steve/majordomo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13 Commits 8 Branches 0 Tags
1029feb0c723f54867fc75b60f056c0ab4be8cfe
Commit Graph

13 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
steve 1029feb0c7 docs: record Phase 9 completion — mort conversion PR open
CI / Tidy (push) Successful in 9m33s
Details
CI / Build & Test (push) Successful in 10m36s
Details 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 18:08:53 +02:00
steve 7c760005f5 docs: README coverage for resolvers, DefineTool, agent hooks, ops controls
CI / Build & Test (push) Successful in 10m8s
Details
CI / Tidy (push) Successful in 9m25s
Details 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:34:29 +02:00
steve 0147a79d18 feat: conversion-driven extensions — resolvers, DefineTool, hooks, ops controls
CI / Tidy (push) Successful in 9m31s
Details
CI / Build & Test (push) Successful in 10m13s
Details 
Phase 9a (ADR-0014): Registry.RegisterResolver for dynamic tiers;
DefineTool[Args] typed tools; Usage cache/reasoning detail fields wired
through anthropic/openai/google; WithPromptCaching (Anthropic
cache_control); agent supervision hooks (WithMaxStepsFunc, WithSteer,
WithCompactor, WithToolErrorLimits + ErrToolLoop); health
Bench/Unbench/Snapshot; ChainConfig.Observer failover events.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:30:06 +02:00
steve 04b21fdad2 feat: live-validated against Ollama Cloud; schema instruction fallback for cloud 
Phase 8: all six live checks pass (tier aliases, thinking-tier chat, real
tool invocation, structured Generate[T], forced failover with bench+skip,
skill agent). Discovery: ollama.com ignores the format field — the
provider now also states the schema as a system instruction (constrained
decoding locally, instruction-guided JSON on cloud), with hermetic test.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:22:54 +02:00
steve 97513141dc docs: examples for every hard requirement + mort migration blueprint 
Phase 7: nine runnable examples/ programs (parse, failover chains with
trailing alias, tiers, LLM_* env providers, multimodal, tool loop,
Generate[T], agent, skills); docs/mort-migration.md mapping mort's
go-llm/go-agentkit usage onto majordomo APIs with the planned additive
library extensions and conversion order; README finalized with the
complete matrix.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:17:20 +02:00
steve 76ecf0e49e feat: skills — additive instruction+tool bundles, clock + calc examples 
Phase 6: skill.New constructor satisfying the agent.Skill contract;
instruction-only skills; ordered additive composition; skill/clock
(injectable-clock time tools) and skill/calc (recursive-descent arithmetic
evaluator) as ready-made examples with full test suites incl. an
agent-loop round trip. ADR-0013; README skills section + matrix synced.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:13:07 +02:00
steve 7dab4112ff feat: agent run loop, Generate[T], reflect-derived schemas 
Phase 5:
- agent/: model + system prompt + toolboxes composition; bounded
  tool-dispatch loop (default 10 steps); panic-proof tool execution;
  unknown-tool and duplicate-name handling; history continuation; step
  observers; partial results on ErrMaxSteps/errors (ADR-0012)
- llm.SchemaFor[T]: strict-compatible JSON schemas from Go types
  (nullable pointers, description/enum tags, recursion rejected)
- majordomo.Generate[T]: typed structured output with fence-stripping
  decode and model-naming errors
- README agents/structured-output sections + matrix synced

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:10:18 +02:00
steve 1ca607906d feat: Google (Gemini) provider on the official Gen AI SDK 
Phase 4: provider/google on google.golang.org/genai v1.59.0 — lazy cached
client, FunctionResponse tool loop, raw-JSON-schema tools and structured
output, ThinkingLevel reasoning mapping, iter.Pull2 streaming, hermetic
httptest suite via HTTPOptions.BaseURL. Registry wires google + gemini
schemes to the real client; stub machinery deleted (all built-ins real).
ADR-0011; README matrix + CLAUDE.md synced.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 13:04:28 +02:00
steve 043249e0e1 feat: OpenAI, Anthropic, and native-Ollama providers + media pipeline 
Phase 3:
- provider/openai: Chat Completions for OpenAI + compat endpoints (SSE
  streaming with by-index tool-call assembly, response_format json_schema,
  legacy max_tokens option, reasoning_effort)
- provider/anthropic: Messages API (tool_use/tool_result, GA structured
  output via output_config.format, full SSE event parser, 529 transient)
- provider/ollama: one native /api/chat client behind the ollama,
  ollama-cloud, and foreman built-ins (presets; NDJSON streaming tolerant
  of foreman's buffered single-object responses; object tool arguments;
  format-schema structured output; think mapping)
- media/: capability normalization (sniff, downscale, transcode, byte
  ladder, ErrUnsupported), wired into the chain executor per target with
  penalty-free advance past incapable elements
- registry: real provider + scheme wiring, WithHTTPClient option, required
  env-foreman TLS chat round-trip test
- ADR-0009 multimodal strategy, ADR-0010 tools/structured mapping; README
  matrix + CLAUDE.md synced

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 12:58:08 +02:00
steve 323558ed72 feat(llm): ReasoningEffort request option and ErrUnsupported sentinel 
Groundwork for the provider phase: reasoning levels map to native knobs
(OpenAI reasoning_effort, Ollama think); ErrUnsupported marks declared
capability mismatches that chains advance past without health penalty.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 12:40:47 +02:00
steve 0d0e8e069e test: deterministic failover matrix — cooldown re-admission, alias chains, policies 
Phase 2: proves ADR-0006/0008 semantics end to end with the fake provider
and fake clock (cooldown expiry, backoff growth, inline-alias failover,
permanent-error policies, retry budgets, bench-mid-request, exhaustion
reporting, custom classifier, chain-of-one parity).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 12:37:32 +02:00
steve dcd004289f feat: foundations — canonical types, Parse grammar, env DSNs, health, chains 
Phase 1 of the majordomo build:
- llm/ canonical contract (messages, parts, tools, capabilities, streaming,
  Model/Provider, error classification)
- health/ clock-injected tracker (threshold bench, exponential capped
  cooldown, reset-on-success)
- root Registry + Parse (verbatim model ids, inline recursive alias
  expansion with cycle detection, chain dedup), LLM_* env-DSN providers
  (go-llm parity: lazy fallback + eager LoadEnv), health-aware chain
  executor behind the Model interface
- provider/fake scriptable test provider; hermetic test suite incl. the
  trailing-thinking chain and foreman:// env loading
- ADRs 0001-0008, CLAUDE.md, README (honest matrix), CI workflow,
  docs/phase-1-design.md

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 12:35:34 +02:00
steve 3025044817 Initial commit 2026-06-10 09:21:08 +00:00