistral-compatible 9-char alphanumeric tool call IDs (#1242)

2026-03-22 18:07:03 -07:00

models.rs

feat(gemini_oauth): full Gemini CLI OAuth integration with Cloud Code API (#1356)

2026-03-21 22:41:44 -07:00

nearai_chat.rs

feat: chat onboarding and routine advisor (#927)

2026-03-19 22:20:34 -07:00

oauth_helpers.rs

fix(tests): eliminate env mutex poison cascade (#1558)

2026-03-22 14:36:24 -07:00

openai_codex_provider.rs

feat(llm): Add OpenAI Codex (ChatGPT subscription) as LLM provider (#1461)

2026-03-20 08:14:20 -07:00

openai_codex_session.rs

feat(llm): Add OpenAI Codex (ChatGPT subscription) as LLM provider (#1461)

2026-03-20 08:14:20 -07:00

provider.rs

fix: generate Mistral-compatible 9-char alphanumeric tool call IDs (#1242)

2026-03-22 18:07:03 -07:00

reasoning_models.rs

feat: upgrade MiniMax default model to M2.7 (#1357)

2026-03-18 11:34:05 -07:00

reasoning.rs

feat: complete multi-tenant isolation — per-user budgets, model selection, heartbeat cycling

2026-03-23 22:46:59 -07:00

recording.rs

refactor: make src/llm/ self-contained for crate extraction (#767)

2026-03-09 22:31:17 +00:00

registry.rs

feat(llm): add GitHub Copilot as LLM provider (#1512)

2026-03-21 00:02:00 -07:00

response_cache.rs

fix(llm): add stop_sequences parity for tool completions (#1170)

2026-03-14 13:06:48 -07:00

retry.rs

fix: staging CI triage — consolidate retry parsing, fix flaky tests, add docs (#1427)

2026-03-19 18:33:15 -07:00

rig_adapter.rs

fix: cost pricing, fire_manual workspace, heartbeat concurrency cap

2026-03-24 12:25:25 -07:00

session.rs

fix(security): make unsafe env::set_var calls safe with explicit invariants (#968)

2026-03-12 00:59:58 +00:00

smart_routing.rs

fix: eliminate panic paths in production code (#1184)

2026-03-15 03:17:03 +00:00

token_refreshing.rs

feat(llm): Add OpenAI Codex (ChatGPT subscription) as LLM provider (#1461)

2026-03-20 08:14:20 -07:00

vision_models.rs

feat: full image support across all channels (#725)

2026-03-09 03:41:27 +00:00