@bolt-foundry/gambit 0.8.1 → 0.8.3

package/CHANGELOG.md

@@ -1,14 +1,90 @@
 +++
 [release]
-since = "769d3de436e4542ed7d0d80201f665657d93efb2"
+since = "849762245925cce325c04da1d604088370ec3723"
 +++
 
 # Changelog
 
-## Unreleased (v0.8.2)
+## Unreleased (v0.8.4)
 
 - TBD
 
+## v0.8.3
+
+- fix(gambit): include CLI docs/reference files in binary builds
+- chore(infra): run the Gambit compile check during `bft gambit:release`
+
+## v0.8.2
+
+- chore(gambit): release 0.8.1
+- revert(gambit): back out Open Responses runtime
+- fix(gambit): resolve gambit-core include paths
+- docs(gambit): add ABOUT files and move public posts
+- docs(gambit): split external docs and align readmes
+- docs(gambit): add ABOUT/README pairs for doc hubs
+- Phase 0: rename deck schema terms
+- feat(gambit-core): add Open Responses v1 types
+- feat(gambit): add OpenRouter responses adapter and flag
+- test(gambit): add OpenRouter provider conformance coverage
+- docs(gambit): document responses flag and Phase 2 progress
+- test(gambit): fix lint in OpenRouter provider tests
+- fix(gambit): preserve response parts and validate tool schemas
+- feat(gambit): add responses mode for runtime/state
+- fix(gambit): preserve optional tool args in responses schemas
+- fix(gambit): avoid coercing non-type tool schemas
+- fix(gambit): only normalize object tool schemas
+- test(gambit): add responses CLI smoke coverage
+- docs(gambit): expand phase 4 checklist
+- docs(gambit): note phase 4 test-bot validation
+- docs(gambit): note 0.8.2 release plan
+- docs(gambit): expand phase 5 checklist
+- chore(gambit): set 0.8.2-dev version
+- chore(gambit-core): align version to 0.8.2-dev
+- fix(gambit): widen context tool name set types
+- [gambit] update simpsons explainer example
+- [gambit] extract Test Bot page and shared helpers
+- [gambit] test bot page updates
+- [gambit] refactor headers/nav, add Button component
+- fix(gambit-core): treat empty responses output as empty string
+- chore(gambit): align grader models and schemas
+- docs(gambit): align openresponses migration status
+- refactor(gambit): move chat compat out of core
+- refactor(gambit): move chat compat out of core
+- fix(simulator-ui): stabilize test bot nav handlers
+- chore(simulator-ui): bundle favicon for distribution
+- refactor(simulator-ui): extract calibrate page
+- feat(simulator-ui): standardize simulator page layout
+- docs(gambit): defer phase 5 and move migration tracker
+- docs(docs): align docs structure and links
+- docs(gambit): add internal project and post docs
+- docs reorg
+- feat(gambit): wire init chat flow and init-only tools
+- feat(simulator-ui): add icon system and grader UI polish
+- refactor(simulator-ui): rename calibrate route to grade
+- refactor(simulator-ui): rename test bot labels to test
+- refactor(simulator-ui): drop copy ref button
+- refactor(simulator-ui): drop reference sample overlays
+- refactor(simulator-ui): simplify raw input details
+- refactor(simulator-ui): remove session metadata display
+- docs(gambit): update simulator links for test/grade
+- feat(simulator-ui): make run header toggleable with icon cue
+- fix(simulator-ui): normalize color tokens
+- chore(simulator-ui): add "+" to positive scores
+- feat(simulator-ui): add status badge component
+- feat(simulator-ui): refine calibrate summary cards
+- feat(simulator-ui): refine tool call display
+- fix(simulator-ui): format json consistently
+- nits(simulator-ui): small tweaks
+- docs(gambit): document Gambit-first strategy shift
+- feat(gambit): add ollama provider routing
+- feat(gambit): auto-pull missing ollama models
+- feat(gambit): add model availability check
+- infra: add obsidian bft command and fix gambit check mocks
+- fix(gambit): include handler decks in model check
+- feat(gambit): add gambit.toml model aliases
+- feat(gambit): default responses mode with chat fallback
+- fix(gambit): publish scaffolds for jsr demo/init commands
+
 ## v0.8.1
 
 - fix(gambit): include gambit-core cards/schemas in compiled binary

package/README.md

@@ -1,6 +1,7 @@
 # <img src="./gambit_1color_bg.png" alt="Gambit logo" height="50" />
 
-Gambit helps you build reliable LLM workflows by composing small, typed “decks”\
+Gambit is an open-source, developer-first framework that helps you build\
+reliable LLM workflows by composing small, typed “decks”\
 with clear inputs/outputs and guardrails. Run decks locally, stream traces, and\
 debug with a built-in UI.
 
@@ -148,12 +149,13 @@ http://localhost:8000/
 It also serves:
 
 ```
-http://localhost:8000/test-bot
-http://localhost:8000/calibrate
+http://localhost:8000/test
+http://localhost:8000/grade
 ```
 
 The Debug UI shows transcript lanes plus a trace/tools feed. If the deck has an\
-`inputSchema`, the UI renders a schema-driven form with defaults and a raw JSON\
+`contextSchema`, the UI renders a schema-driven form with defaults and a raw
+JSON\
 tab. Local-first state is stored under `.gambit/` (sessions, traces, notes).
 
 ## Using the Library
@@ -166,7 +168,7 @@ Import the helpers from JSR:
 import { defineDeck, defineCard } from "jsr:@bolt-foundry/gambit";
 ```
 
-Define `inputSchema`/`outputSchema` with Zod to validate IO, and implement\
+Define `contextSchema`/`responseSchema` with Zod to validate IO, and implement\
 `run`/`execute` for compute decks. To call a child deck from code, use\
 `ctx.spawnAndWait({ path, input })`. Emit structured trace events with\
 `ctx.log(...)`.
@@ -204,8 +206,8 @@ import { z } from "zod";
 
 export default defineDeck({
   label: "echo",
-  inputSchema: z.object({ text: z.string() }),
-  outputSchema: z.object({ text: z.string(), length: z.number() }),
+  contextSchema: z.object({ text: z.string() }),
+  responseSchema: z.object({ text: z.string(), length: z.number() }),
   run(ctx) {
     return { text: ctx.input.text, length: ctx.input.text.length };
   },
@@ -242,8 +244,8 @@ import { z } from "zod";
 
 export default defineDeck({
   label: "get_time",
-  inputSchema: z.object({}), // no args
-  outputSchema: z.object({ iso: z.string() }),
+  contextSchema: z.object({}), // no args
+  responseSchema: z.object({ iso: z.string() }),
   run() {
     return { iso: new Date().toISOString() };
   },
@@ -256,6 +258,26 @@ Run it:
 npx @bolt-foundry/gambit run ./agent_with_time.deck.md --context '"hello"' --stream
 ```
 
+### Respond flow demo (non-root decks + grading)
+
+Need a turnkey scenario that hits personas → init → non-root `gambit_respond`
+payloads → graders? Use the example in `packages/gambit/examples/respond_flow/`.
+
+```
+cd packages/gambit
+npx @bolt-foundry/gambit serve ./examples/respond_flow/decks/root.deck.ts --port 8000
+```
+
+Then:
+
+1. Open `http://localhost:8000/test`, pick the **Escalation persona**, and run
+   it. Leave the “Use test deck input for init” toggle on to see persona data
+   seed the init form automatically.
+2. Switch to the Debug tab to inspect the session—the child deck emits a
+   `gambit_respond` payload that now shows up as a structured assistant turn.
+3. Head to the Calibrate tab and run the **Respond payload grader** to exercise
+   grading on the non-root respond output.
+
 ## Deno
 
 If you prefer Deno, use the Deno commands below.