summaryrefslogtreecommitdiff
path: root/internal/llm/provider.go
AgeCommit message (Collapse)Author
2026-06-11Consolidate LLM timeout/retry/breaker values into policy packagePaul Buetow
The per-request HTTP timeouts (30s chat, 120s research), retry policy (attempts, backoff, jitter), and circuit-breaker tuning (threshold, cooldown) were previously scattered as bare literals across each provider constructor and resilience.go/circuitbreaker.go, making the operational policy hard to discover and prone to drift. Introduce internal/llm/policy with documented named constants as the single source of truth, and reference them from all provider constructors, the default retry policy, and the shared circuit breaker. Update comments to explain the policy and reasoning. Add tests validating the values and their internal consistency. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-10Replace panics with returned errors in llm.RegisterProviderPaul Buetow
RegisterProvider now returns an error for an empty name, a nil factory, or a duplicate registration instead of panicking, making registration composable and testable without recover(). RegisterAllProviders caches the one-time registration error (sync.Once cannot return a value) and returns it to every caller. Updated all call sites: hexailsp, hexaicli and hexaiaction propagate the error with context; test TestMains fail fast via panic. Added unit tests covering empty name, nil factory, duplicate, success and idempotent re-registration. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-20Add YouSearch (You.com Research API) provider integrationPaul Buetow
Amp-Thread-ID: https://ampcode.com/threads/T-019e45ff-4976-750c-b2e6-121d0e5991ef Co-authored-by: Amp <amp@ampcode.com>
2026-04-26feat: default to Ollama Cloud (kimi-k2.6) when no provider configuredPaul Buetow
Switches the in-code defaults so that hexai talks to Ollama Cloud (https://ollama.com) with model kimi-k2.6 when no provider is configured, instead of OpenAI. The example config, README, and configuration guide all reflect the new recommended setup; previous OpenAI / local-Ollama options are still documented as alternatives. Tests that depended on the implicit "openai" default now pin the provider explicitly so they continue to exercise the OpenAI / gpt-5 code paths they were designed to cover. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-26feat: optional API key for Ollama provider (Ollama Cloud)Paul Buetow
Adds an optional HEXAI_OLLAMA_API_KEY (with OLLAMA_API_KEY fallback) so the existing Ollama provider can target Ollama Cloud (ollama.ai) in addition to a local server. When the key is empty the request is unauthenticated, preserving local-server behavior byte-for-byte; when set, an Authorization: Bearer header is attached for both Chat and ChatStream. Documented cloud usage in config.toml.example. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-03-23chore: bump version to v0.25.9v0.25.9Paul Buetow
Code quality fixes from audit: - Log silently discarded errors in status sinks and stats.Update call sites - Fix json.Marshal errors silently ignored in LSP handlers - Replace time.Sleep in tests with channel signaling (mcp) and fake clock (stats) - Make context cancellation work in production time.Sleep sites (handlers_document, cmdentry) - Remove init()-based provider registration from llm package; use explicit RegisterAllProviders() - Add WaitGroup goroutine tracking to MCP server Run() Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-23fix: code quality improvements across lsp, askcli, appconfig, integrationtestsPaul Buetow
- lsp/handlers_completion.go: track collectFirstCompletion goroutine in inflight WaitGroup (goroutine leak fix) - lsp/transport.go: use %w instead of %v for error wrapping - askcli/command_list.go: extract handleListWithFilters shared helper; handleList/handleAll/handleReady are now single-liners - askcli/command_list.go, urgency.go, dep.go: log ParseTaskExport errors to stderr instead of returning 1 silently - appconfig/config_load.go: rename 'any' variable to 'found' to avoid shadowing the built-in identifier - llm/provider.go: add explanatory comment for package-level registry - integrationtests/ask_test.go: add //go:build integration tag; move repoRoot init from init() to TestMain with diagnostic error message Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-19Improve actionable error guidancePaul Buetow
2026-03-16Replace Summary: prefixes with standard Go package doc commentsPaul Buetow
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16Add doc comments to exported types and functionsPaul Buetow
Document ~30 exported types in lsp/types.go and exported functions in llm/provider.go, lsp/server.go, and hexailsp/run.go. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02llm: add provider registry and self-registration factories (task 410)Paul Buetow
2026-02-06Remove GitHub Copilot provider supportpaul@buetow.org
Remove all GitHub Copilot integration from the codebase to streamline the supported provider set to OpenAI, OpenRouter, Anthropic, and Ollama. Changes: - Delete core Copilot implementation (copilot.go) and all related tests - Remove Copilot configuration fields from App struct and Config - Remove Copilot from provider factory and API key handling - Update all test files to replace Copilot references with other providers - Remove Copilot documentation from README, configuration guide, and examples - Remove Copilot section from config.toml.example All tests pass successfully after removal. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-01-31feat: add configurable request timeout for LLM callsFlorian
Local LLMs (LM Studio, Ollama, etc.) often need more than the default 30-second timeout. Added request_timeout config option (in seconds) to [general] section and HEXAI_REQUEST_TIMEOUT env var. Original constructor signatures preserved via *WithTimeout variants, so no test changes required.
2026-01-29feat: add native Anthropic API provider supportPaul Buetow
- Implement new anthropicClient with full Client interface - Add Streamer interface for token-by-token streaming via SSE - Add Anthropic Messages API v1 integration with proper headers - Support claude-3-5-sonnet-20241022 as default model - Add configuration via [anthropic] TOML section - Add environment variable overrides (HEXAI_ANTHROPIC_*) - Support both HEXAI_ANTHROPIC_API_KEY and ANTHROPIC_API_KEY fallback - Integrate Anthropic key handling in LSP, CLI, and llmutils - Update provider factory to support 'anthropic' provider name - Add 11 comprehensive unit tests for Anthropic client - Update config.toml.example with [anthropic] section - Update NewFromConfig() signature to accept anthropicAPIKey parameter - All 51 internal LLM tests pass (11 new Anthropic tests + 40 existing) Anthropic models can be accessed via: [anthropic] model = "claude-3-5-sonnet-20241022" base_url = "https://api.anthropic.com/v1" temperature = 0.2 or environment: export HEXAI_PROVIDER="anthropic" export HEXAI_ANTHROPIC_API_KEY="your-key" Amp-Thread-ID: https://ampcode.com/threads/T-019c0af1-f215-72cf-9940-b014b1a9576b Co-authored-by: Amp <amp@ampcode.com>
2025-10-02feat: add OpenRouter providerv0.15.0Paul Buetow
2025-09-17chore(version): bump to v0.11.1 (gpt-5 defaults, timeouts, global stats, ↵v0.11.1Paul Buetow
editor fix)
2025-09-06use gofumptPaul Buetow
2025-08-28copilot: add session token + codex code completion; lsp: prefer native ↵v0.3.0Paul Buetow
CodeCompleter with chat fallback; remove obsolete throttle path; add tests; bump version to 0.3.0
2025-08-18feat(config): per-provider temperature defaults and docs\n\n- Add , , to ↵Paul Buetow
config with coding-friendly default 0.2.\n- Wire defaults through providers (OpenAI, Copilot, Ollama).\n- Update CLI and LSP runners to pass configured temperatures.\n- Document temperature behavior and examples in README.\n- Update config.json.example to show new keys.
2025-08-17review changesPaul Buetow
2025-08-17cli+lsp: refactor main packages into internal runners; add testsPaul Buetow
- Move CLI logic to internal/hexaicli with Run/RunWithClient - Move LSP logic to internal/hexailsp with Run/RunWithFactory - Extract helpers; keep behavior identical for both binaries - Add unit tests for hexaicli (input parsing, messages, streaming) and hexailsp (factory wiring, client creation, logging settings) - Add top-of-file summaries and 'Not yet reviewed by a human' comments to all Go files - Update README with internal package docs
2025-08-17cli: stream responses in hexai when supported (OpenAI, Ollama)Paul Buetow
- Add llm.Streamer optional interface - Implement ChatStream for OpenAI (SSE) and Ollama (JSON stream) - CLI uses streaming; LSP unchanged (non-streaming) - README: document streaming behavior for CLI
2025-08-17llm: add GitHub Copilot providerPaul Buetow
- Implement copilot client reading COPILOT_API_KEY - Wire copilot_base_url and copilot_model config - Update README and config example; defaults to gpt-4.1 - Keep OpenAI default at gpt-4.1 for consistency
2025-08-17lsp/config: make completion trigger characters configurablePaul Buetow
- Add trigger_characters to JSON config and ServerOptions - Store on server and advertise in initialize - Update README and example config - Preserve previous defaults when unset
2025-08-16refactor(config): drop env-based config (except OPENAI_API_KEY)Paul Buetow
- Switch to config-file-only; only OPENAI_API_KEY read from env.\n- llm: replace env autodetect with Config + NewFromConfig; add newOpenAI/newOllama.\n- lsp: NewServer now accepts injected llm.Client.\n- cli: remove env overrides; extend appConfig with provider-specific fields; build client from config + OPENAI_API_KEY.\n- docs: update README (config-only, defaults to OpenAI, minimal example); simplify flags table.\n- add config.json.example.\n- prompts: enforce ;text; (no spaces) and add ;;text; to remove entire line; tests added.
2025-08-16feat(llm): add Ollama provider + provider selection and CLI override; update ↵v0.0.1Paul Buetow
README and logs
2025-08-16logging: migrate LSP logs to global singleton (internal/logging); use ↵Paul Buetow
consistent colors/prefix; refactor LLM provider to use global logger and remove per-client loggers
2025-08-16llm: centralize ANSI color and logging helpers in logging.go; remove ↵Paul Buetow
duplicate color constants from openai.go
2025-08-16logging: add -log-preview-limit flag with HEXAI_LOG_PREVIEW_LIMIT env; wire ↵Paul Buetow
through llm.SetLogPreviewLimit; document in README
2025-08-16llm: add pluggable provider with OpenAI default; extensive logging; LSP ↵Paul Buetow
completion integration with TextEdit, param-aware prompts; remove idle gating; label/filter improvements; docs update
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-19 21:23:45 +0000