docs: rewrite the documentation for proxy server, authentication, and concepts#32
Draft
pratik-mahalle wants to merge 4 commits intokreuzberg-dev:mainfrom
Draft
Conversation
- Add docs/server/proxy-server.md: CLI flags, endpoint table, Tower middleware diagram, Docker/TLS/CORS deployment notes, curl snippets - Add docs/server/proxy-configuration.md: full TOML reference for all config tables ([server], [general], [[models]], [[aliases]], [[keys]], [rate_limit], [budget], [cache], [files], [health], [cooldown]) - Add docs/server/mcp-server.md: 22 tools grouped by category, stdio and HTTP transports, Claude Desktop and Cursor config examples - Add docs/usage/error-handling.md: canonical 17-variant error taxonomy, retry semantics, HTTP-status mapping, tabbed per-language examples - Add 26 snippet files wired via --8<-- includes - Audit all 11 language API ref error sections: correct fabricated exception hierarchies in ruby.md, elixir.md, php.md, wasm.md; add missing BudgetExceeded/HookRejected variants throughout - Update zensical.toml nav: Server tab (3 pages), Error Handling under Usage
- Add docs/usage/authentication.md: Azure AD client-credentials flow, AWS Bedrock STS web identity (IRSA), Vertex AI service-account JWT assertion; env var tables sourced from auth/*.rs; static token provider; proxy TOML examples - Add docs/usage/observability.md: TracingLayer GenAI semantic convention attributes, per-language tracing enable snippets, OTEL exporter wiring with otel feature flag, CostTrackingLayer, Tower layer composition order - Add docs/usage/fallback-routing.md: FallbackLayer transient-only trigger semantics, Router with all 5 strategies (RoundRobin, Fallback, LatencyBased EMA alpha=0.3, CostBased, WeightedRandom), streaming buffer warning, proxy fallbacks config - Update docs/usage/configuration.md: replace Tracing section with a git add .! note stub pointing to observability.md - Update zensical.toml nav: add Authentication, Observability, Fallback & Routing under Usage
…cost, chat expansion - Add docs/concepts/architecture.md: crate graph, Tower middleware stack diagram with layer table and request lifecycle sequenceDiagram, language binding strategy table, proxy structure - Add docs/concepts/feature-flags.md: all 11 flags from Cargo.toml:17-62 with purpose, dependencies, and binary-size guidance - Add docs/concepts/tokenizer.md: count_tokens() and count_request_tokens() API, model-prefix-to-HuggingFace-repo mapping table, two-phase cache locking behavior - Add docs/concepts/cost-estimation.md: completion_cost() and model_pricing() API, prefix-fallback resolution, response-level estimated_cost(), tracing and proxy budget integration - Expand docs/usage/chat.md: add sections for reasoning_effort (o-series and extended-thinking), JSON schema structured outputs, extra_body passthrough, audio content parts (input_audio), AWS EventStream streaming note with Tower buffer warning - Update zensical.toml nav: add Concepts tab with 4 pages
pratik-mahalle
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request updates error handling documentation across multiple language bindings to clarify the mapping between liter-llm’s canonical 17 error variants and each binding’s exception or error types. It adds detailed tables for each language, explains transient error handling, and provides direct links to the shared Error Handling guide. Additionally, it updates the project changelog to follow Keep a Changelog format and documents recent and unreleased changes.
Error handling documentation improvements:
BudgetExceeded,HookRejected, and improved provider error handling. [1] [2] [3] [4] [5]Changelog and project metadata:
docs/CHANGELOG.mdto follow Keep a Changelog format, added detailed entries for versions 1.2.0, 1.1.1, 1.1.0, and 1.0.0, and documented unreleased changes.Tooling and versioning:
.ruby-versionfrom 3.4.8 to 3.3.6.(as the test were failing)These changes ensure that users of all supported language bindings have clear, consistent guidance on programmatic error handling and retry logic, and that the project changelog is up-to-date and standardized.