Skip to content

graff — a fast agentic coding harness in Zig: multi-provider, MCP, workflows, DGM evolution loop, TS/Python SDKs

Python

Prepare v0.302.60 release

Rach Pradhana279612f39e4
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 18effefe..f47f4905 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,14 @@ The release workflow uses a tag's section here as its release notes (a
hand-written `docs/releases/<tag>.md` wins if present), so keeping this file
current is part of cutting a release.
+## v0.302.60
+
+- A resumed session keeps the provider's count of its Responses compaction state. A restart no longer re-estimates that opaque state from its size, which could show the context meter far over 100% and force a compaction the session did not need. The count is saved with the session and reapplied only to the same state, provider and model (#1686).
+- The count is learned from chained (WebSocket) replies as well as full requests, so chatgpt-new sessions are counted during normal use.
+- WebSocket accepts events as large as SSE does (128 MiB). A large compaction item over WebSocket previously failed, retried, and fell back to SSE, re-running the turn each time.
+- `GRAFF_CHATGPT_URL` points chatgpt-new at a local mock for testing.
+- Retains all changes from v0.302.59.
+
## v0.302.59
- Large, steadily arriving SSE events no longer trigger false stream stalls or replay a request merely because the next newline has not arrived (#1765).
diff --git a/docs/releases/v0.302.60.md b/docs/releases/v0.302.60.md
new file mode 100644
index 00000000..a557f5a7
--- /dev/null
+++ b/docs/releases/v0.302.60.md
@@ -0,0 +1,12 @@
+# v0.302.60
+
+Compaction state survives a restart.
+
+- **Resumed sessions keep their real context size.** After a Responses provider counts a session's compaction state, that count is saved with the session and reapplied when it is loaded, for the same state, provider and model. A restart used to re-estimate the opaque state from its byte size: in a controlled test an 8 MB state counted at about 80k tokens restored as about 508k, so the meter showed 188% and the next prompt paid for a forced compaction. It now restores at the counted size (#1686, ADR 0307).
+- **WebSocket sessions are counted during normal use.** The count is learned from chained replies (`previous_response_id`) as well as full requests; OpenAI bills the whole chain as input, which is how the meter already reads it. chatgpt-new uses WebSocket by default.
+- **Large compaction items work over WebSocket.** The WebSocket client accepts events up to 128 MiB, matching SSE. A larger item used to fail, retry on a fresh socket, and fall back to SSE, re-running the turn each time.
+- **chatgpt-new can be tested offline.** `GRAFF_CHATGPT_URL` points its Responses endpoint, WebSocket and model discovery at a local mock, as `GRAFF_CODEX_URL` does for codex.
+
+Sessions saved before this release carry no count, so their first reload still estimates the state until the next reply.
+
+Includes all changes from v0.302.59.
diff --git a/scripts/eval/tier1-manifest.json b/scripts/eval/tier1-manifest.json
index 55e0902d..7c4b09de 100644
--- a/scripts/eval/tier1-manifest.json
+++ b/scripts/eval/tier1-manifest.json
@@ -14,7 +14,7 @@
"src/main.zig",
"src/repl.zig"
],
- "test_count_baseline": 3553,
+ "test_count_baseline": 3562,
"test_count_slack": 25,
"required_invariants": [
{
diff --git a/src/cli_text_source.zig b/src/cli_text_source.zig
index 67754b4e..173fb816 100644
--- a/src/cli_text_source.zig
+++ b/src/cli_text_source.zig
@@ -5,6 +5,10 @@
pub const changelog_text =
\\What's new
\\──────────
+ \\0.302.60
+ \\ • a resumed session keeps its real context size instead of re-estimating compaction state
+ \\ • large compaction items work over WebSocket without re-running the turn
+ \\
\\0.302.59
\\ • steadily arriving partial SSE events no longer trigger false stalls or replay
\\ • genuine stalls still time out and unfinished events remain bounded