feat: intelligent auto-router — routes to fastest/cheapest provider automatically by gnanam1990 · Pull Request #2 · Twigpine/openclaude

gnanam1990 · 2026-04-01T04:49:54Z

What this adds

The Problem

openclaude currently routes ALL requests to ONE fixed provider.
If that provider is slow or down, every request suffers.

The Solution: SmartRouter

smart_router.py ? a drop-in intelligent routing layer that:

?? Benchmarks providers on startup

Pings OpenAI, Gemini, and Ollama to measure real latency before
routing any requests.

?? Scores every provider

Each provider gets a score based on:

Latency ? how fast it responds (measured in real-time)
Cost ? price per 1k tokens (Ollama=free, Gemini=cheap, OpenAI=mid)
Error rate ? providers with failures get penalized

??? Routes intelligently

Short prompts ? small/fast model on best provider
Long prompts ? big model on best provider
Configurable strategy: latency, cost, or balanced

?? Automatic fallback

If a provider fails mid-request, SmartRouter:

Marks it unhealthy
Re-pings it after 60 seconds
Restores it automatically when it recovers

?? Learns from real traffic

Uses exponential moving average to update latency scores
from actual request timings ? gets smarter over time.

Usage

Add to server.py:

from smart_router import SmartRouter
router = SmartRouter()
await router.initialize()

# In your request handler:
decision = await router.route(messages, claude_model)
# decision = { 'provider': 'gemini', 'model': 'gemini-2.5-pro', ... }

# After request completes:
await router.record_result(decision['provider'], success=True, duration_ms=230)

.env config

ROUTER_MODE=smart
ROUTER_STRATEGY=balanced   # latency | cost | balanced
ROUTER_FALLBACK=true

Files

smart_router.py ? full implementation (250 lines)
test_smart_router.py ? 20 unit tests, all passing

Test

pytest test_smart_router.py -v

Contributor: gnanam1990 (PR #3)

…ension Initial VS Code Extension for OpenClaude

boofpackdev · 2026-04-04T22:07:40Z

✅ Build tooling verification complete - all acceptance criteria met:

Verification Results:

✅ bun install completes without errors (695 packages)
✅ bun run build produces clean dist/ output (dist/cli.mjs ~20MB)
✅ bun run dev starts successfully (verified with --help flag)
✅ bun run smoke passes (version 1.0.0)
✅ bun test runs (338 pass, 33 fail - pre-existing test failures unrelated to build tooling)

Scripts verified for hermes use case:

build, dev, start, smoke, typecheck, test scripts all functional
All acceptance criteria from issue feat: intelligent auto-router — routes to fastest/cheapest provider automatically #2 verified

- Fix permission rule field: expression → ruleContent (Copilot #1) - Handle empty command prefix: skip rule creation (Copilot Twigpine#2) - Remove unused useTheme() import (Copilot Twigpine#3) - Save permission rules under 'Bash' toolName so bashToolHasPermission can match them — Monitor delegates to Bash permission system (Copilot Twigpine#4) - Remove unused logError import from MonitorMcpTask (Copilot Twigpine#6) - Copilot Twigpine#5 (getAppState throws): same pattern as BashTool:915, not a bug

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

…ension Initial VS Code Extension for OpenClaude

* feat: implement Monitor tool for streaming shell output Add the Monitor tool that executes shell commands in the background and streams stdout line-by-line as notifications to the model. This enables real-time monitoring of logs, builds, and long-running processes. Implementation: - MonitorTool (src/tools/MonitorTool/) — spawns LocalShellTask with kind='monitor', returns immediately with task ID - MonitorMcpTask (src/tasks/MonitorMcpTask/) — task lifecycle management and agent cleanup via killMonitorMcpTasksForAgent() - MonitorPermissionRequest — permission dialog component The codebase already had all integration points wired (tools.ts, tasks.ts, PermissionRequest.tsx, LocalShellTask kind='monitor', BashTool prompt). This PR provides the missing implementations. * fix: command-specific permission rule + architecture docs - MonitorPermissionRequest: "don't ask again" now creates a command-prefix rule (like BashTool) instead of a blanket tool-name-only rule that would auto-allow all Monitor commands - MonitorMcpTask: clarify architecture comments explaining why monitor_mcp type exists as a registry stub while actual tasks are local_bash with kind='monitor' * fix: address Copilot review feedback - Fix permission rule field: expression → ruleContent (Copilot #1) - Handle empty command prefix: skip rule creation (Copilot #2) - Remove unused useTheme() import (Copilot #3) - Save permission rules under 'Bash' toolName so bashToolHasPermission can match them — Monitor delegates to Bash permission system (Copilot #4) - Remove unused logError import from MonitorMcpTask (Copilot #6) - Copilot #5 (getAppState throws): same pattern as BashTool:915, not a bug

Addresses the security review on feat/bash-command-safety-classifier. Each finding traced by reviewer is fixed locally; adversarial tests cover each bypass pattern. P0 — parser bypasses (CRITICAL / HIGH): #1 Escaped backslash before close quote — `echo "test\\" && rm -rf /` slipped through as one quoted echo. The prior `input[i-1] !== '\\'` check fails when the backslash itself is escaped. Replaced with an isCharEscaped() helper that counts consecutive backslashes; a quote is escaped only when preceded by an odd count. Applied in BOTH splitCompound AND tokenize so they agree on quote boundaries. #2 Process substitution not detected — `cat <(curl ...)` passed the cat safe gate. tokenize now returns null on `<(` / `>(` same as it did for `$(` / backticks, degrading to 'unknown'. Twigpine#3 Newline as command separator — `echo safe\nrm -rf /` was treated as one line by splitCompound (bash splits on \n = ;). Added \n to the separator list alongside ; | &. P1 — classification bypasses (MEDIUM): Twigpine#4 Sensitive-path denylist — cat/head/tail/less/more/file/stat/wc and readlink/realpath now consult SENSITIVE_PATH_PATTERNS. /etc/shadow, ~/.ssh/id_rsa, /proc/*/environ, /dev/sd*, ~/.aws/credentials, ~/.kube/config, id_rsa / *.pem / *.key etc. degrade to 'unknown'. Public keys (*.pub) and normal files remain safe. Twigpine#5 `git config key value` misclassified — removed `config` from the READ_ONLY_SUBCOMMANDS list and added explicit unsafe gate: two+ positional args with no --get/--list is a set, marked unsafe. --unset / --replace-all / --add / --unset-all also marked unsafe. Single-arg read form falls to 'unknown' (defers to existing rules). Twigpine#6 `git stash` (bare) misclassified — equivalent to `git stash push`, mutates worktree + index. Safe path now requires `git stash list` or `git stash show`; everything else in stash falls to unsafe or unknown. P2 — hygiene (LOW): Twigpine#7 env / printenv removed from ALWAYS_SAFE_COMMANDS. Plain `env` dumps all environment variables (API keys, tokens) to the caller — not safe to auto-approve. FOO=bar cmd idiom still works via the existing env-assignment-prefix stripping. Twigpine#8 git gc / prune / repack / bisect removed from READ_ONLY_SUBCOMMANDS and added to the unsafe gate. gc repacks + deletes loose objects; bisect start/good/bad/reset/run/skip/terms/replay mutate HEAD. Tests: 35 new adversarial cases across all 8 findings, plus regression coverage (public keys still safe, FOO=bar pwd still safe, git stash list/show still safe). Full suite: 1187/1187 pass. PR intent scan: clean. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>

…3.6 shim enhancements - Bug Twigpine#1: Remove isLocalProviderUrl guard on stream_options; always send include_usage - Bug Twigpine#1: Add retry escape hatch when server rejects stream_options with 400 - Bug Twigpine#2: Add isBinaryContent/sanitizeBinaryOutput to prevent ESC sequence injection from raw shell output - Qwen3.6: Add isQwenModel detection, presence_penalty, top_k, chat_template_kwargs, reasoning_content preservation - Docs: Update optimization plan with verified dependency map and low-effort agent task plan

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

…code-extension Initial VS Code Extension for OpenClaude

Addresses the security review on feat/bash-command-safety-classifier. Each finding traced by reviewer is fixed locally; adversarial tests cover each bypass pattern. P0 — parser bypasses (CRITICAL / HIGH): #1 Escaped backslash before close quote — `echo "test\\" && rm -rf /` slipped through as one quoted echo. The prior `input[i-1] !== '\\'` check fails when the backslash itself is escaped. Replaced with an isCharEscaped() helper that counts consecutive backslashes; a quote is escaped only when preceded by an odd count. Applied in BOTH splitCompound AND tokenize so they agree on quote boundaries. #2 Process substitution not detected — `cat <(curl ...)` passed the cat safe gate. tokenize now returns null on `<(` / `>(` same as it did for `$(` / backticks, degrading to 'unknown'. Twigpine#3 Newline as command separator — `echo safe\nrm -rf /` was treated as one line by splitCompound (bash splits on \n = ;). Added \n to the separator list alongside ; | &. P1 — classification bypasses (MEDIUM): Twigpine#4 Sensitive-path denylist — cat/head/tail/less/more/file/stat/wc and readlink/realpath now consult SENSITIVE_PATH_PATTERNS. /etc/shadow, ~/.ssh/id_rsa, /proc/*/environ, /dev/sd*, ~/.aws/credentials, ~/.kube/config, id_rsa / *.pem / *.key etc. degrade to 'unknown'. Public keys (*.pub) and normal files remain safe. Twigpine#5 `git config key value` misclassified — removed `config` from the READ_ONLY_SUBCOMMANDS list and added explicit unsafe gate: two+ positional args with no --get/--list is a set, marked unsafe. --unset / --replace-all / --add / --unset-all also marked unsafe. Single-arg read form falls to 'unknown' (defers to existing rules). Twigpine#6 `git stash` (bare) misclassified — equivalent to `git stash push`, mutates worktree + index. Safe path now requires `git stash list` or `git stash show`; everything else in stash falls to unsafe or unknown. P2 — hygiene (LOW): Twigpine#7 env / printenv removed from ALWAYS_SAFE_COMMANDS. Plain `env` dumps all environment variables (API keys, tokens) to the caller — not safe to auto-approve. FOO=bar cmd idiom still works via the existing env-assignment-prefix stripping. Twigpine#8 git gc / prune / repack / bisect removed from READ_ONLY_SUBCOMMANDS and added to the unsafe gate. gc repacks + deletes loose objects; bisect start/good/bad/reset/run/skip/terms/replay mutate HEAD. Tests: 35 new adversarial cases across all 8 findings, plus regression coverage (public keys still safe, FOO=bar pwd still safe, git stash list/show still safe). Full suite: 1187/1187 pass. PR intent scan: clean. Co-Authored-By: OpenClaude <openclaude@gitlawb.com>

* feat: implement Monitor tool for streaming shell output Add the Monitor tool that executes shell commands in the background and streams stdout line-by-line as notifications to the model. This enables real-time monitoring of logs, builds, and long-running processes. Implementation: - MonitorTool (src/tools/MonitorTool/) — spawns LocalShellTask with kind='monitor', returns immediately with task ID - MonitorMcpTask (src/tasks/MonitorMcpTask/) — task lifecycle management and agent cleanup via killMonitorMcpTasksForAgent() - MonitorPermissionRequest — permission dialog component The codebase already had all integration points wired (tools.ts, tasks.ts, PermissionRequest.tsx, LocalShellTask kind='monitor', BashTool prompt). This PR provides the missing implementations. * fix: command-specific permission rule + architecture docs - MonitorPermissionRequest: "don't ask again" now creates a command-prefix rule (like BashTool) instead of a blanket tool-name-only rule that would auto-allow all Monitor commands - MonitorMcpTask: clarify architecture comments explaining why monitor_mcp type exists as a registry stub while actual tasks are local_bash with kind='monitor' * fix: address Copilot review feedback - Fix permission rule field: expression → ruleContent (Copilot Twigpine#1) - Handle empty command prefix: skip rule creation (Copilot Twigpine#2) - Remove unused useTheme() import (Copilot Twigpine#3) - Save permission rules under 'Bash' toolName so bashToolHasPermission can match them — Monitor delegates to Bash permission system (Copilot Twigpine#4) - Remove unused logError import from MonitorMcpTask (Copilot Twigpine#6) - Copilot Twigpine#5 (getAppState throws): same pattern as BashTool:915, not a bug

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

Per final-review follow-up #1 and #2: 1. docs/ports/bg-agent-view.md — summarizes the bg-agent-view port: - What was ported verbatim / adapted (16 components) - 7 deviations from the original plan with rationale - What was deliberately not ported (per plan §6) - 3 known wiring gaps (DAEMON/BG_SESSIONS feature flags, bg-agents argv wiring) with file:line references - Recommended T12 follow-up plan - How to test locally 2. docs/superpowers/plans/2026-06-13-plan-bg-agent-view.md — committed the plan doc itself so the audit trail is in git history. Previously left untracked in the worktree; reviewers found it hard to find.

… (TDD test #2) Per upstream claude-code 2.1.177, the LLM evaluator gets an immediate "Condition: " prefix on the user message so it knows what to evaluate without parsing context. Non-Stop prompt hooks (UserPromptSubmit etc.) pass the prompt through unchanged to avoid behavior drift. TDD: red in execPromptHook.goal.test.ts (asserts prefix present + before condition text), green via conditional wrap on hookEvent==='Stop'. Step 3 of 5 for /goal Stop-hook prompt port. Refs: opencc-goal-prompt-comparison-audit-2026-06-15

Pre-existing typecheck error at line 234 — gap #2 test (T3) was missing the `(queryModelWithoutStreamingMock as any)` cast that all other gap tests use. Runtime was fine (10 tests pass), but typecheck failed. Confirmed pre-existing via `git stash` (introduced by T3, not by T4-T6). Fix: 1-character `as any` cast on the mock call, consistent with sibling tests (T2 line 198, T4 control line 393, T6 line 432). Refs: opencc-goal-prompt-comparison-audit-2026-06-15

* feat(claude): add Opus 4.8 model support Adds Claude Opus 4.8 alongside 4.7 in the model registry, picker, pricing, integrations, and 1M-context support. Mirrors the established 4.7 pattern so longer suffixes resolve first in canonical-name matching. - configs: CLAUDE_OPUS_4_8_CONFIG + opus48 registry entry - model.ts: canonical resolver, default-model dispatch (1P -> 4.8, 3P bumped to 4.7), display & marketing names - modelOptions: getOpus48Option in PAYG 1P/3P, opusplan description - modelCost: COST_TIER_5_25 pricing - context: 1M-capable assertion - prompts: FRONTIER_MODEL_NAME -> Opus 4.8 - integrations: hicap gateway, nearai brand/vendor/model entries - claude brand catalog: new defineModel block Tests: extends modelSupports1M coverage for 4.8. * fix(models): gate Opus 4.8 out of PAYG 3P picker until rollout Opus 4.8 was being added to the third-party (3P) model picker while getDefaultOpusModel() keeps non-first-party usage on Opus 4.7. Remove the 3P option until 3P rollout is active; first-party picker is unaffected. Addresses CodeRabbit review on #1769. * test(integrations): cover NearAI anthropic/claude-opus-4-8 route Adds focused regression coverage for the new Opus 4.8 provider/model path: asserts the NearAI vendor catalog exposes the anthropic/claude-opus-4-8 entry and that it resolves through its modelDescriptorId to a registered NearAI model descriptor (vendor/brand nearai, correct default model + label), plus the NearAI route base URL. Addresses CodeRabbit's [Minor] request to test the exact route. * fix(models): wire Opus 4.8 into adaptive thinking, 3P fallback, and knowledge cutoff Addresses jatmn's review findings on #1769. - [High] thinking.ts: add opus-4-8 to the adaptive-thinking allowlist. Without it, claude-opus-4-8 hit the generic opus exclusion and returned false, dropping first-party Opus 4.8 into budget-based thinking instead of thinking: { type: 'adaptive' }. Adds a regression test (provider mocked to a non-1P value so the allowlist is the only reason 4.8 returns true). - [Medium] validateModel.ts: add an opus-4-8 -> opus47 entry to get3PFallbackSuggestion so an unavailable Opus 4.8 selection suggests 4.7. - [Medium] prompts.ts: getKnowledgeCutoff now returns "January 2026" for claude-opus-4-8 and claude-opus-4-7 instead of falling through to the stale generic "January 2025". - [Low] modelOptions.ts: update the PAYG 1P picker comment to include Opus 4.8. The betas.ts structured-outputs / auto-mode allowlists are intentionally left unchanged for this PR's scope (4.7 is also absent; auto mode is gated on PI safety probes) — to be revisited with safety-research before enabling. * fix(models): update remaining model-launch markers for Opus 4.8 default Addresses jatmn's follow-up review on #1769 — markers missed when Opus 4.8 became the default. - [P2] commitAttribution.ts: add explicit `opus-4-8` and `opus-4-7` branches to sanitizeModelName before the broad `opus-4` fallback, so commit/PR attribution shows the real model instead of `claude-opus-4`. Adds a focused regression test (commitAttribution.modelName.test.ts; mutation-checked). - [P2] attribution.ts: update the unknown-first-party-model co-author fallback from 'Claude Opus 4.6' to 'Claude Opus 4.8', and the matching test expectation. Also fixed a sibling de-dup test that was passing only by coincidence (it hit the 4.6 fallback): point it at a model the public-name map actually recognizes (dot form) so it exercises the real prefix-dedup path. - [P3] fastMode.ts: FAST_MODE_MODEL_DISPLAY 'Opus 4.6' -> 'Opus 4.8'. - [P3] context.test.ts: update the stale modelSupports1M test title/comment from Opus 4.7 to 4.8 (the current first-party default). * test(models): pin the claude-opus-4-7[1m] sanitizeModelName mapping too CodeRabbit follow-up on #1769: the test covered the suffixed 4.8 path but not the 4.7 branch with the same [1m] session suffix. Add the claude-opus-4-7[1m] case so both newly added mappings are pinned. * fix(models): extend fast-mode + default-effort gates to the current default Opus Addresses jatmn's review on #1769 — two predicates still gated to opus-4-6 only while the default Opus is now 4.8. - [P1] fastMode.ts: isFastModeSupportedByModel returned true only for opus-4-6, so for Max/Team Premium users on claude-opus-4-8 fast mode wouldn't actually enable even though FAST_MODE_MODEL_DISPLAY/the /fast command now say "Opus 4.8 only". Extend the predicate to the fast-mode-capable Opus models (4.8/4.7/4.6). - [P2] effort.ts: getDefaultEffortForModel applied the Pro/Max/Team `medium` default only for opus-4-6, so Pro/Max/Team sessions on the new default claude-opus-4-8 fell through to the generic effort path. Extend the branch to 4.8/4.7/4.6 (per the @[MODEL LAUNCH] marker). Adds regression tests for both (mutation-checked: reverting either predicate to opus-4-6 only fails them). * fix(models): wire Opus 4.8 into advisor, teammate fallback, skill vars, comments Addresses jatmn's follow-up model-launch markers on #1769. - [High] advisor.ts: modelSupportsAdvisor / isValidAdvisorModel only whitelisted opus-4-6 / sonnet-4-6, so first-party sessions on the new default claude-opus-4-8 reported the advisor tool unsupported. Add opus-4-8 and opus-4-7 to both (commands/advisor.ts and claude.ts use these centralized predicates, so they're covered). Adds a regression test (mutation-checked). - [Medium] swarm/teammateModel.ts: getHardcodedTeammateModelFallback hardcoded CLAUDE_OPUS_4_6_CONFIG -> CLAUDE_OPUS_4_8_CONFIG, so new teammates spawn on the current default. Adds a first-party test case (mutation-checked). - [Medium] skills/bundled/claudeApiContent.ts: SKILL_MODEL_VARS OPUS_ID/OPUS_NAME 4.6 -> 4.8 (the bundled claude-api skill docs don't hardcode 4.6 elsewhere). - [Low] effort.ts + figures.ts: refresh stale "max is Opus 4.6 only" comments to reflect the 4.8/4.7/4.6 runtime behavior. * test(swarm): assert provider-aware teammate fallback for Bedrock too CodeRabbit follow-up on #1769: add a non-first-party case so the provider-aware fallback is covered. Bedrock resolves to the Opus 4.8 Bedrock model id. * fix(models): give Opus 4.8/4.7 the elevated output-token limits and 3P fallback chain Addresses jatmn's review on #1769. - context.ts: getModelMaxOutputTokens only gave opus-4-6 the 64k/128k branch, so opus-4-7/4-8 fell through to the generic opus-4 branch and capped at 32k — including the new first-party default Opus 4.8. Extend the elevated branch to 4.8/4.7/4.6. Adds a regression test (mutation-checked). - errors.ts: get3PModelFallbackSuggestion had chains for opus-4-6/sonnet but not opus-4-8/4-7, so the error path suggested no fallback for the new default while validateModel.ts already does. Add opus-4-8 -> opus47 and opus-4-7 -> opus46 to mirror validateModel.ts. * fix(models): allow structured outputs on Opus 4.8/4.7 Addresses jatmn's finding #2 on #1769. modelSupportsStructuredOutputs whitelisted opus-4-1/4-5/4-6 but not 4-7/4-8, so first-party/Foundry requests on the new default Opus 4.8 lost the structured-output support that 4.6 had. Add claude-opus-4-7 and claude-opus-4-8 to the allowlist (4.6 supports it, so the newer Opus models do too). Adds a first-party regression test (mutation-checked). Auto-mode (modelSupportsExternalAutoMode) is intentionally left unchanged — it is gated on separate safety review and was not part of this finding. * fix(models): extend file-read mitigation exemption and effort callout to Opus 4.8/4.7 Addresses jatmn's remaining findings on #1769. - [P2] FileReadTool.ts: MITIGATION_EXEMPT_MODELS only held claude-opus-4-6, so the new default claude-opus-4-8 got the cyber-risk reminder appended to every file read that 4.6 did not — a behavioral regression. Add claude-opus-4-8 and claude-opus-4-7 so the recent Opus models inherit 4.6's exemption. - [P3] EffortCallout.tsx: shouldShowEffortCallout gated the medium-effort-default notification to opus-4-6 only; the same default now applies to opus-4-8, so users on the new default never saw it. Extend the gate to 4.8/4.7/4.6. Adds a regression test (mutation-checked). * fix(models): resolve Opus 4.6→4.8 drift in cost tracking, notifications, and picker strings Addresses jatmn's review on #1769 — remaining model-launch drift now that the first-party default is Opus 4.8. - [P1] modelCost.ts: getModelCosts only applied the elevated fast-mode tier to opus-4-6, so fast-mode Opus 4.8 was billed at the normal COST_TIER_5_25 rate while the picker advertised the fast-mode $30/$150 price. Extend the fast-mode cost check to the fast-mode-capable Opus models (4.8/4.7/4.6). Non-fast usage is unchanged (all three already map to COST_TIER_5_25). Adds a regression test (mutation-checked). - [P2] useModelMigrationNotifications.tsx: "Model updated to Opus 4.6" -> 4.8 (the migration lands users on the opus alias = 4.8 for first party). - [P2] commands/model/model.tsx: the 1M-unavailable error said "Opus 4.6"; made it generic ("Opus with 1M context...") since the gate matches any opus[1m]. - [P2] modelOptions.ts: getOpus46_1MOption is now provider-aware (3P → Opus 4.6, first-party → Opus 4.8); getMaxOpus46_1MOption (always first-party) → Opus 4.8. - [P3] migrateLegacyOpusToCurrent.ts: corrected the stale comment (opus alias resolves to 4.8, not 4.6). * docs(notifs): correct Opus default comment to 4.8 for 1P Comment said 4.6 but the migration notification text and the opus alias both resolve to Opus 4.8 for first-party users. Addresses jatmn P3 review note. * fix(integrations): remove duplicate claude-opus-4-8 descriptor A second claude-opus-4-8 entry (vendorId anthropic) with downgraded 200k/8192 specs duplicated the canonical 1M/128k descriptor. The artifact generator rejects duplicate (id, vendorId) pairs, so integrations:generate failed and smoke-and-tests could not pass. Removed the duplicate; the canonical entry and checked-in generated artifacts are unchanged. Addresses jatmn P1. * fix(models): address Opus 4.8 review — extra-usage label, callout test, stale copy - isBilledAsExtraUsage: recognize opus-4-7/4-8 1M variants, not just 4.6, so the "Billed as extra usage" label shows for the new default and 3P default - EffortCallout modelGate test: drop the unreliable `?ts=` cache-busting import and rely on mock.module live bindings, so the gate runs against the mocked deps on Linux CI (where the query-tagged specifier was not re-evaluated) - refresh stale "Opus 4.6+" effort help text and callout comments to reflect the recent Opus models (4.8/4.7/4.6) the gate now covers * test(effort): make Opus 4.8 callout regression deterministic via pure predicate The behavioral test mocked auth/config/effort and relied on the already-evaluated EffortCallout picking up those mocks, which is order-dependent and failed only in the full Linux CI suite (both the `?ts=` dynamic-import and the static-import variants regressed there). Extract the model check as a pure exported `effortCalloutCoversModel` and assert it directly with no module mocking, so the #1769 regression is covered deterministically on every platform. * test(effort): drop config-dependent 'opus' alias from callout regression test The bare 'opus' alias routes through getDefaultOpusModel(), whose result is environment/config-dependent, so `effortCalloutCoversModel('opus')` was false in a clean Linux CI environment even though the gate logic is correct — that single assertion was the only failure in smoke-and-tests (the explicit-id assertions passed). Assert the gate's opus-4-8/4-7/4-6 coverage with explicit canonical model ids (incl. a [1m] variant) instead, which is deterministic on every platform.

feat: add intelligent smart auto-router with latency/cost scoring

6b163e2

kevincodex1 merged commit 55098bf into Twigpine:main Apr 1, 2026

kevincodex1 pushed a commit that referenced this pull request Apr 2, 2026

Merge pull request #2 from devNull-bootloader/feat/initial-vscode-ext…

a430237

…ension Initial VS Code Extension for OpenClaude

auriti mentioned this pull request Apr 3, 2026

fix: strip Anthropic-specific params from 3P provider paths #258

Closed

2 of 4 tasks

Vasanthdev2004 mentioned this pull request Apr 7, 2026

Improve GitHub Copilot provider: official OAuth onboarding, Copilot API routing, and test hardening and auto refresh token logic #288

Merged

3 tasks done

euxaristia referenced this pull request in euxaristia/openclaude Apr 13, 2026

Merge pull request #2 from gnanam1990/feat/smart-auto-router

ba45b7f

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

euxaristia referenced this pull request in euxaristia/openclaude Apr 13, 2026

Merge pull request #2 from devNull-bootloader/feat/initial-vscode-ext…

db340cc

…ension Initial VS Code Extension for OpenClaude

Vasanthdev2004 mentioned this pull request Apr 13, 2026

fix: bump axios 1.14.0 → 1.15.0 (Dependabot #4, #5) #670

Merged

2 of 3 tasks

FluxLuFFy mentioned this pull request Apr 15, 2026

fix: fixed 76 bugs from security audit (BUGS_README.md) #697

Closed

LifeJiggy mentioned this pull request Apr 20, 2026

feat: add streaming optimizer and structured request logging #703

Merged

1 of 3 tasks

auriti mentioned this pull request Apr 21, 2026

feat(permissions): pattern-based Bash command safety classifier #787

Closed

adrianstanca1 mentioned this pull request Apr 21, 2026

docs: add AGENTS.md and agent workflow guide for AI-assisted edits #766

Closed

fernandoxavier02 mentioned this pull request Apr 22, 2026

Two critical bugs in v0.6.0 make interactive mode unusable with plugin ecosystems #825

Closed

andersonviudes mentioned this pull request Apr 22, 2026

feat(api): expose cache metrics in REPL + normalize across providers #813

Merged

ojungo69 mentioned this pull request Apr 22, 2026

Freeze on prompt input: bash snapshot blocking + secret-tool hang + logForDebugging undefined (Linux) #842

Closed

This was referenced Apr 29, 2026

fix(input): strip leading ! when entering bash mode (#662) #947

Merged

feat: SDK Core — Permission System, Async Context, and Engine Extensions #951

Merged

reymaster pushed a commit to reymaster/openclaude that referenced this pull request May 5, 2026

Merge pull request Twigpine#2 from gnanam1990/feat/smart-auto-router

920deb4

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

reymaster pushed a commit to reymaster/openclaude that referenced this pull request May 5, 2026

Merge pull request Twigpine#2 from devNull-bootloader/feat/initial-vs…

770a780

…code-extension Initial VS Code Extension for OpenClaude

thedeveloloper pushed a commit to thedeveloloper/openclaude that referenced this pull request Jun 8, 2026

Merge pull request Twigpine#2 from gnanam1990/feat/smart-auto-router

b276bf9

feat: intelligent auto-router — routes to fastest/cheapest provider automatically

Gravirei mentioned this pull request Jun 19, 2026

Centralize credential redaction in src/utils/redaction.ts + channel gate tests #1711

Merged

10 tasks done

kevincodex1 mentioned this pull request Jun 24, 2026

fix(update): stop false "development build" block on npm installs with NODE_ENV=development #1781

Merged

euxaristia mentioned this pull request Jun 25, 2026

feat(claude): add Opus 4.8 model support #1769

Merged

8 of 9 tasks

dhlqiang7 mentioned this pull request Jul 2, 2026

Memory Leak: RSS grows ~115 MB/hour while idle (PerformanceMeasure accumulation via Ink reconciler) #1839

Closed

ussoewwin mentioned this pull request Jul 30, 2026

fix(session): persist listing deltas so Moonshot prefix cache survives --resume #2070

Closed

3 of 7 tasks

ussoewwin mentioned this pull request Aug 9, 2026

feat(privacy): strip listing payloads on external transcript egress #2104

Closed

devNull-bootloader mentioned this pull request Aug 15, 2026

Fix/resume task duplicate imports #2130

Closed

Navigation Menu

feat: intelligent auto-router — routes to fastest/cheapest provider automatically - #2

feat: intelligent auto-router — routes to fastest/cheapest provider automatically#2
kevincodex1 merged 1 commit into
Twigpine:mainfrom
gnanam1990:feat/smart-auto-router

gnanam1990 commented Apr 1, 2026

Uh oh!

boofpackdev commented Apr 4, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

gnanam1990 commented Apr 1, 2026

What this adds

The Problem

The Solution: SmartRouter

?? Benchmarks providers on startup

?? Scores every provider

??? Routes intelligently

?? Automatic fallback

?? Learns from real traffic

Usage

.env config

Files

Test

Uh oh!

boofpackdev commented Apr 4, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants